{"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/cross-modal-retrieval","name":"Cross-Modal Retrieval","slug":"cross-modal-retrieval","description_markdown":"**Cross-Modal Retrieval (CMR)** is a task of retrieving items across different modalities, such as image, text, video, and audio. The core challenge of CMR is the *heterogeneity gap*, which arises because data from different modalities have distinct representations, making direct comparison difficult.  To address this, most CMR methods focus on learning a *shared latent embedding space*. In this space, concepts from different modalities are projected, allowing their similarity to be measured using a distance metric.\r\n\r\n\r\n<span class=\"description-source\">[Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study](https://arxiv.org/abs/2301.05174)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":522,"papers_with_code":244,"benchmarks":13,"benchmark_tables_in_archive":13,"benchmark_tables_shown":13,"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":24,"subtasks":5,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/cross-modal-retrieval-on-coco-2014","slug":"cross-modal-retrieval-on-coco-2014","dataset":"COCO 2014","dataset_url":"/dataset/coco","rows_in_archive":36,"metrics":["Text-to-image R@1","Text-to-image R@5","Text-to-image R@10","Image-to-text R@1","Image-to-text R@5","Image-to-text R@10"],"first_row_in_archive_order":{"model":"VAST","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","paper_url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","paper_date":"2023-05-29","arxiv_id":"2305.18500","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}],"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/cross-modal-retrieval-on-flickr30k","slug":"cross-modal-retrieval-on-flickr30k","dataset":"Flickr30k","dataset_url":"/dataset/flickr30k","rows_in_archive":27,"metrics":["Image-to-text R@1","Image-to-text R@5","Image-to-text R@10","Text-to-image R@1","Text-to-image R@5","Text-to-image R@10"],"first_row_in_archive_order":{"model":"X2-VLM (large)","paper_title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","paper_url":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","paper_date":"2022-11-22","arxiv_id":"2211.12402","code_links":[{"title":"zengyan-97/x-vlm","url":"https://github.com/zengyan-97/x-vlm"},{"title":"zengyan-97/x2-vlm","url":"https://github.com/zengyan-97/x2-vlm"}],"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/x-2-vlm-all-in-one-pre-trained-model-for#ran","syntology_url":"https://syntology.ai/paper/2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}},"official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/cross-modal-retrieval-on-rsicd","slug":"cross-modal-retrieval-on-rsicd","dataset":"RSICD","dataset_url":"/dataset/rsicd","rows_in_archive":10,"metrics":["Mean Recall","Image-to-text R@1","text-to-image R@1"],"first_row_in_archive_order":{"model":"HarMA (w/ GeoRSCLIP)","paper_title":"Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment","paper_url":"/paper/efficient-remote-sensing-with-harmonized","paper_date":"2024-04-28","arxiv_id":"2404.18253","code_links":[{"title":"seekerhuang/harma","url":"https://github.com/seekerhuang/harma"}],"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/efficient-remote-sensing-with-harmonized#ran","syntology_url":"https://syntology.ai/paper/2404.18253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18253"}},"official":{"repos":["seekerhuang/harma"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/cross-modal-retrieval-on-rsitmd","slug":"cross-modal-retrieval-on-rsitmd","dataset":"RSITMD","dataset_url":"/dataset/rsitmd","rows_in_archive":10,"metrics":["Image-to-text R@1","Mean Recall","text-to-imageR@1"],"first_row_in_archive_order":{"model":"HarMA (w/ GeoRSCLIP)","paper_title":"Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment","paper_url":"/paper/efficient-remote-sensing-with-harmonized","paper_date":"2024-04-28","arxiv_id":"2404.18253","code_links":[{"title":"seekerhuang/harma","url":"https://github.com/seekerhuang/harma"}],"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/efficient-remote-sensing-with-harmonized#ran","syntology_url":"https://syntology.ai/paper/2404.18253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18253"}},"official":{"repos":["seekerhuang/harma"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/cross-modal-retrieval-on-chebi-20","slug":"cross-modal-retrieval-on-chebi-20","dataset":"ChEBI-20","dataset_url":"/dataset/chebi-20","rows_in_archive":9,"metrics":["Hits@1","Hits@10","Mean