{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-retrieval","name":"Image Retrieval","slug":"image-retrieval","description_markdown":"**Image Retrieval** is a fundamental and long-standing computer vision task that involves finding images similar to a given query from a large database. It is often considered a form of fine-grained, instance-level classification. The task is integral to image recognition alongside [classification](/task/image-classification) and [cross-modal retrieval](/task/cross-modal-retrieva). By leveraging visual similarity and other criteria, image retrieval enables users to efficiently discover relevant images, making it a crucial tool in applications such as search and recommendation.\r\n\r\n<span class=\"description-source\">[Extending CLIP for Category-to-image Retrieval in E-commerce](https://arxiv.org/abs/2112.11294)</span>\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [DELF](https://github.com/tensorflow/models/tree/master/research/delf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2239,"papers_with_code":835,"benchmarks":56,"benchmark_tables_in_archive":56,"benchmark_tables_shown":56,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":87,"subtasks":10,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/image-retrieval-on-roxford-hard","slug":"image-retrieval-on-roxford-hard","dataset":"ROxford (Hard)","dataset_url":"/dataset/roxford","rows_in_archive":23,"metrics":["mAP"],"first_row_in_archive_order":{"model":"SuperGlobal","paper_title":"Global Features are All You Need for Image Retrieval and Reranking","paper_url":"/paper/global-features-are-all-you-need-for-image","paper_date":"2023-08-14","arxiv_id":"2308.06954","code_links":[{"title":"shihaoshao-gh/superglobal","url":"https://github.com/shihaoshao-gh/superglobal"},{"title":"edwardguil/CVNet","url":"https://github.com/edwardguil/CVNet"}],"syntology":{"n":18,"n_ran":14,"n_constructed":9,"n_ran_checked":12,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/global-features-are-all-you-need-for-image#ran","syntology_url":"https://syntology.ai/paper/2308.06954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06954"}},"official":{"repos":["shihaoshao-gh/superglobal"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":9,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-roxford-medium","slug":"image-retrieval-on-roxford-medium","dataset":"ROxford (Medium)","dataset_url":"/dataset/roxford","rows_in_archive":23,"metrics":["mAP"],"first_row_in_archive_order":{"model":"AMES","paper_title":"AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval","paper_url":"/paper/2408-03282","paper_date":"2024-08-06","arxiv_id":"2408.03282","code_links":[{"title":"pavelsuma/ames","url":"https://github.com/pavelsuma/ames"}],"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-03282#ran","syntology_url":"https://syntology.ai/paper/2408.03282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03282"}},"official":{"repos":["pavelsuma/ames"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-rparis-hard","slug":"image-retrieval-on-rparis-hard","dataset":"RParis (Hard)","dataset_url":null,"rows_in_archive":23,"metrics":["mAP"],"first_row_in_archive_order":{"model":"AMES","paper_title":"AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval","paper_url":"/paper/2408-03282","paper_date":"2024-08-06","arxiv_id":"2408.03282","code_links":[{"title":"pavelsuma/ames","url":"https://github.com/pavelsuma/ames"}],"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-03282#ran","syntology_url":"https://syntology.ai/paper/2408.03282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03282"}},"official":{"repos":["pavelsuma/ames"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-rparis-medium","slug":"image-retrieval-on-rparis-medium","dataset":"RParis (Medium)","dataset_url":null,"rows_in_archive":23,"metrics":["mAP"],"first_row_in_archive_order":{"model":"AMES","paper_title":"AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval","paper_url":"/paper/2408-03282","paper_date":"2024-08-06","arxiv_id":"2408.03282","code_links":[{"title":"pavelsuma/ames","url":"https://github.com/pavelsuma/ames"}],"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-03282#ran","syntology_url":"https://syntology.ai/paper/2408.03282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03282"}},"official":{"repos":["pavelsuma/ames"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-crepe-vision-language","slug":"image-retrieval-on-crepe-vision-language","dataset":"CREPE (Compositional REPresentation Evaluation)","dataset_url":"/dataset/crepe-vision-language","rows_in_archive":22,"metrics":["Recall@1 (HN-Atom + HN-Comp, SC)","Recall@1 (HN-Atom + HN-Comp, UC)","Recall@1 (HN-Atom, UC)","Recall@1 (HN-Comp, UC)"],"first_row_in_archive_order":{"model":"ViT-L-14 (LAION400M)","paper_title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","paper_url":"/paper/crepe-can-vision-language-foundation-models","paper_date":"2022-12-13","arxiv_id":"2212.07796","code_links":[{"title":"raivnlab/crepe","url":"https://github.com/raivnlab/crepe"}],"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crepe-can-vision-language-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.07796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07796"}},"official":{"repos":["raivnlab/crepe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-fashion-iq","slug":"image-retrieval-on-fashion-iq","dataset":"Fashion IQ","dataset_url":"/dataset/fashion-iq","rows_in_archive":22,"metrics":["(Recall@10+Recall@50)/2","Recall@10"],"first_row_in_archive_order":{"model":"DQU-CIR","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-flickr30k-1k-test","slug":"image-retrieval-on-flickr30k-1k-test","dataset":"Flickr30K 1K test","dataset_url":"/dataset/flickr30k","rows_in_archive":18,"metrics":["R@1","R@5","R@10"],"first_row_in_archive_order":{"model":"X-VLM (base)","paper_title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","paper_url":"/paper/multi-grained-vision-language-pre-training","paper_date":"2021-11-16","arxiv_id":"2111.08276","code_links":[{"title":"zengyan-97/x-vlm","url":"https://github.com/zengyan-97/x-vlm"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-grained-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2111.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08276"}},"official":{"repos":["zengyan-97/x-vlm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-cirr","slug":"image-retrieval-on-cirr","dataset":"CIRR","dataset_url":"/dataset/cirr","rows_in_archive":17,"metrics":["(Recall@5+Recall_subset@1)/2","Recall@10"],"first_row_in_archive_order":{"model":"TMCIR","paper_title":"TMCIR: Token Merge Benefits Composed Image Retrieval","paper_url":"/paper/tmcir-token-merge-benefits-composed-image","paper_date":"2025-04-15","arxiv_id":"2504.10995","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-sop","slug":"image-retrieval-on-sop","dataset":"SOP","dataset_url":"/dataset/stanford-online-products","rows_in_archive":14,"metrics":["R@1"],"first_row_in_archive_order":{"model":"Unicom+ViT-L@336px","paper_title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","paper_url":"/paper/unicom-universal-and-compact-representation","paper_date":"2023-04-12","arxiv_id":"2304.05884","code_links":[{"title":"OML-Team/open-metric-learning","url":"https://github.com/OML-Team/open-metric-learning"},{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"},{"title":"RocketFlash/easy_metric_learning","url":"https://github.com/RocketFlash/easy_metric_learning/tree/master/tools"}],"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unicom-universal-and-compact-representation#ran","syntology_url":"https://syntology.ai/paper/2304.05884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05884"}},"official":{"repos":["deepglint/unicom"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}}},{"leaderboard":"/sota/image-retrieval-on-flickr30k-cn","slug":"image-retrieval-on-flickr30k-cn","dataset":"Flickr30k-CN","dataset_url":"/dataset/flickr30k-cna","rows_in_archive":11,"metrics":["R@1","R@10","R@5"],"first_row_in_archive_order":{"model":"InternVL-G-FT","paper_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","paper_url":"/paper/internvl-scaling-up-vision-foundation-models","paper_date":"2023-12-21","arxiv_id":"2312.14238","code_links":[{"title":"opengvlab/internvl","url":"https://github.com/opengvlab/internvl"},{"title":"opengvlab/internvl-mmdetseg","url":"https://github.com/opengvlab/internvl-mmdetseg"}],"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/image-retrieval-on-oxf5k","slug":"image-retrieval-on-oxf5k","dataset":"Oxf5k","dataset_url":null,"rows_in_archive":11,"metrics":["MAP"],"first_row_in_archive_order":{"model":"Offline Diffusion","paper_title":"Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing","paper_url":"/paper/efficient-image-retrieval-via-decoupling","paper_date":"2018-11-27","arxiv_id":"1811.10907","code_links":[{"title":"fyang93/diffusion","url":"https://github.com/fyang93/diffusion"},{"title":"chjort/diffusion","url":"https://github.com/chjort/diffusion"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-inaturalist","slug":"image-retrieval-on-inaturalist","dataset":"iNaturalist","dataset_url":"/dataset/inaturalist","rows_in_archive":10,"metrics":["R@1","R@16","R@32","R@5"],"first_row_in_archive_order":{"model":"Unicom+ViT-L@336px","paper_title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","paper_url":"/paper/unicom-universal-and-compact-representation","paper_date":"2023-04-12","arxiv_id":"2304.05884","code_links":[{"title":"OML-Team/open-metric-learning","url":"https://github.com/OML-Team/open-metric-learning"},{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"},{"title":"RocketFlash/easy_metric_learning","url":"https://github.com/RocketFlash/easy_metric_learning/tree/master/tools"}],"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unicom-universal-and-compact-representation#ran","syntology_url":"https://syntology.ai/paper/2304.05884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05884"}},"official":{"repos":["deepglint/unicom"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}}},{"leaderboard":"/sota/image-retrieval-on-coco-cn","slug":"image-retrieval-on-coco-cn","dataset":"COCO-CN","dataset_url":"/dataset/coco-cn","rows_in_archive":9,"metrics":["R@1","R@10","R@5"],"first_row_in_archive_order":{"model":"CN-CLIP (ViT-H/14)","paper_title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","paper_url":"/paper/chinese-clip-contrastive-vision-language","paper_date":"2022-11-02","arxiv_id":"2211.01335","code_links":[{"title":"ofa-sys/chinese-clip","url":"https://github.com/ofa-sys/chinese-clip"}],"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chinese-clip-contrastive-vision-language#ran","syntology_url":"https://syntology.ai/paper/2211.01335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01335"}},"official":{"repos":["ofa-sys/chinese-clip"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-flickr30k","slug":"image-retrieval-on-flickr30k","dataset":"Flickr30k","dataset_url":"/dataset/flickr30k","rows_in_archive":9,"metrics":["Recall@10","Recall@5","Recall@1","Recall@Sum","Image-to-text R@1","Image-to-text R@10","Image-to-text R@5","QPS"],"first_row_in_archive_order":{"model":"BLIP-2 ViT-G (zero-shot, 1K test set)","paper_title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","paper_url":"/paper/blip-2-bootstrapping-language-image-pre","paper_date":"2023-01-30","arxiv_id":"2301.12597","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}],"syntology":{"n":8,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}},"official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/image-retrieval-on-muge-retrieval","slug":"image-retrieval-on-muge-retrieval","dataset":"MUGE Retrieval","dataset_url":null,"rows_in_archive":9,"metrics":["Mean Recall","R@1","R@10","R@5"],"first_row_in_archive_order":{"model":"CN-CLIP (ViT-H/14)","paper_title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","paper_url":"/paper/chinese-clip-contrastive-vision-language","paper_date":"2022-11-02","arxiv_id":"2211.01335","code_links":[{"title":"ofa-sys/chinese-clip","url":"https://github.com/ofa-sys/chinese-clip"}],"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chinese-clip-contrastive-vision-language#ran","syntology_url":"https://syntology.ai/paper/2211.01335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01335"}},"official":{"repos":["ofa-sys/chinese-clip"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-oxf105k","slug":"image-retrieval-on-oxf105k","dataset":"Oxf105k","dataset_url":null,"rows_in_archive":9,"metrics":["MAP"],"first_row_in_archive_order":{"model":"Offline Diffusion","paper_title":"Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing","paper_url":"/paper/efficient-image-retrieval-via-decoupling","paper_date":"2018-11-27","arxiv_id":"1811.10907","code_links":[{"title":"fyang93/diffusion","url":"https://github.com/fyang93/diffusion"},{"title":"chjort/diffusion","url":"https://github.com/chjort/diffusion"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-cars196","slug":"image-retrieval-on-cars196","dataset":"CARS196","dataset_url":"/dataset/cars196","rows_in_archive":8,"metrics":["R@1","R@8"],"first_row_in_archive_order":{"model":"CGD (MG/SG)","paper_title":"Combination of Multiple Global Descriptors for Image Retrieval","paper_url":"/paper/combination-of-multiple-global-descriptors","paper_date":"2019-03-26","arxiv_id":"1903.10663","code_links":[{"title":"naver/cgd","url":"https://github.com/naver/cgd"},{"title":"leftthomas/CGD","url":"https://github.com/leftthomas/CGD"},{"title":"clovaai/embedding-expansion","url":"https://github.com/clovaai/embedding-expansion"},{"title":"flyingsheepbin/pet-biometrics","url":"https://github.com/flyingsheepbin/pet-biometrics"},{"title":"puneesh00/loop","url":"https://github.com/puneesh00/loop"},{"title":"PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval","url":"https://github.com/PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval"},{"title":"Samjoel3101/Self-Supervised-Learning-fastai2","url":"https://github.com/Samjoel3101/Self-Supervised-Learning-fastai2"}],"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/combination-of-multiple-global-descriptors#ran","syntology_url":"https://syntology.ai/paper/1903.10663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10663"}},"official":{"repos":["naver/cgd"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/image-retrieval-on-cub-200-2011","slug":"image-retrieval-on-cub-200-2011","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":8,"metrics":["R@1","R@2","R@4","R@8"],"first_row_in_archive_order":{"model":"CGD (MG/SG)","paper_title":"Combination of Multiple Global Descriptors for Image Retrieval","paper_url":"/paper/combination-of-multiple-global-descriptors","paper_date":"2019-03-26","arxiv_id":"1903.10663","code_links":[{"title":"naver/cgd","url":"https://github.com/naver/cgd"},{"title":"leftthomas/CGD","url":"https://github.com/leftthomas/CGD"},{"title":"clovaai/embedding-expansion","url":"https://github.com/clovaai/embedding-expansion"},{"title":"flyingsheepbin/pet-biometrics","url":"https://github.com/flyingsheepbin/pet-biometrics"},{"title":"puneesh00/loop","url":"https://github.com/puneesh00/loop"},{"title":"PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval","url":"https://github.com/PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval"},{"title":"Samjoel3101/Self-Supervised-Learning-fastai2","url":"https://github.com/Samjoel3101/Self-Supervised-Learning-fastai2"}],"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/combination-of-multiple-global-descriptors#ran","syntology_url":"https://syntology.ai/paper/1903.10663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10663"}},"official":{"repos":["naver/cgd"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/image-retrieval-on-in-shop","slug":"image-retrieval-on-in-shop","dataset":"In-Shop","dataset_url":"/dataset/in-shop","rows_in_archive":7,"metrics":["R@1"],"first_row_in_archive_order":{"model":"CGD (SG/GS)","paper_title":"Combination of Multiple Global Descriptors for Image Retrieval","paper_url":"/paper/combination-of-multiple-global-descriptors","paper_date":"2019-03-26","arxiv_id":"1903.10663","code_links":[{"title":"naver/cgd","url":"https://github.com/naver/cgd"},{"title":"leftthomas/CGD","url":"https://github.com/leftthomas/CGD"},{"title":"clovaai/embedding-expansion","url":"https://github.com/clovaai/embedding-expansion"},{"title":"flyingsheepbin/pet-biometrics","url":"https://github.com/flyingsheepbin/pet-biometrics"},{"title":"puneesh00/loop","url":"https://github.com/puneesh00/loop"},{"title":"PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval","url":"https://github.com/PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval"},{"title":"Samjoel3101/Self-Supervised-Learning-fastai2","url":"https://github.com/Samjoel3101/Self-Supervised-Learning-fastai2"}],"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/combination-of-multiple-global-descriptors#ran","syntology_url":"https://syntology.ai/paper/1903.10663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10663"}},"official":{"repos":["naver/cgd"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/image-retrieval-on-par106k","slug":"image-retrieval-on-par106k","dataset":"Par106k","dataset_url":null,"rows_in_archive":7,"metrics":["mAP"],"first_row_in_archive_order":{"model":"Offline Diffusion","paper_title":"Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing","paper_url":"/paper/efficient-image-retrieval-via-decoupling","paper_date":"2018-11-27","arxiv_id":"1811.10907","code_links":[{"title":"fyang93/diffusion","url":"https://github.com/fyang93/diffusion"},{"title":"chjort/diffusion","url":"https://github.com/chjort/diffusion"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-par6k","slug":"image-retrieval-on-par6k","dataset":"Par6k","dataset_url":null,"rows_in_archive":7,"metrics":["mAP"],"first_row_in_archive_order":{"model":"Offline Diffusion","paper_title":"Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing","paper_url":"/paper/efficient-image-retrieval-via-decoupling","paper_date":"2018-11-27","arxiv_id":"1811.10907","code_links":[{"title":"fyang93/diffusion","url":"https://github.com/fyang93/diffusion"},{"title":"chjort/diffusion","url":"https://github.com/chjort/diffusion"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-coco","slug":"image-retrieval-on-coco","dataset":"COCO (Common Objects in Context)","dataset_url":"/dataset/coco","rows_in_archive":6,"metrics":["recall@1","recall@5","Recall@10","QPS"],"first_row_in_archive_order":{"model":"BLIP-2 ViT-G (fine-tuned)","paper_title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","paper_url":"/paper/blip-2-bootstrapping-language-image-pre","paper_date":"2023-01-30","arxiv_id":"2301.12597","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}],"syntology":{"n":8,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}},"official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/image-retrieval-on-amstertime","slug":"image-retrieval-on-amstertime","dataset":"AmsterTime","dataset_url":"/dataset/amstertime","rows_in_archive":5,"metrics":["mAP"],"first_row_in_archive_order":{"model":"DINOv2 distilled (ViT-L/14 frozen)","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","paper_url":"/paper/dinov2-learning-robust-visual-features","paper_date":"2023-04-14","arxiv_id":"2304.07193","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"facebookresearch/dinov2","url":"https://github.com/facebookresearch/dinov2"},{"title":"roboflow/rf-detr","url":"https://github.com/roboflow/rf-detr"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"OML-Team/open-metric-learning","url":"https://github.com/OML-Team/open-metric-learning"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/beit"},{"title":"fabio-sim/Depth-Anything-ONNX","url":"https://github.com/fabio-sim/Depth-Anything-ONNX"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"facebookresearch/highrescanopyheight","url":"https://github.com/facebookresearch/highrescanopyheight"},{"title":"PaddlePaddle/PASSL","url":"https://github.com/PaddlePaddle/PASSL"},{"title":"beneroth13/dinov2","url":"https://github.com/beneroth13/dinov2"},{"title":"mohammedsb/dinov2formedical","url":"https://github.com/mohammedsb/dinov2formedical"},{"title":"marrlab/dinobloom","url":"https://github.com/marrlab/dinobloom"},{"title":"bespontaneous/proteus-pytorch","url":"https://github.com/bespontaneous/proteus-pytorch"},{"title":"ByungKwanLee/Causal-Unsupervised-Segmentation","url":"https://github.com/ByungKwanLee/Causal-Unsupervised-Segmentation"},{"title":"zhu-xlab/softcon","url":"https://github.com/zhu-xlab/softcon"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"gorkaydemir/DINOSAUR","url":"https://github.com/gorkaydemir/DINOSAUR"},{"title":"seatizendoi/dinovdeau","url":"https://github.com/seatizendoi/dinovdeau"},{"title":"BurguerJohn/global_perceptual_similarity_loss","url":"https://github.com/BurguerJohn/global_perceptual_similarity_loss"},{"title":"buyeah1109/KEN","url":"https://github.com/buyeah1109/KEN"},{"title":"JHKim-snu/PGA","url":"https://github.com/JHKim-snu/PGA"},{"title":"BurguerJohn/torch-felix","url":"https://github.com/BurguerJohn/torch-felix"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/dinov2"},{"title":"buyeah1109/finc","url":"https://github.com/buyeah1109/finc"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/dinov2"}],"syntology":{"n":46,"n_ran":39,"n_constructed":13,"n_ran_checked":32,"n_instrument":7,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":30,"n_pointer_only":12,"phrase":"39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/dinov2-learning-robust-visual-features#ran","syntology_url":"https://syntology.ai/paper/2304.07193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.07193"}},"official":{"repos":["facebookresearch/dinov2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/image-retrieval-on-conqa-conceptual","slug":"image-retrieval-on-conqa-conceptual","dataset":"ConQA Conceptual","dataset_url":"/dataset/conqa","rows_in_archive":5,"metrics":["Recall@1","Recall@5","Recall@10","R-precision"],"first_row_in_archive_order":{"model":"CLIP","paper_title":"Does the Performance of Text-to-Image Retrieval Models Generalize Beyond Captions-as-a-Query?","paper_url":"/paper/does-the-performance-of-text-to-image","paper_date":"2024-03-15","arxiv_id":null,"code_links":[{"title":"AU-DIS/ConQA","url":"https://github.com/AU-DIS/ConQA"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-conqa-descriptive","slug":"image-retrieval-on-conqa-descriptive","dataset":"ConQA Descriptive","dataset_url":"/dataset/conqa","rows_in_archive":5,"metrics":["Recall@1","Recall@5","Recall@10","R-precision"],"first_row_in_archive_order":{"model":"CLIP","paper_title":"Does the Performance of Text-to-Image Retrieval Models Generalize Beyond Captions-as-a-Query?","paper_url":"/paper/does-the-performance-of-text-to-image","paper_date":"2024-03-15","arxiv_id":null,"code_links":[{"title":"AU-DIS/ConQA","url":"https://github.com/AU-DIS/ConQA"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-photochat","slug":"image-retrieval-on-photochat","dataset":"PhotoChat","dataset_url":"/dataset/photochat","rows_in_archive":5,"metrics":["R1","R@10","R@5","Sum(R@1,5,10)"],"first_row_in_archive_order":{"model":"PaCE","paper_title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","paper_url":"/paper/pace-unified-multi-modal-dialogue-pre","paper_date":"2023-05-24","arxiv_id":"2305.14839","code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/pace"}],"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pace-unified-multi-modal-dialogue-pre#ran","syntology_url":"https://syntology.ai/paper/2305.