Rank","Test MRR"],"first_row_in_archive_order":{"model":"CLASS (ORMA)","paper_title":"CLASS: Enhancing Cross-Modal Text-Molecule Retrieval Performance and Training Efficiency","paper_url":"/paper/class-enhancing-cross-modal-text-molecule","paper_date":"2025-02-17","arxiv_id":"2502.11633","code_links":[],"syntology":null}},{"leaderboard":"/sota/cross-modal-retrieval-on-recipe1m","slug":"cross-modal-retrieval-on-recipe1m","dataset":"Recipe1M","dataset_url":"/dataset/recipe1m-1","rows_in_archive":9,"metrics":["Image-to-text R@1","Text-to-image R@1"],"first_row_in_archive_order":{"model":"VLPCook (R1M+)","paper_title":"Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval","paper_url":"/paper/structured-vision-language-pretraining-for","paper_date":"2022-12-08","arxiv_id":"2212.04267","code_links":[{"title":"mshukor/vlpcook","url":"https://github.com/mshukor/vlpcook"}],"syntology":null}},{"leaderboard":"/sota/cross-modal-retrieval-on-mscoco-1k","slug":"cross-modal-retrieval-on-mscoco-1k","dataset":"MSCOCO-1k","dataset_url":"/dataset/coco","rows_in_archive":2,"metrics":["Image-to-text R@1","Text-to-image R@1"],"first_row_in_archive_order":{"model":"NAPReg","paper_title":"NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings","paper_url":"/paper/napreg-nouns-as-proxies-regularization-for","paper_date":"2023-01-07","arxiv_id":null,"code_links":[{"title":"bhavinjawade/NAPReq","url":"https://github.com/bhavinjawade/NAPReq"}],"syntology":null}},{"leaderboard":"/sota/cross-modal-retrieval-on-recipe1m-1","slug":"cross-modal-retrieval-on-recipe1m-1","dataset":"Recipe1M+","dataset_url":"/dataset/recipe1m-1","rows_in_archive":2,"metrics":["Image-to-text R@1","Text-to-image R@1"],"first_row_in_archive_order":{"model":"VLPCook","paper_title":"Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval","paper_url":"/paper/structured-vision-language-pretraining-for","paper_date":"2022-12-08","arxiv_id":"2212.04267","code_links":[{"title":"mshukor/vlpcook","url":"https://github.com/mshukor/vlpcook"}],"syntology":null}},{"leaderboard":"/sota/cross-modal-retrieval-on-soundingearth","slug":"cross-modal-retrieval-on-soundingearth","dataset":"SoundingEarth","dataset_url":"/dataset/soundingearth","rows_in_archive":2,"metrics":["Median Rank","Image-to-sound R@100","Sound-to-image R@100"],"first_row_in_archive_order":{"model":"GeoCLAP","paper_title":"Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping","paper_url":"/paper/learning-tri-modal-embeddings-for-zero-shot","paper_date":"2023-09-19","arxiv_id":"2309.10667","code_links":[{"title":"mvrl/geoclap","url":"https://github.com/mvrl/geoclap"}],"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-tri-modal-embeddings-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2309.10667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10667"}},"official":{"repos":["mvrl/geoclap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/cross-modal-retrieval-on-cuhk-pedes","slug":"cross-modal-retrieval-on-cuhk-pedes","dataset":"CUHK-PEDES","dataset_url":"/dataset/cuhk-pedes","rows_in_archive":1,"metrics":["Text-to-image Medr"],"first_row_in_archive_order":{"model":"Dual Path","paper_title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","paper_url":"/paper/dual-path-convolutional-image-text-embedding","paper_date":"2017-11-15","arxiv_id":"1711.05535","code_links":[{"title":"layumi/Image-Text-Embedding","url":"https://github.com/layumi/Image-Text-Embedding"},{"title":"pshroff04/Dual_Path_CNN","url":"https://github.com/pshroff04/Dual_Path_CNN"}],"syntology":null}},{"leaderboard":"/sota/cross-modal-retrieval-on-flickr-8k","slug":"cross-modal-retrieval-on-flickr-8k","dataset":"Flickr-8k","dataset_url":"/dataset/flickr-8k","rows_in_archive":1,"metrics":["Image-to-text R@1","Text-to-image R@1"],"first_row_in_archive_order":{"model":"NAPReg","paper_title":"NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings","paper_url":"/paper/napreg-nouns-as-proxies-regularization-for","paper_date":"2023-01-07","arxiv_id":null,"code_links":[{"title":"bhavinjawade/NAPReq","url":"https://github.com/bhavinjawade/NAPReq"}],"syntology":null}},{"leaderboard":"/sota/cross-modal-retrieval-on-ms-coco-2014-1","slug":"cross-modal-retrieval-on-ms-coco-2014-1","dataset":"MS-COCO-2014","dataset_url":null,"rows_in_archive":1,"metrics":["Text-to-image