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14839"}},"official":{"repos":["AlibabaResearch/DAMO-ConvAI"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/image-retrieval-on-deepfashion-consumer-to","slug":"image-retrieval-on-deepfashion-consumer-to","dataset":"DeepFashion - Consumer-to-shop","dataset_url":null,"rows_in_archive":4,"metrics":["mAP","Rank-1","Rank-10","Rank-20","Rank-50"],"first_row_in_archive_order":{"model":"CTL Model (ResNet50-IBN-A, 320x320)","paper_title":"On the Unreasonable Effectiveness of Centroids in Image Retrieval","paper_url":"/paper/on-the-unreasonable-effectiveness-of-1","paper_date":"2021-04-28","arxiv_id":"2104.13643","code_links":[{"title":"mikwieczorek/centroids-reid","url":"https://github.com/mikwieczorek/centroids-reid"},{"title":"lannguyen0910/deep-efficient-reid","url":"https://github.com/lannguyen0910/deep-efficient-reid"},{"title":"lannguyen0910/deep-efficient-person-reid","url":"https://github.com/lannguyen0910/deep-efficient-person-reid"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-deeppatent","slug":"image-retrieval-on-deeppatent","dataset":"DeepPatent","dataset_url":"/dataset/deeppatent","rows_in_archive":4,"metrics":["mean average precision"],"first_row_in_archive_order":{"model":"SwinV2","paper_title":"Patent image retrieval using transformer-based deep metric learning","paper_url":"/paper/patent-image-retrieval-using-transformer","paper_date":"2023-09-01","arxiv_id":null,"code_links":[{"title":"L4Clippers/Patent-Image-Retrieval-Transformer-DML","url":"https://github.com/L4Clippers/Patent-Image-Retrieval-Transformer-DML"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-google-landmarks-dataset","slug":"image-retrieval-on-google-landmarks-dataset","dataset":"Google Landmarks Dataset v2 (retrieval, testing)","dataset_url":"/dataset/google-landmarks-dataset-v2","rows_in_archive":4,"metrics":["mAP@100"],"first_row_in_archive_order":{"model":"AMES","paper_title":"AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval","paper_url":"/paper/2408-03282","paper_date":"2024-08-06","arxiv_id":"2408.03282","code_links":[{"title":"pavelsuma/ames","url":"https://github.com/pavelsuma/ames"}],"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-03282#ran","syntology_url":"https://syntology.ai/paper/2408.03282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03282"}},"official":{"repos":["pavelsuma/ames"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-24-7-tokyo","slug":"image-retrieval-on-24-7-tokyo","dataset":"24/7 Tokyo","dataset_url":null,"rows_in_archive":3,"metrics":["mAP"],"first_row_in_archive_order":{"model":"HED-N-GAN","paper_title":"Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning","paper_url":"/paper/dark-side-augmentation-generating-diverse-1","paper_date":"2023-09-28","arxiv_id":"2309.16351","code_links":[{"title":"mohwald/gandtr","url":"https://github.com/mohwald/gandtr"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dark-side-augmentation-generating-diverse-1#ran","syntology_url":"https://syntology.ai/paper/2309.16351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16351"}},"official":{"repos":["mohwald/gandtr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-exact-street2shop","slug":"image-retrieval-on-exact-street2shop","dataset":"Exact Street2Shop","dataset_url":"/dataset/exact-street2shop","rows_in_archive":3,"metrics":["Rank-1","Rank-10","Rank-20","mAP","Rank-50"],"first_row_in_archive_order":{"model":"CTL Model (ResNet50-IBN-A, 320x320)","paper_title":"On the Unreasonable Effectiveness of Centroids in Image Retrieval","paper_url":"/paper/on-the-unreasonable-effectiveness-of-1","paper_date":"2021-04-28","arxiv_id":"2104.13643","code_links":[{"title":"mikwieczorek/centroids-reid","url":"https://github.com/mikwieczorek/centroids-reid"},{"title":"lannguyen0910/deep-efficient-reid","url":"https://github.com/lannguyen0910/deep-efficient-reid"},{"title":"lannguyen0910/deep-efficient-person-reid","url":"https://github.com/lannguyen0910/deep-efficient-person-reid"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-google-landmarks-dataset-1","slug":"image-retrieval-on-google-landmarks-dataset-1","dataset":"Google Landmarks Dataset v2 (retrieval, validation)","dataset_url":"/dataset/google-landmarks-dataset-v2","rows_in_archive":3,"metrics":["mAP@100"],"first_row_in_archive_order":{"model":"UNICOM-ViT-L-14-512px","paper_title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","paper_url":"/paper/unicom-universal-and-compact-representation","paper_date":"2023-04-12","arxiv_id":"2304.05884","code_links":[{"title":"OML-Team/open-metric-learning","url":"https://github.com/OML-Team/open-metric-learning"},{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"},{"title":"RocketFlash/easy_metric_learning","url":"https://github.com/RocketFlash/easy_metric_learning/tree/master/tools"}],"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unicom-universal-and-compact-representation#ran","syntology_url":"https://syntology.ai/paper/2304.05884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05884"}},"official":{"repos":["deepglint/unicom"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}}},{"leaderboard":"/sota/image-retrieval-on-lasco","slug":"image-retrieval-on-lasco","dataset":"LaSCo","dataset_url":"/dataset/lasco","rows_in_archive":3,"metrics":["Recall@1 (%)"],"first_row_in_archive_order":{"model":"CASE","paper_title":"Data Roaming and Quality Assessment for Composed Image Retrieval","paper_url":"/paper/data-roaming-and-early-fusion-for-composed","paper_date":"2023-03-16","arxiv_id":"2303.09429","code_links":[{"title":"levymsn/LaSCo","url":"https://github.com/levymsn/LaSCo"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-mscoco","slug":"image-retrieval-on-mscoco","dataset":"MSCOCO","dataset_url":"/dataset/mscoco","rows_in_archive":3,"metrics":["Recall@1","Recall@10","Recall@5"],"first_row_in_archive_order":{"model":"HADA","paper_title":"HADA: A Graph-based Amalgamation Framework in Image-text Retrieval","paper_url":"/paper/hada-a-graph-based-amalgamation-framework-in","paper_date":"2023-01-11","arxiv_id":"2301.04742","code_links":[{"title":"m2man/hada","url":"https://github.com/m2man/hada"},{"title":"m2man/HADA-LAVIS","url":"https://github.com/m2man/HADA-LAVIS"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-aic-icc","slug":"image-retrieval-on-aic-icc","dataset":"AIC-ICC","dataset_url":null,"rows_in_archive":2,"metrics":["Recall@1","Recall@10","Recall@5"],"first_row_in_archive_order":{"model":"ERNIE-ViL2.0","paper_title":"ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training","paper_url":"/paper/ernie-vil-2-0-multi-view-contrastive-learning","paper_date":"2022-09-30","arxiv_id":"2209.15270","code_links":[{"title":"PaddlePaddle/ERNIE","url":"https://github.com/PaddlePaddle/ERNIE"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-cbvs","slug":"image-retrieval-on-cbvs","dataset":"CBVS","dataset_url":"/dataset/cbvs","rows_in_archive":2,"metrics":["PNR","Recall@1"],"first_row_in_archive_order":{"model":"UniCLP","paper_title":"CBVS: A Large-Scale Chinese Image-Text Benchmark for Real-World Short Video Search Scenarios","paper_url":"/paper/cbvs-a-large-scale-chinese-image-text","paper_date":"2024-01-19","arxiv_id":"2401.10475","code_links":[{"title":"QQBrowserVideoSearch/CBVS-UniCLIP","url":"https://github.com/QQBrowserVideoSearch/CBVS-UniCLIP"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-inria-holidays","slug":"image-retrieval-on-inria-holidays","dataset":"INRIA Holidays","dataset_url":null,"rows_in_archive":2,"metrics":["Mean mAP"],"first_row_in_archive_order":{"model":"MultiGrain R50 @ 800","paper_title":"MultiGrain: a unified image embedding for classes and instances","paper_url":"/paper/multigrain-a-unified-image-embedding-for","paper_date":"2019-02-14","arxiv_id":"1902.05509","code_links":[{"title":"facebookresearch/multigrain","url":"https://github.com/facebookresearch/multigrain"},{"title":"2023-MindSpore-1/ms-code-62","url":"https://github.com/2023-MindSpore-1/ms-code-62"},{"title":"leehangyu/MultiGrain_Application","url":"https://github.com/leehangyu/MultiGrain_Application"}],"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multigrain-a-unified-image-embedding-for#ran","syntology_url":"https://syntology.ai/paper/1902.05509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.05509"}},"official":{"repos":["facebookresearch/multigrain"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/image-retrieval-on-oxford5k","slug":"image-retrieval-on-oxford5k","dataset":"Oxford5k","dataset_url":"/dataset/oxford5k","rows_in_archive":2,"metrics":["mAP"],"first_row_in_archive_order":{"model":"GNN-Reranking","paper_title":"Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective","paper_url":"/paper/understanding-image-retrieval-re-ranking-a","paper_date":"2020-12-14","arxiv_id":"2012.07620","code_links":[{"title":"Xuanmeng-Zhang/gnn-re-ranking","url":"https://github.com/Xuanmeng-Zhang/gnn-re-ranking"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-paris6k","slug":"image-retrieval-on-paris6k","dataset":"Paris6k","dataset_url":"/dataset/paris6k","rows_in_archive":2,"metrics":["mAP"],"first_row_in_archive_order":{"model":"IME layer","paper_title":"Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-scale Image Retrieval","paper_url":"/paper/iterative-manifold-embedding-layer-learned-by","paper_date":"2017-07-14","arxiv_id":"1707.09862","code_links":[{"title":"XJhaoren/IME_layer","url":"https://github.com/XJhaoren/IME_layer"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-street2shop-topwear","slug":"image-retrieval-on-street2shop-topwear","dataset":"street2shop - topwear","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Ranknet","paper_title":"Retrieving Similar E-Commerce Images Using Deep Learning","paper_url":"/paper/retrieving-similar-e-commerce-images-using","paper_date":"2019-01-11","arxiv_id":"1901.03546","code_links":[{"title":"gofynd/mildnet","url":"https://github.com/gofynd/mildnet"},{"title":"khatria/Retrieving-Similar-E-Commerce-Images-Using-Deep-Learning","url":"https://github.com/khatria/Retrieving-Similar-E-Commerce-Images-Using-Deep-Learning"},{"title":"Ducvoccer/mildnet","url":"https://github.com/Ducvoccer/mildnet"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-wit","slug":"image-retrieval-on-wit","dataset":"WIT","dataset_url":"/dataset/wit","rows_in_archive":2,"metrics":["R@1","R@5"],"first_row_in_archive_order":{"model":"WIT-ALL","paper_title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","paper_url":"/paper/wit-wikipedia-based-image-text-dataset-for","paper_date":"2021-03-02","arxiv_id":"2103.01913","code_links":[{"title":"google-research-datasets/wit","url":"https://github.com/google-research-datasets/wit"},{"title":"clip-italian/clip-italian","url":"https://github.com/clip-italian/clip-italian"},{"title":"paullerner/viquae","url":"https://github.com/paullerner/viquae"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-cifar-10","slug":"image-retrieval-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":1,"metrics":["Average-mAP"],"first_row_in_archive_order":{"model":"Custom: 3 conv + 2 fcn","paper_title":"Deep Supervised Hashing for Fast Image Retrieval","paper_url":"/paper/deep-supervised-hashing-for-fast-image","paper_date":"2016-06-01","arxiv_id":null,"code_links":[{"title":"bgswaroop/deep-hashing","url":"https://github.com/bgswaroop/deep-hashing"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-cofar","slug":"image-retrieval-on-cofar","dataset":"COFAR","dataset_url":"/dataset/cofar","rows_in_archive":1,"metrics":["Recall@1","Recall@5"],"first_row_in_archive_order":{"model":"KRAMT","paper_title":"COFAR: Commonsense and Factual Reasoning in Image Search","paper_url":"/paper/cofar-commonsense-and-factual-reasoning-in","paper_date":"2022-10-16","arxiv_id":"2210.08554","code_links":[{"title":"vl2g/cofar","url":"https://github.com/vl2g/cofar"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-deepfashion","slug":"image-retrieval-on-deepfashion","dataset":"DeepFashion","dataset_url":"/dataset/deepfashion","rows_in_archive":1,"metrics":["Recall@20"],"first_row_in_archive_order":{"model":"RCCapsNet","paper_title":"Fashion Image Retrieval with Capsule Networks","paper_url":"/paper/fashion-image-retrieval-with-capsule-networks","paper_date":"2019-08-26","arxiv_id":"1908.09943","code_links":[{"title":"birdortyedi/image-retrieval-with-capsules","url":"https://github.com/birdortyedi/image-retrieval-with-capsules"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-feta-car-manuals","slug":"image-retrieval-on-feta-car-manuals","dataset":"FETA Car-Manuals","dataset_url":"/dataset/feta-car-manuals","rows_in_archive":1,"metrics":["R@1","R@10","R@5"],"first_row_in_archive_order":{"model":"FETA's CLIP-MIL (Many-Shot Image-to-text)","paper_title":"FETA: Towards Specializing Foundation Models for Expert Task Applications","paper_url":"/paper/feta-towards-specializing-foundation-models","paper_date":"2022-09-08","arxiv_id":"2209.03648","code_links":[{"title":"alfassy/FETA","url":"https://github.com/alfassy/FETA"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-foodi-ml-global","slug":"image-retrieval-on-foodi-ml-global","dataset":"FooDI-ML (Global)","dataset_url":"/dataset/foodi-ml","rows_in_archive":1,"metrics":["A-R@1","A-R@10","A-R@5","Re-R@1","Re-R@10","Re-R@5"],"first_row_in_archive_order":{"model":"ADAPT-I2T","paper_title":"FooDI-ML: a large multi-language dataset of food, drinks and groceries images and descriptions","paper_url":"/paper/foodi-ml-a-large-multi-language-dataset-of","paper_date":"2021-10-05","arxiv_id":"2110.02035","code_links":[{"title":"glovo/foodi-ml-dataset","url":"https://github.com/glovo/foodi-ml-dataset"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-foodi-ml-spain","slug":"image-retrieval-on-foodi-ml-spain","dataset":"FooDI-ML (Spain)","dataset_url":"/dataset/foodi-ml","rows_in_archive":1,"metrics":["A-R@1","A-R@10","A-R@5","Re-R@1","Re-R@10","Re-R@5"],"first_row_in_archive_order":{"model":"ADAPT-I2T","paper_title":"FooDI-ML: a large multi-language dataset of food, drinks and groceries images and descriptions","paper_url":"/paper/foodi-ml-a-large-multi-language-dataset-of","paper_date":"2021-10-05","arxiv_id":"2110.02035","code_links":[{"title":"glovo/foodi-ml-dataset","url":"https://github.com/glovo/foodi-ml-dataset"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-icfg-pedes","slug":"image-retrieval-on-icfg-pedes","dataset":"ICFG-PEDES","dataset_url":"/dataset/icfg-pedes","rows_in_archive":1,"metrics":["rank-1"],"first_row_in_archive_order":{"model":"SSAN","paper_title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","paper_url":"/paper/semantically-self-aligned-network-for-text-to","paper_date":"2021-07-27","arxiv_id":"2107.12666","code_links":[{"title":"zifyloo/SSAN","url":"https://github.com/zifyloo/SSAN"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-imagecode","slug":"image-retrieval-on-imagecode","dataset":"ImageCoDe","dataset_url":"/dataset/imagecode","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ContextualCLIP","paper_title":"Image Retrieval from Contextual Descriptions","paper_url":"/paper/image-retrieval-from-contextual-descriptions-1","paper_date":"2022-03-29","arxiv_id":"2203.15867","code_links":[{"title":"mcgill-nlp/imagecode","url":"https://github.com/mcgill-nlp/imagecode"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/image-retrieval-from-contextual-descriptions-1#ran","syntology_url":"https://syntology.ai/paper/2203.15867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15867"}},"official":{"repos":["mcgill-nlp/imagecode"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-retrieval-on-instre","slug":"image-retrieval-on-instre","dataset":"INSTRE","dataset_url":"/dataset/instre","rows_in_archive":1,"metrics":["MAP"],"first_row_in_archive_order":{"model":"IME layer","paper_title":"Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-scale Image Retrieval","paper_url":"/paper/iterative-manifold-embedding-layer-learned-by","paper_date":"2017-07-14","arxiv_id":"1707.09862","code_links":[{"title":"XJhaoren/IME_layer","url":"https://github.com/XJhaoren/IME_layer"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-localized-narratives","slug":"image-retrieval-on-localized-narratives","dataset":"Localized Narratives","dataset_url":"/dataset/localized-narratives","rows_in_archive":1,"metrics":["Text-to-image R@1","Text-to-image R@10","Text-to-image R@5"],"first_row_in_archive_order":{"model":"OPT","paper_title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","paper_url":"/paper/opt-omni-perception-pre-trainer-for-cross","paper_date":"2021-07-01","arxiv_id":"2107.00249","code_links":[{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/mm/opt"},{"title":"2023-MindSpore-1/ms-code-161","url":"https://github.com/2023-MindSpore-1/ms-code-161"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-nus-wide","slug":"image-retrieval-on-nus-wide","dataset":"NUS-WIDE","dataset_url":"/dataset/nus-wide","rows_in_archive":1,"metrics":["MAP"],"first_row_in_archive_order":{"model":"DTQ","paper_title":"Deep Triplet Quantization","paper_url":"/paper/deep-triplet-quantization","paper_date":"2019-02-01","arxiv_id":"1902.00153","code_links":[{"title":"thulab/DeepHash","url":"https://github.com/thulab/DeepHash"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-triplet-quantization#ran","syntology_url":"https://syntology.ai/paper/1902.00153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00153"}},"official":null}}},{"leaderboard":"/sota/image-retrieval-on-pku-reid","slug":"image-retrieval-on-pku-reid","dataset":"PKU-Reid","dataset_url":"/dataset/pku-reid","rows_in_archive":1,"metrics":["R1"],"first_row_in_archive_order":{"model":"IHDA","paper_title":"Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval","paper_url":"/paper/instance-level-heterogeneous-domain-1","paper_date":"2022-11-26","arxiv_id":"2211.14515","code_links":[{"title":"fandulu/IHDA","url":"https://github.com/fandulu/IHDA"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-pku-sketchre-id-dataset","slug":"image-retrieval-on-pku-sketchre-id-dataset","dataset":"PKU SketchRe-ID Dataset","dataset_url":"/dataset/pku-sketchre-id-dataset","rows_in_archive":1,"metrics":["R1"],"first_row_in_archive_order":{"model":"IHDA","paper_title":"Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval","paper_url":"/paper/instance-level-heterogeneous-domain-1","paper_date":"2022-11-26","arxiv_id":"2211.14515","code_links":[{"title":"fandulu/IHDA","url":"https://github.com/fandulu/IHDA"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-roxford-medium-without","slug":"image-retrieval-on-roxford-medium-without","dataset":"ROxford Medium without fine-tuning","dataset_url":"/dataset/roxford","rows_in_archive":1,"metrics":["Average mAP"],"first_row_in_archive_order":{"model":"HesAff–rSIFT–VLAD","paper_title":"Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking","paper_url":"/paper/revisiting-oxford-and-paris-large-scale-image","paper_date":"2018-03-29","arxiv_id":"1803.11285","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/delf"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"}],"syntology":null}},{"leaderboard":"/sota/image-retrieval-on-ruc-cas-wenlan","slug":"image-retrieval-on-ruc-cas-wenlan","dataset":"RUC-CAS-WenLan","dataset_url":null,"rows_in_archive":1,"metrics":["Recall@1","Recall@10","Recall@5"],"first_row_in_archive_order":{"model":"CMCL","paper_title":"WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training","paper_url":"/paper/wenlan-bridging-vision-and-language-by-large","paper_date":"2021-03-11","arxiv_id":"2103.06561","code_links":[{"title":"BAAI-WuDao/BriVl","url":"https://github.com/BAAI-WuDao/BriVl"},{"title":"Aman-4-Real/MMTG","url":"https://github.com/Aman-4-Real/MMTG"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/flickr30k","name":"Flickr30k","full_name":"Flickr30k","num_papers_in_archive":880},{"url":"/dataset/inaturalist","name":"iNaturalist","full_name":"","num_papers_in_archive":603},{"url":"/dataset/deepfashion","name":"DeepFashion","full_name":"","num_papers_in_archive":397},{"url":"/dataset/nus-wide","name":"NUS-WIDE","full_name":"","num_papers_in_archive":348},{"url":"/dataset/yfcc100m","name":"YFCC100M","full_name":"","num_papers_in_archive":243},{"url":"/dataset/stanford-online-products","name":"Stanford Online Products","full_name":"Stanford Online Products","num_papers_in_archive":231},{"url":"/dataset/in-shop","name":"In-Shop","full_name":"In-shop Clothes Retrieval Benchmark","num_papers_in_archive":154},{"url":"/dataset/oxford5k","name":"Oxford5k","full_name":"Oxford Buildings","num_papers_in_archive":137},{"url":"/dataset/tiny-images","name":"Tiny Images","full_name":"","num_papers_in_archive":103},{"url":"/dataset/fashion-iq","name":"Fashion IQ","full_name":"","num_papers_in_archive":102},{"url":"/dataset/mscoco","name":"MSCOCO","full_name":"","num_papers_in_archive":90},{"url":"/dataset/wit","name":"WIT","full_name":"Wikipedia-based Image Text","num_papers_in_archive":79},{"url":"/dataset/roxford","name":"ROxford","full_name":"","num_papers_in_archive":73},{"url":"/dataset/inloc","name":"InLoc","full_name":"","num_papers_in_archive":67},{"url":"/dataset/localized-narratives","name":"Localized Narratives","full_name":"","num_papers_in_archive":63},{"url":"/dataset/cirr","name":"CIRR","full_name":"Compose Image Retrieval on Real-life images","num_papers_in_archive":61},{"url":"/dataset/quick-draw-dataset","name":"Quick, Draw! Dataset","full_name":"","num_papers_in_archive":50},{"url":"/dataset/oxford105k","name":"Oxford105k","full_name":"","num_papers_in_archive":44},{"url":"/dataset/cars196","name":"CARS196","full_name":"","num_papers_in_archive":43},{"url":"/dataset/fashion-gen","name":"Fashion-Gen","full_name":"","num_papers_in_archive":36},{"url":"/dataset/circo","name":"CIRCO","full_name":"Composed Image Retrieval on Common Objects in context","num_papers_in_archive":35},{"url":"/dataset/google-landmarks-dataset-v2","name":"Google Landmarks Dataset v2","full_name":null,"num_papers_in_archive":35},{"url":"/dataset/spot-the-diff","name":"Spot-the-diff","full_name":"","num_papers_in_archive":35},{"url":"/dataset/deepfashion2","name":"DeepFashion2","full_name":"","num_papers_in_archive":30},{"url":"/dataset/sketch-me-that-shoe","name":"ShoeV2","full_name":"ShoeV2","num_papers_in_archive":30},{"url":"/dataset/google-landmarks","name":"Google Landmarks","full_name":"","num_papers_in_archive":24},{"url":"/dataset/coco-cn","name":"COCO-CN","full_name":"","num_papers_in_archive":21},{"url":"/dataset/photochat","name":"PhotoChat","full_name":"","num_papers_in_archive":20},{"url":"/dataset/oven","name":"OVEN","full_name":"Open-domain Visual Entity Recognition","num_papers_in_archive":19},{"url":"/dataset/icfg-pedes","name":"ICFG-PEDES","full_name":"Identity-Centric and Fine-Grained Person Description Dataset","num_papers_in_archive":16},{"url":"/dataset/exact-street2shop","name":"Exact Street2Shop","full_name":"","num_papers_in_archive":15},{"url":"/dataset/vegfru","name":"VegFru","full_name":null,"num_papers_in_archive":14},{"url":"/dataset/visual-madlibs","name":"Visual Madlibs","full_name":"","num_papers_in_archive":13},{"url":"/dataset/imagecode","name":"ImageCoDe","full_name":"Image Retrieval from Contextual Descriptions","num_papers_in_archive":11},{"url":"/dataset/amstertime","name":"AmsterTime","full_name":"AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift","num_papers_in_archive":9},{"url":"/dataset/quickdraw-extended","name":"QuickDraw-Extended","full_name":"","num_papers_in_archive":9},{"url":"/dataset/sketchyscene","name":"SketchyScene","full_name":"","num_papers_in_archive":9},{"url":"/dataset/eth-sfm","name":"ETH SfM","full_name":"ETH Structure-from-Motion","num_papers_in_archive":8},{"url":"/dataset/flickr30k-cna","name":"Flickr30k-CNA","full_name":"Flickr30k-Chinese All","num_papers_in_archive":7},{"url":"/dataset/hotels-50k","name":"Hotels-50K","full_name":"","num_papers_in_archive":7},{"url":"/dataset/lasco","name":"LaSCo","full_name":"","num_papers_in_archive":7},{"url":"/dataset/oxford-affine","name":"Oxford-Affine","full_name":"","num_papers_in_archive":7},{"url":"/dataset/retrieval-sfm","name":"Retrieval-SfM","full_name":null,"num_papers_in_archive":7},{"url":"/dataset/paris6k","name":"Paris6k","full_name":"","num_papers_in_archive":6},{"url":"/dataset/pku-reid","name":"PKU-Reid","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/deeppatent","name":"DeepPatent","full_name":"","num_papers_in_archive":4},{"url":"/dataset/kitchen-scenes","name":"Kitchen Scenes","full_name":"","num_papers_in_archive":4},{"url":"/dataset/retvqa","name":"RetVQA","full_name":"Retrieval-Based Visual Question Answering","num_papers_in_archive":4},{"url":"/dataset/stair-captions","name":"STAIR Captions","full_name":"STAIR Captions","num_papers_in_archive":4},{"url":"/dataset/verse","name":"Verse","full_name":"","num_papers_in_archive":4},{"url":"/dataset/cv-cities","name":"CV-Cities","full_name":"","num_papers_in_archive":3},{"url":"/dataset/gpr1200","name":"GPR1200","full_name":"","num_papers_in_archive":3},{"url":"/dataset/large-time-lags-location-ltll","name":"Large Time Lags Location (LTLL)","full_name":"","num_papers_in_archive":3},{"url":"/dataset/mmid","name":"MMID","full_name":"Massively Multilingual Image Dataset","num_papers_in_archive":3},{"url":"/dataset/gpscap","name":"SCapRepo","full_name":"Google Play Screenshot Caption","num_papers_in_archive":3},{"url":"/dataset/spagbol","name":"SpaGBOL","full_name":"Spatial-Graph-Based Orientated Cross-View Geo-Localisation","num_papers_in_archive":3},{"url":"/dataset/cofar","name":"COFAR","full_name":"Commonsense and Factual Reasoning in Image Search","num_papers_in_archive":2},{"url":"/dataset/crepe-vision-language","name":"CREPE (Compositional REPresentation Evaluation)","full_name":"","num_papers_in_archive":2},{"url":"/dataset/cross-view-time-dataset","name":"Cross-View Time Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/dyml-animal","name":"DyML-Animal","full_name":"Dynamic Metric Learning Animal","num_papers_in_archive":2},{"url":"/dataset/dyml-product","name":"DyML-Product","full_name":"Dynamic Metric Learning Product","num_papers_in_archive":2},{"url":"/dataset/dyml-vehicle","name":"DyML-Vehicle","full_name":"Dynamic Metric Learning Vehicle","num_papers_in_archive":2},{"url":"/dataset/european-flood-2013-dataset","name":"European Flood 2013 Dataset","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/instre","name":"INSTRE","full_name":"","num_papers_in_archive":2},{"url":"/dataset/salient-object-subitizing-dataset","name":"Salient Object Subitizing Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/cbvs","name":"CBVS","full_name":"","num_papers_in_archive":1},{"url":"/dataset/conqa","name":"ConQA","full_name":"Conceptual Query Answering","num_papers_in_archive":1},{"url":"/dataset/cross-view-time-dataset-cross-camera-split","name":"Cross-View Time Dataset (Cross-Camera Split)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/dataset-of-structured-queries-and-spatial","name":"Dataset of Structured Queries and Spatial Relations","full_name":"","num_papers_in_archive":1},{"url":"/dataset/dialogcc","name":"DialogCC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/feta-car-manuals","name":"FETA Car-Manuals","full_name":"FETA Car-Manuals dataset, image-text retrieval for foundation models' expert data performance.","num_papers_in_archive":1},{"url":"/dataset/foodi-ml","name":"FooDI-ML","full_name":"Food Drinks and groceries Images Multi Lingual","num_papers_in_archive":1},{"url":"/dataset/fruit-salad","name":"fruit-SALAD","full_name":"","num_papers_in_archive":1},{"url":"/dataset/iapr-tc-12","name":"IAPR TC-12","full_name":"IAPR TC-12 Benchmark","num_papers_in_archive":1},{"url":"/dataset/ikea-assembly-in-the-wild-dataset","name":"IAW Dataset","full_name":"Ikea Assembly In The Wild Dataset","num_papers_in_archive":1},{"url":"/dataset/ilias","name":"ILIAS","full_name":"ILIAS: Instance-Level Image retrieval At Scale","num_papers_in_archive":1},{"url":"/dataset/impact-patent","name":"IMPACT Patent","full_name":"A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents","num_papers_in_archive":1},{"url":"/dataset/instacities1m","name":"InstaCities1M","full_name":"","num_papers_in_archive":1},{"url":"/dataset/large-labelled-logo-dataset-l3d","name":"Large Labelled Logo Dataset (L3D)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/melon","name":"MELON","full_name":"Melodic Design","num_papers_in_archive":1},{"url":"/dataset/naver-labs-localization-datasets","name":"NAVER LABS Localization Datasets","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pku-sketchre-id-dataset","name":"PKU SketchRe-ID Dataset","full_name":"PKU SketchRe-ID Dataset","num_papers_in_archive":1},{"url":"/dataset/visual-haystacks-vhs","name":"Visual Haystacks (VHs)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/webli","name":"WebLI","full_name":"Web Language Image","num_papers_in_archive":1}],"subtasks":[{"url":"/task/chat-based-image-retrieval","name":"Chat-based Image Retrieval"},{"url":"/task/composed-image-retrieval","name":"Composed Image Retrieval (CoIR)"},{"url":"/task/content-based-image-retrieval","name":"Content-Based Image Retrieval"},{"url":"/task/face-image-retrieval","name":"Face Image Retrieval"},{"url":"/task/image-instance-retrieval","name":"Image Instance Retrieval"},{"url":"/task/medical-image-retrieval","name":"Medical Image Retrieval"},{"url":"/task/multi-label-image-retrieval","name":"Multi-Label Image Retrieval"},{"url":"/task/semi-supervised-sketch-based-image-retrieval","name":"Semi-Supervised Sketch Based Image Retrieval"},{"url":"/task/sketch-based-image-retrieval","name":"Sketch-Based Image Retrieval"},{"url":"/task/video-to-shop","name":"Video-to-Shop"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":23,"rows_per_page":100,"shown":100,"of":2239,"of_with_code":835,"tagged_in_all":2239,"counts":{"archive_papers_tagged":2239,"with_a_code_link":835,"where_syntology_ran_a_sample":218,"not_listed_spam_title":0,"listed":2239,"listed_where_code_ran":218,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":181,"every_run_a_failure_of_syntologys_instrument":37,"listed_with_a_run_with_no_instrument_failure":181,"listed_every_run_a_failure_of_syntologys_instrument":37,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/emerging-properties-in-self-supervised-vision","slug":"emerging-properties-in-self-supervised-vision","title":"Emerging Properties in Self-Supervised Vision Transformers","date":"2021-04-29","arxiv_id":"2104.14294","repositories_listed":32,"syntology":{"n":20,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/emerging-properties-in-self-supervised-vision#ran","syntology_url":"https://syntology.ai/paper/2104.14294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14294"}},"official":{"repos":["facebookresearch/dino"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/dinov2-learning-robust-visual-features","slug":"dinov2-learning-robust-visual-features","title":"DINOv2: Learning Robust Visual Features without Supervision","date":"2023-04-14","arxiv_id":"2304.07193","repositories_listed":26,"syntology":{"n":46,"n_ran":39,"n_constructed":13,"n_ran_checked":32,"n_instrument":7,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":30,"n_pointer_only":12,"phrase":"39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/dinov2-learning-robust-visual-features#ran","syntology_url":"https://syntology.ai/paper/2304.07193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.07193"}},"official":{"repos":["facebookresearch/dinov2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/vggface2-a-dataset-for-recognising-faces","slug":"vggface2-a-dataset-for-recognising-faces","title":"VGGFace2: A dataset for recognising faces across pose and age","date":"2017-10-23","arxiv_id":"1710.08092","repositories_listed":24,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vggface2-a-dataset-for-recognising-faces#ran","syntology_url":"https://syntology.ai/paper/1710.08092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.08092"}},"official":null}},{"url":"/paper/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","repositories_listed":17,"syntology":{"n":8,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}},"official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/circle-loss-a-unified-perspective-of-pair","slug":"circle-loss-a-unified-perspective-of-pair","title":"Circle Loss: A Unified Perspective of Pair Similarity Optimization","date":"2020-02-25","arxiv_id":"2002.10857","repositories_listed":16,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/circle-loss-a-unified-perspective-of-pair#ran","syntology_url":"https://syntology.ai/paper/2002.10857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10857"}},"official":null}},{"url":"/paper/fine-tuning-cnn-image-retrieval-with-no-human","slug":"fine-tuning-cnn-image-retrieval-with-no-human","title":"Fine-tuning CNN Image Retrieval with No Human Annotation","date":"2017-11-03","arxiv_id":"1711.02512","repositories_listed":14,"syntology":{"n":24,"n_ran":17,"n_constructed":0,"n_ran_checked":16,"n_instrument":1,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":15,"n_pointer_only":5,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/fine-tuning-cnn-image-retrieval-with-no-human#ran","syntology_url":"https://syntology.ai/paper/1711.02512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.02512"}},"official":{"repos":["filipradenovic/cnnimageretrieval-pytorch"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/netvlad-cnn-architecture-for-weakly","slug":"netvlad-cnn-architecture-for-weakly","title":"NetVLAD: CNN architecture for weakly supervised place recognition","date":"2015-11-23","arxiv_id":"1511.07247","repositories_listed":14,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/netvlad-cnn-architecture-for-weakly#ran","syntology_url":"https://syntology.ai/paper/1511.07247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.07247"}},"official":{"repos":["Relja/netvlad"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","repositories_listed":13,"syntology":{"n":51,"n_ran":16,"n_constructed":6,"n_ran_checked":8,"n_instrument":8,"n_unverified":35,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}},"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]}}},{"url":"/paper/large-scale-image-retrieval-with-attentive","slug":"large-scale-image-retrieval-with-attentive","title":"Large-Scale Image Retrieval with Attentive Deep Local Features","date":"2016-12-19","arxiv_id":"1612.06321","repositories_listed":13,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-scale-image-retrieval-with-attentive#ran","syntology_url":"https://syntology.ai/paper/1612.06321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.06321"}},"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","repositories_listed":11,"syntology":{"n":34,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":24,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":34,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 24 unverified","sample_list":"/paper/vilbert-pretraining-task-agnostic#ran","syntology_url":"https://syntology.ai/paper/1908.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02265"}},"official":null}},{"url":"/paper/vse-improving-visual-semantic-embeddings-with","slug":"vse-improving-visual-semantic-embeddings-with","title":"VSE++: Improving Visual-Semantic Embeddings with Hard Negatives","date":"2017-07-18","arxiv_id":"1707.05612","repositories_listed":10,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vse-improving-visual-semantic-embeddings-with#ran","syntology_url":"https://syntology.ai/paper/1707.05612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.05612"}},"official":{"repos":["fartashf/vsepp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/looking-at-outfit-to-parse-clothing","slug":"looking-at-outfit-to-parse-clothing","title":"Looking at Outfit to Parse Clothing","date":"2017-03-04","arxiv_id":"1703.01386","repositories_listed":9,"syntology":null},{"url":"/paper/learning-deep-representations-of-fine-grained","slug":"learning-deep-representations-of-fine-grained","title":"Learning Deep Representations of Fine-grained Visual Descriptions","date":"2016-05-17","arxiv_id":"1605.05395","repositories_listed":9,"syntology":null},{"url":"/paper/combination-of-multiple-global-descriptors","slug":"combination-of-multiple-global-descriptors","title":"Combination of Multiple Global Descriptors for Image Retrieval","date":"2019-03-26","arxiv_id":"1903.10663","repositories_listed":7,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/combination-of-multiple-global-descriptors#ran","syntology_url":"https://syntology.ai/paper/1903.10663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10663"}},"official":{"repos":["naver/cgd"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/vilt-vision-and-language-transformer-without","slug":"vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","repositories_listed":6,"syntology":{"n":4,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/vilt-vision-and-language-transformer-without#ran","syntology_url":"https://syntology.ai/paper/2102.03334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03334"}},"official":{"repos":["dandelin/vilt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/stacked-cross-attention-for-image-text","slug":"stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","arxiv_id":"1803.08024","repositories_listed":6,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stacked-cross-attention-for-image-text#ran","syntology_url":"https://syntology.ai/paper/1803.08024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08024"}},"official":{"repos":["kuanghuei/SCAN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/sampling-matters-in-deep-embedding-learning","slug":"sampling-matters-in-deep-embedding-learning","title":"Sampling Matters in Deep Embedding Learning","date":"2017-06-23","arxiv_id":"1706.07567","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sampling-matters-in-deep-embedding-learning#ran","syntology_url":"https://syntology.ai/paper/1706.07567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.07567"}},"official":null}},{"url":"/paper/particular-object-retrieval-with-integral-max","slug":"particular-object-retrieval-with-integral-max","title":"Particular object retrieval with integral max-pooling of CNN activations","date":"2015-11-18","arxiv_id":"1511.05879","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/particular-object-retrieval-with-integral-max#ran","syntology_url":"https://syntology.ai/paper/1511.05879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.05879"}},"official":null}},{"url":"/paper/dolg-single-stage-image-retrieval-with-deep","slug":"dolg-single-stage-image-retrieval-with-deep","title":"DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features","date":"2021-08-06","arxiv_id":"2108.02927","repositories_listed":5,"syntology":{"n":23,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":0,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/dolg-single-stage-image-retrieval-with-deep#ran","syntology_url":"https://syntology.ai/paper/2108.02927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02927"}},"official":{"repos":["feymanpriv/DOLG"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/google-landmarks-dataset-v2-a-large-scale","slug":"google-landmarks-dataset-v2-a-large-scale","title":"Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval","date":"2020-04-03","arxiv_id":"2004.01804","repositories_listed":5,"syntology":null},{"url":"/paper/deepemd-few-shot-image-classification-with","slug":"deepemd-few-shot-image-classification-with","title":"DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning","date":"2020-03-15","arxiv_id":"2003.06777","repositories_listed":5,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deepemd-few-shot-image-classification-with#ran","syntology_url":"https://syntology.ai/paper/2003.06777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06777"}},"official":null}},{"url":"/paper/unifying-deep-local-and-global-features-for","slug":"unifying-deep-local-and-global-features-for","title":"Unifying Deep Local and Global Features for Image Search","date":"2020-01-14","arxiv_id":"2001.05027","repositories_listed":5,"syntology":null},{"url":"/paper/cross-batch-memory-for-embedding-learning","slug":"cross-batch-memory-for-embedding-learning","title":"Cross-Batch Memory for Embedding Learning","date":"2019-12-14","arxiv_id":"1912.06798","repositories_listed":5,"syntology":null},{"url":"/paper/12-in-1-multi-task-vision-and-language","slug":"12-in-1-multi-task-vision-and-language","title":"12-in-1: Multi-Task Vision and Language Representation Learning","date":"2019-12-05","arxiv_id":"1912.02315","repositories_listed":5,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":20,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/12-in-1-multi-task-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/1912.02315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02315"}},"official":{"repos":["facebookresearch/vilbert-multi-task"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/kornia-an-open-source-differentiable-computer","slug":"kornia-an-open-source-differentiable-computer","title":"Kornia: an Open Source Differentiable Computer Vision Library for PyTorch","date":"2019-10-05","arxiv_id":"1910.02190","repositories_listed":5,"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/kornia-an-open-source-differentiable-computer#ran","syntology_url":"https://syntology.ai/paper/1910.02190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.02190"}},"official":{"repos":["kornia/kornia"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/softtriple-loss-deep-metric-learning-without","slug":"softtriple-loss-deep-metric-learning-without","title":"SoftTriple Loss: Deep Metric Learning Without Triplet Sampling","date":"2019-09-11","arxiv_id":"1909.05235","repositories_listed":5,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/softtriple-loss-deep-metric-learning-without#ran","syntology_url":"https://syntology.ai/paper/1909.05235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05235"}},"official":{"repos":["idstcv/SoftTriple"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/batch-feature-erasing-for-person-re","slug":"batch-feature-erasing-for-person-re","title":"Batch DropBlock Network for Person Re-identification and Beyond","date":"2018-11-17","arxiv_id":"1811.07130","repositories_listed":5,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/batch-feature-erasing-for-person-re#ran","syntology_url":"https://syntology.ai/paper/1811.07130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.07130"}},"official":null}},{"url":"/paper/cnn-image-retrieval-learns-from-bow","slug":"cnn-image-retrieval-learns-from-bow","title":"CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples","date":"2016-04-08","arxiv_id":"1604.02426","repositories_listed":5,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/cnn-image-retrieval-learns-from-bow#ran","syntology_url":"https://syntology.ai/paper/1604.02426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.02426"}},"official":null}},{"url":"/paper/improving-zero-shot-learning-by-mitigating","slug":"improving-zero-shot-learning-by-mitigating","title":"Improving zero-shot learning by mitigating the hubness problem","date":"2014-12-20","arxiv_id":"1412.6568","repositories_listed":5,"syntology":null},{"url":"/paper/cogvlm-visual-expert-for-pretrained-language","slug":"cogvlm-visual-expert-for-pretrained-language","title":"CogVLM: Visual Expert for Pretrained Language Models","date":"2023-11-06","arxiv_id":"2311.03079","repositories_listed":4,"syntology":null},{"url":"/paper/nllb-clip-train-performant-multilingual-image","slug":"nllb-clip-train-performant-multilingual-image","title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","date":"2023-09-04","arxiv_id":"2309.01859","repositories_listed":4,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/nllb-clip-train-performant-multilingual-image#ran","syntology_url":"https://syntology.ai/paper/2309.01859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01859"}},"official":null}},{"url":"/paper/eigenplaces-training-viewpoint-robust-models","slug":"eigenplaces-training-viewpoint-robust-models","title":"EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition","date":"2023-08-21","arxiv_id":"2308.10832","repositories_listed":4,"syntology":{"n":13,"n_ran":12,"n_constructed":2,"n_ran_checked":9,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/eigenplaces-training-viewpoint-robust-models#ran","syntology_url":"https://syntology.ai/paper/2308.10832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10832"}},"official":{"repos":["gmberton/auto_vpr","gmberton/eigenplaces"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/instructblip-towards-general-purpose-vision","slug":"instructblip-towards-general-purpose-vision","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","date":"2023-05-11","arxiv_id":"2305.06500","repositories_listed":4,"syntology":null},{"url":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","repositories_listed":4,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}},"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/semicon-a-learning-to-hash-solution-for-large","slug":"semicon-a-learning-to-hash-solution-for-large","title":"SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval","date":"2022-09-28","arxiv_id":"2209.13833","repositories_listed":4,"syntology":null},{"url":"/paper/flava-a-foundational-language-and-vision","slug":"flava-a-foundational-language-and-vision","title":"FLAVA: A Foundational Language And Vision Alignment Model","date":"2021-12-08","arxiv_id":"2112.04482","repositories_listed":4,"syntology":null},{"url":"/paper/oscar-object-semantics-aligned-pre-training","slug":"oscar-object-semantics-aligned-pre-training","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","date":"2020-04-13","arxiv_id":"2004.06165","repositories_listed":4,"syntology":{"n":23,"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/oscar-object-semantics-aligned-pre-training#ran","syntology_url":"https://syntology.ai/paper/2004.06165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06165"}},"official":{"repos":["microsoft/Oscar"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/composing-text-and-image-for-image-retrieval","slug":"composing-text-and-image-for-image-retrieval","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","date":"2018-12-18","arxiv_id":"1812.07119","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/composing-text-and-image-for-image-retrieval#ran","syntology_url":"https://syntology.ai/paper/1812.07119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.07119"}},"official":null}},{"url":"/paper/working-hard-to-know-your-neighbors-margins","slug":"working-hard-to-know-your-neighbors-margins","title":"Working hard to know your neighbor's margins: Local descriptor learning loss","date":"2017-05-30","arxiv_id":"1705.10872","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/working-hard-to-know-your-neighbors-margins#ran","syntology_url":"https://syntology.ai/paper/1705.10872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.10872"}},"official":{"repos":["DagnyT/hardnet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/a-discriminatively-learned-cnn-embedding-for","slug":"a-discriminatively-learned-cnn-embedding-for","title":"A Discriminatively Learned CNN Embedding for Person Re-identification","date":"2016-11-17","arxiv_id":"1611.05666","repositories_listed":4,"syntology":null},{"url":"/paper/end-to-end-learning-of-deep-visual","slug":"end-to-end-learning-of-deep-visual","title":"End-to-end Learning of Deep Visual Representations for Image Retrieval","date":"2016-10-25","arxiv_id":"1610.07940","repositories_listed":4,"syntology":null},{"url":"/paper/cnn-features-off-the-shelf-an-astounding","slug":"cnn-features-off-the-shelf-an-astounding","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","date":"2014-03-23","arxiv_id":"1403.6382","repositories_listed":4,"syntology":null},{"url":"/paper/encrypted-vector-similarity-computations","slug":"encrypted-vector-similarity-computations","title":"Encrypted Vector Similarity Computations Using Partially Homomorphic Encryption: Applications and Performance Analysis","date":"2025-03-07","arxiv_id":"2503.05850","repositories_listed":3,"syntology":null},{"url":"/paper/geoclip-clip-inspired-alignment-between","slug":"geoclip-clip-inspired-alignment-between","title":"GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization","date":"2023-09-27","arxiv_id":"2309.16020","repositories_listed":3,"syntology":{"n":13,"n_ran":5,"n_constructed":2,"n_ran_checked":5,"n_instrument":0,"n_unverified":8,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/geoclip-clip-inspired-alignment-between#ran","syntology_url":"https://syntology.ai/paper/2309.16020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16020"}},"official":{"repos":["VicenteVivan/geo-clip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-models-in-remote-sensing","slug":"vision-language-models-in-remote-sensing","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","date":"2023-05-09","arxiv_id":"2305.05726","repositories_listed":3,"syntology":null},{"url":"/paper/unicom-universal-and-compact-representation","slug":"unicom-universal-and-compact-representation","title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","date":"2023-04-12","arxiv_id":"2304.05884","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unicom-universal-and-compact-representation#ran","syntology_url":"https://syntology.ai/paper/2304.05884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05884"}},"official":{"repos":["deepglint/unicom"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/sgdraw-scene-graph-drawing-interface-using","slug":"sgdraw-scene-graph-drawing-interface-using","title":"SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation","date":"2022-11-30","arxiv_id":"2211.16697","repositories_listed":3,"syntology":null},{"url":"/paper/tvlt-textless-vision-language-transformer","slug":"tvlt-textless-vision-language-transformer","title":"TVLT: Textless Vision-Language Transformer","date":"2022-09-28","arxiv_id":"2209.14156","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tvlt-textless-vision-language-transformer#ran","syntology_url":"https://syntology.ai/paper/2209.14156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14156"}},"official":{"repos":["zinengtang/tvlt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/one-shot-adaptation-of-gan-in-just-one-clip","slug":"one-shot-adaptation-of-gan-in-just-one-clip","title":"One-Shot Adaptation of GAN in Just One CLIP","date":"2022-03-17","arxiv_id":"2203.09301","repositories_listed":3,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-shot-adaptation-of-gan-in-just-one-clip#ran","syntology_url":"https://syntology.ai/paper/2203.09301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09301"}},"official":{"repos":["anon96652/oneshotclip","cyclomon/oneshotclip","submission6378/oneshotclip"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/webqa-multihop-and-multimodal-qa","slug":"webqa-multihop-and-multimodal-qa","title":"WebQA: Multihop and Multimodal QA","date":"2021-09-01","arxiv_id":"2109.00590","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/webqa-multihop-and-multimodal-qa#ran","syntology_url":"https://syntology.ai/paper/2109.00590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00590"}},"official":null}},{"url":"/paper/image-retrieval-on-real-life-images-with-pre","slug":"image-retrieval-on-real-life-images-with-pre","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","date":"2021-08-09","arxiv_id":"2108.04024","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/image-retrieval-on-real-life-images-with-pre#ran","syntology_url":"https://syntology.ai/paper/2108.04024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04024"}},"official":{"repos":["Cuberick-Orion/CIRPLANT","Cuberick-Orion/CIRR"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-unreasonable-effectiveness-of-1","slug":"on-the-unreasonable-effectiveness-of-1","title":"On the Unreasonable Effectiveness of Centroids in Image Retrieval","date":"2021-04-28","arxiv_id":"2104.13643","repositories_listed":3,"syntology":null},{"url":"/paper/wit-wikipedia-based-image-text-dataset-for","slug":"wit-wikipedia-based-image-text-dataset-for","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","date":"2021-03-02","arxiv_id":"2103.01913","repositories_listed":3,"syntology":null},{"url":"/paper/improving-the-hardnet-descriptor","slug":"improving-the-hardnet-descriptor","title":"Improving the HardNet Descriptor","date":"2020-07-19","arxiv_id":"2007.09699","repositories_listed":3,"syntology":null},{"url":"/paper/self-supervising-fine-grained-region","slug":"self-supervising-fine-grained-region","title":"Self-supervising Fine-grained Region Similarities for Large-scale Image Localization","date":"2020-06-06","arxiv_id":"2006.03926","repositories_listed":3,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/self-supervising-fine-grained-region#ran","syntology_url":"https://syntology.ai/paper/2006.03926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03926"}},"official":{"repos":["yxgeee/SFRS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/fastreid-a-pytorch-toolbox-for-real-world","slug":"fastreid-a-pytorch-toolbox-for-real-world","title":"FastReID: A Pytorch Toolbox for General Instance Re-identification","date":"2020-06-04","arxiv_id":"2006.02631","repositories_listed":3,"syntology":null},{"url":"/paper/adversarial-ranking-attack-and-defense","slug":"adversarial-ranking-attack-and-defense","title":"Adversarial Ranking Attack and Defense","date":"2020-02-26","arxiv_id":"2002.11293","repositories_listed":3,"syntology":null},{"url":"/paper/the-fashion-iq-dataset-retrieving-images-by","slug":"the-fashion-iq-dataset-retrieving-images-by","title":"Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback","date":"2019-05-30","arxiv_id":"1905.12794","repositories_listed":3,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-fashion-iq-dataset-retrieving-images-by#ran","syntology_url":"https://syntology.ai/paper/1905.12794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12794"}},"official":{"repos":["XiaoxiaoGuo/fashion-iq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/improved-embeddings-with-easy-positive","slug":"improved-embeddings-with-easy-positive","title":"Improved Embeddings with Easy Positive Triplet Mining","date":"2019-04-08","arxiv_id":"1904.04370","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improved-embeddings-with-easy-positive#ran","syntology_url":"https://syntology.ai/paper/1904.04370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04370"}},"official":{"repos":["littleredxh/EasyPositiveHardNegative"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperbolic-image-embeddings","slug":"hyperbolic-image-embeddings","title":"Hyperbolic Image Embeddings","date":"2019-04-03","arxiv_id":"1904.02239","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hyperbolic-image-embeddings#ran","syntology_url":"https://syntology.ai/paper/1904.02239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02239"}},"official":{"repos":["KhrulkovV/hyperbolic-image-embeddings","leymir/hyperbolic-image-embeddings"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multigrain-a-unified-image-embedding-for","slug":"multigrain-a-unified-image-embedding-for","title":"MultiGrain: a unified image embedding for classes and instances","date":"2019-02-14","arxiv_id":"1902.05509","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multigrain-a-unified-image-embedding-for#ran","syntology_url":"https://syntology.ai/paper/1902.05509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.05509"}},"official":{"repos":["facebookresearch/multigrain"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/retrieving-similar-e-commerce-images-using","slug":"retrieving-similar-e-commerce-images-using","title":"Retrieving Similar E-Commerce Images Using Deep Learning","date":"2019-01-11","arxiv_id":"1901.03546","repositories_listed":3,"syntology":null},{"url":"/paper/detect-to-retrieve-efficient-regional","slug":"detect-to-retrieve-efficient-regional","title":"Detect-to-Retrieve: Efficient Regional Aggregation for Image Search","date":"2018-12-04","arxiv_id":"1812.01584","repositories_listed":3,"syntology":null},{"url":"/paper/single-shot-scene-text-retrieval","slug":"single-shot-scene-text-retrieval","title":"Single Shot Scene Text Retrieval","date":"2018-08-27","arxiv_id":"1808.09044","repositories_listed":3,"syntology":null},{"url":"/paper/repeatability-is-not-enough-learning-affine","slug":"repeatability-is-not-enough-learning-affine","title":"Repeatability Is Not Enough: Learning Affine Regions via Discriminability","date":"2017-11-17","arxiv_id":"1711.06704","repositories_listed":3,"syntology":null},{"url":"/paper/variational-deep-semantic-hashing-for-text","slug":"variational-deep-semantic-hashing-for-text","title":"Variational Deep Semantic Hashing for Text Documents","date":"2017-08-11","arxiv_id":"1708.03436","repositories_listed":3,"syntology":null},{"url":"/paper/efficient-diffusion-on-region-manifolds","slug":"efficient-diffusion-on-region-manifolds","title":"Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations","date":"2016-11-16","arxiv_id":"1611.05113","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-diffusion-on-region-manifolds#ran","syntology_url":"https://syntology.ai/paper/1611.05113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.05113"}},"official":{"repos":["gtolias/mom"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-image-retrieval-learning-global","slug":"deep-image-retrieval-learning-global","title":"Deep Image Retrieval: Learning global representations for image search","date":"2016-04-05","arxiv_id":"1604.01325","repositories_listed":3,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/deep-image-retrieval-learning-global#ran","syntology_url":"https://syntology.ai/paper/1604.01325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.01325"}},"official":null}},{"url":"/paper/semantic-editing-increment-benefits-zero-shot","slug":"semantic-editing-increment-benefits-zero-shot","title":"Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval","date":"2024-10-28","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/evaluating-pre-trained-convolutional-neural","slug":"evaluating-pre-trained-convolutional-neural","title":"Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrieval","date":"2024-09-14","arxiv_id":"2409.09430","repositories_listed":2,"syntology":null},{"url":"/paper/ldre-llm-based-divergent-reasoning-and","slug":"ldre-llm-based-divergent-reasoning-and","title":"LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval","date":"2024-07-11","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/simple-yet-efficient-towards-self-supervised","slug":"simple-yet-efficient-towards-self-supervised","title":"ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling","date":"2024-06-17","arxiv_id":"2406.11551","repositories_listed":2,"syntology":null},{"url":"/paper/isearle-improving-textual-inversion-for-zero","slug":"isearle-improving-textual-inversion-for-zero","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","date":"2024-05-05","arxiv_id":"2405.02951","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/isearle-improving-textual-inversion-for-zero#ran","syntology_url":"https://syntology.ai/paper/2405.02951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.02951"}},"official":{"repos":["miccunifi/circo"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]}}},{"url":"/paper/learning-embeddings-with-centroid-triplet","slug":"learning-embeddings-with-centroid-triplet","title":"Learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Grasping","date":"2024-04-09","arxiv_id":"2404.06277","repositories_listed":2,"syntology":null},{"url":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/data-efficient-multimodal-fusion-on-a-single","slug":"data-efficient-multimodal-fusion-on-a-single","title":"Data-Efficient Multimodal Fusion on a Single GPU","date":"2023-12-15","arxiv_id":"2312.10144","repositories_listed":2,"syntology":null},{"url":"/paper/pairwise-similarity-learning-is-simple-1","slug":"pairwise-similarity-learning-is-simple-1","title":"Pairwise Similarity Learning is SimPLE","date":"2023-10-13","arxiv_id":"2310.09449","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":1,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pairwise-similarity-learning-is-simple-1#ran","syntology_url":"https://syntology.ai/paper/2310.09449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09449"}},"official":{"repos":["ydwen/opensphere"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/optimization-of-rank-losses-for-image","slug":"optimization-of-rank-losses-for-image","title":"Optimization of Rank Losses for Image Retrieval","date":"2023-09-15","arxiv_id":"2309.08250","repositories_listed":2,"syntology":null},{"url":"/paper/introspective-deep-metric-learning-1","slug":"introspective-deep-metric-learning-1","title":"Introspective Deep Metric Learning","date":"2023-09-11","arxiv_id":"2309.09982","repositories_listed":2,"syntology":null},{"url":"/paper/composed-image-retrieval-using-contrastive","slug":"composed-image-retrieval-using-contrastive","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","date":"2023-08-22","arxiv_id":"2308.11485","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/composed-image-retrieval-using-contrastive#ran","syntology_url":"https://syntology.ai/paper/2308.11485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11485"}},"official":{"repos":["ABaldrati/CLIP4Cir"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/global-features-are-all-you-need-for-image","slug":"global-features-are-all-you-need-for-image","title":"Global Features are All You Need for Image Retrieval and Reranking","date":"2023-08-14","arxiv_id":"2308.06954","repositories_listed":2,"syntology":{"n":18,"n_ran":14,"n_constructed":9,"n_ran_checked":12,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/global-features-are-all-you-need-for-image#ran","syntology_url":"https://syntology.ai/paper/2308.06954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06954"}},"official":{"repos":["shihaoshao-gh/superglobal"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":9,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/histopathology-slide-indexing-and-search-are","slug":"histopathology-slide-indexing-and-search-are","title":"Histopathology Slide Indexing and Search: Are We There Yet?","date":"2023-06-29","arxiv_id":"2306.17019","repositories_listed":2,"syntology":null},{"url":"/paper/candidate-set-re-ranking-for-composed-image","slug":"candidate-set-re-ranking-for-composed-image","title":"Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder","date":"2023-05-25","arxiv_id":"2305.16304","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/candidate-set-re-ranking-for-composed-image#ran","syntology_url":"https://syntology.ai/paper/2305.16304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16304"}},"official":{"repos":["Cuberick-Orion/Candidate-Reranking-CIR"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-composed-image-retrieval-with","slug":"zero-shot-composed-image-retrieval-with","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","date":"2023-03-27","arxiv_id":"2303.15247","repositories_listed":2,"syntology":null},{"url":"/paper/grounding-language-models-to-images-for","slug":"grounding-language-models-to-images-for","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","date":"2023-01-31","arxiv_id":"2301.13823","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/grounding-language-models-to-images-for#ran","syntology_url":"https://syntology.ai/paper/2301.13823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13823"}},"official":{"repos":["kohjingyu/fromage"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/upop-unified-and-progressive-pruning-for","slug":"upop-unified-and-progressive-pruning-for","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","date":"2023-01-31","arxiv_id":"2301.13741","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/upop-unified-and-progressive-pruning-for#ran","syntology_url":"https://syntology.ai/paper/2301.13741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13741"}},"official":{"repos":["sdc17/upop"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/hada-a-graph-based-amalgamation-framework-in","slug":"hada-a-graph-based-amalgamation-framework-in","title":"HADA: A Graph-based Amalgamation Framework in Image-text Retrieval","date":"2023-01-11","arxiv_id":"2301.04742","repositories_listed":2,"syntology":null},{"url":"/paper/altclip-altering-the-language-encoder-in-clip","slug":"altclip-altering-the-language-encoder-in-clip","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","date":"2022-11-12","arxiv_id":"2211.06679","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/altclip-altering-the-language-encoder-in-clip#ran","syntology_url":"https://syntology.ai/paper/2211.06679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06679"}},"official":{"repos":["flagai-open/flagai"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-clinically-motivated-self-supervised","slug":"a-clinically-motivated-self-supervised","title":"A clinically motivated self-supervised approach for content-based image retrieval of CT liver images","date":"2022-07-11","arxiv_id":"2207.04812","repositories_listed":2,"syntology":null},{"url":"/paper/hierarchical-average-precision-training-for","slug":"hierarchical-average-precision-training-for","title":"Hierarchical Average Precision Training for Pertinent Image Retrieval","date":"2022-07-05","arxiv_id":"2207.04873","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":1,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":4,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-average-precision-training-for#ran","syntology_url":"https://syntology.ai/paper/2207.04873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.04873"}},"official":{"repos":["elias-ramzi/happier"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/conditioned-and-composed-image-retrieval","slug":"conditioned-and-composed-image-retrieval","title":"Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features","date":"2022-06-19","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/gradient-backpropagation-through","slug":"gradient-backpropagation-through","title":"Backpropagation through Combinatorial Algorithms: Identity with Projection Works","date":"2022-05-30","arxiv_id":"2205.15213","repositories_listed":2,"syntology":null},{"url":"/paper/introspective-deep-metric-learning","slug":"introspective-deep-metric-learning","title":"Introspective Deep Metric Learning for Image Retrieval","date":"2022-05-09","arxiv_id":"2205.04449","repositories_listed":2,"syntology":null},{"url":"/paper/privacy-preserving-model-upgrades-with","slug":"privacy-preserving-model-upgrades-with","title":"Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval","date":"2022-04-29","arxiv_id":"2204.13919","repositories_listed":2,"syntology":null},{"url":"/paper/multiple-environment-self-adaptive-network","slug":"multiple-environment-self-adaptive-network","title":"Multiple-environment Self-adaptive Network for Aerial-view Geo-localization","date":"2022-04-18","arxiv_id":"2204.08381","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multiple-environment-self-adaptive-network#ran","syntology_url":"https://syntology.ai/paper/2204.08381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08381"}},"official":{"repos":["wtyhub/MuseNet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["named_in_paper"]}}},{"url":"/paper/rethinking-visual-geo-localization-for-large","slug":"rethinking-visual-geo-localization-for-large","title":"Rethinking Visual Geo-localization for Large-Scale Applications","date":"2022-04-05","arxiv_id":"2204.02287","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rethinking-visual-geo-localization-for-large#ran","syntology_url":"https://syntology.ai/paper/2204.02287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02287"}},"official":{"repos":["gmberton/cosplace"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/correlation-verification-for-image-retrieval","slug":"correlation-verification-for-image-retrieval","title":"Correlation Verification for Image Retrieval","date":"2022-04-04","arxiv_id":"2204.01458","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/correlation-verification-for-image-retrieval#ran","syntology_url":"https://syntology.ai/paper/2204.01458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01458"}},"official":{"repos":["sungonce/cvnet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/this-is-my-unicorn-fluffy-personalizing","slug":"this-is-my-unicorn-fluffy-personalizing","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","date":"2022-04-04","arxiv_id":"2204.01694","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/this-is-my-unicorn-fluffy-personalizing#ran","syntology_url":"https://syntology.ai/paper/2204.01694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01694"}},"official":{"repos":["nvlabs/palavra","nvlabs/pervlbenchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/clip-event-connecting-text-and-images-with","slug":"clip-event-connecting-text-and-images-with","title":"CLIP-Event: Connecting Text and Images with Event Structures","date":"2022-01-13","arxiv_id":"2201.05078","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clip-event-connecting-text-and-images-with#ran","syntology_url":"https://syntology.ai/paper/2201.05078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05078"}},"official":{"repos":["limanling/clip-event"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}}],"syntology_records":58,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/image-retrieval-on-roxford-medium","since_archive":"/sota/image-retrieval-on-roxford-medium#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/image-retrieval-on-flickr30k-cn","since_archive":"/sota/image-retrieval-on-flickr30k-cn#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/image-retrieval-on-flickr30k","since_archive":"/sota/image-retrieval-on-flickr30k#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/image-retrieval-on-coco","since_archive":"/sota/image-retrieval-on-coco#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/image-retrieval-on-mscoco","since_archive":"/sota/image-retrieval-on-mscoco#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":218,"papers_where_code_ran_first_page":"/task/image-retrieval/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":23,"url":"/task/image-retrieval/papers/2","json":"/task/image-retrieval/papers/2.json","rows":100},{"order":"archive","page":3,"of":23,"url":"/task/image-retrieval/papers/3","json":"/task/image-retrieval/papers/3.json","rows":100},{"order":"archive","page":4,"of":23,"url":"/task/image-retrieval/papers/4","json":"/task/image-retrieval/papers/4.json","rows":100},{"order":"archive","page":5,"of":23,"url":"/task/image-retrieval/papers/5","json":"/task/image-retrieval/papers/5.json","rows":100},{"order":"archive","page":6,"of":23,"url":"/task/image-retrieval/papers/6","json":"/task/image-retrieval/papers/6.json","rows":100},{"order":"archive","page":7,"of":23,"url":"/task/image-retrieval/papers/7","json":"/task/image-retrieval/papers/7.json","rows":100},{"order":"archive","page":8,"of":23,"url":"/task/image-retrieval/papers/8","json":"/task/image-retrieval/papers/8.json","rows":100},{"order":"archive","page":9,"of":23,"url":"/task/image-retrieval/papers/9","json":"/task/image-retrieval/papers/9.json","rows":100},{"order":"archive","page":10,"of":23,"url":"/task/image-retrieval/papers/10","json":"/task/image-retrieval/papers/10.json","rows":100},{"order":"archive","page":11,"of":23,"url":"/task/image-retrieval/papers/11","json":"/task/image-retrieval/papers/11.json","rows":100},{"order":"archive","page":12,"of":23,"url":"/task/image-retrieval/papers/12","json":"/task/image-retrieval/papers/12.json","rows":100},{"order":"archive","page":13,"of":23,"url":"/task/image-retrieval/papers/13","json":"/task/image-retrieval/papers/13.json","rows":100},{"order":"archive","page":14,"of":23,"url":"/task/image-retrieval/papers/14","json":"/task/image-retrieval/papers/14.json","rows":100},{"order":"archive","page":15,"of":23,"url":"/task/image-retrieval/papers/15","json":"/task/image-retrieval/papers/15.json","rows":100},{"order":"archive","page":16,"of":23,"url":"/task/image-retrieval/papers/16","json":"/task/image-retrieval/papers/16.json","rows":100},{"order":"archive","page":17,"of":23,"url":"/task/image-retrieval/papers/17","json":"/task/image-retrieval/papers/17.json","rows":100},{"order":"archive","page":18,"of":23,"url":"/task/image-retrieval/papers/18","json":"/task/image-retrieval/papers/18.json","rows":100},{"order":"archive","page":19,"of":23,"url":"/task/image-retrieval/papers/19","json":"/task/image-retrieval/papers/19.json","rows":100},{"order":"archive","page":20,"of":23,"url":"/task/image-retrieval/papers/20","json":"/task/image-retrieval/papers/20.json","rows":100},{"order":"archive","page":21,"of":23,"url":"/task/image-retrieval/papers/21","json":"/task/image-retrieval/papers/21.json","rows":100},{"order":"archive","page":22,"of":23,"url":"/task/image-retrieval/papers/22","json":"/task/image-retrieval/papers/22.json","rows":100},{"order":"archive","page":23,"of":23,"url":"/task/image-retrieval/papers/23","json":"/task/image-retrieval/papers/23.json","rows":39},{"order":"ran","page":1,"of":3,"url":"/task/image-retrieval/papers/ran/1","json":"/task/image-retrieval/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":3,"url":"/task/image-retrieval/papers/ran/2","json":"/task/image-retrieval/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":3,"url":"/task/image-retrieval/papers/ran/3","json":"/task/image-retrieval/papers/ran/3.json","rows":18}],"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"17be1196779415aad28a1f8c878cb017b0fe4a5022d601f627dcf352450a55ce","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}