R@1"],"first_row_in_archive_order":{"model":"NAPReg","paper_title":"NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings","paper_url":"/paper/napreg-nouns-as-proxies-regularization-for","paper_date":"2023-01-07","arxiv_id":null,"code_links":[{"title":"bhavinjawade/NAPReq","url":"https://github.com/bhavinjawade/NAPReq"}],"syntology":null}},{"leaderboard":"/sota/cross-modal-retrieval-on-mscoco","slug":"cross-modal-retrieval-on-mscoco","dataset":"MSCOCO","dataset_url":"/dataset/mscoco","rows_in_archive":1,"metrics":["Image-to-text R@1"],"first_row_in_archive_order":{"model":"3SHNet","paper_title":"3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting","paper_url":"/paper/3shnet-boosting-image-sentence-retrieval-via","paper_date":"2024-04-26","arxiv_id":"2404.17273","code_links":[{"title":"xurige1995/3shnet","url":"https://github.com/xurige1995/3shnet"}],"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/3shnet-boosting-image-sentence-retrieval-via#ran","syntology_url":"https://syntology.ai/paper/2404.17273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.17273"}},"official":{"repos":["xurige1995/3shnet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/flickr30k","name":"Flickr30k","full_name":"Flickr30k","num_papers_in_archive":880},{"url":"/dataset/nus-wide","name":"NUS-WIDE","full_name":"","num_papers_in_archive":348},{"url":"/dataset/pascal-voc-2007","name":"PASCAL VOC 2007","full_name":"PASCAL VOC 2007","num_papers_in_archive":126},{"url":"/dataset/cuhk-pedes","name":"CUHK-PEDES","full_name":"CUHK-PEDES","num_papers_in_archive":93},{"url":"/dataset/mscoco","name":"MSCOCO","full_name":"","num_papers_in_archive":90},{"url":"/dataset/rsicd","name":"RSICD","full_name":"Remote Sensing Image Captioning Dataset","num_papers_in_archive":70},{"url":"/dataset/recipe1m-1","name":"Recipe1M+","full_name":"Recipe1M+","num_papers_in_archive":68},{"url":"/dataset/chebi-20","name":"ChEBI-20","full_name":"","num_papers_in_archive":43},{"url":"/dataset/rsitmd","name":"RSITMD","full_name":"","num_papers_in_archive":26},{"url":"/dataset/semart","name":"SemArt","full_name":"","num_papers_in_archive":16},{"url":"/dataset/soundingearth","name":"SoundingEarth","full_name":"","num_papers_in_archive":8},{"url":"/dataset/chinesefoodnet","name":"ChineseFoodNet","full_name":"","num_papers_in_archive":6},{"url":"/dataset/flickr-8k","name":"Flickr-8k","full_name":"","num_papers_in_archive":5},{"url":"/dataset/song-describer-dataset","name":"Song Describer Dataset","full_name":"","num_papers_in_archive":5},{"url":"/dataset/twitter100k","name":"Twitter100k","full_name":"","num_papers_in_archive":5},{"url":"/dataset/ctc","name":"CTC","full_name":"COCO-Text Captioned","num_papers_in_archive":3},{"url":"/dataset/posescript","name":"PoseScript","full_name":"","num_papers_in_archive":2},{"url":"/dataset/cinat-birds-2021","name":"CiNAT-Birds-2021","full_name":"Cross-View iNaturalist Birds 2021","num_papers_in_archive":1},{"url":"/dataset/ushasi-chaudhuri","name":"Earth on Canvas","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/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/musechat-dataset","name":"MuseChat Dataset","full_name":"MuseChat: A Conversational Music Recommendation System for Videos (CVPR 2024 Highlight Paper)","num_papers_in_archive":1},{"url":"/dataset/taxabench-8k","name":"TaxaBench-8k","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/cross-modal-retrieval-on-rsitmd","name":"Cross-Modal Retrieval on RSITMD"},{"url":"/task/cross-modal-retrieval-with-noisy","name":"Cross-modal retrieval with noisy correspondence"},{"url":"/task/image-text-matching","name":"Image-text matching"},{"url":"/task/multilingual-cross-modal-retrieval","name":"multilingual cross-modal retrieval"},{"url":"/task/zero-shot-composed-person-retrieval","name":"Zero-shot Composed Person Retrieval"}],"parent_tasks":[{"url":"/task/cross-modal-information-retrieval","name":"Cross-Modal Information Retrieval"},{"url":"/task/multi-modal","name":"Image Retrieval with Multi-Modal Query"}],"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":6,"rows_per_page":100,"shown":100,"of":522,"of_with_code":244,"tagged_in_all":522,"counts":{"archive_papers_tagged":522,"with_a_code_link":244,"where_syntology_ran_a_sample":70,"not_listed_spam_title":0,"listed":522,"listed_where_code_ran":70,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":56,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":56,"listed_every_run_a_failure_of_syntologys_instrument":14,"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/stacked-capsule-autoencoders","slug":"stacked-capsule-autoencoders","title":"Stacked Capsule Autoencoders","date":"2019-06-17","arxiv_id":"1906.06818","repositories_listed":11,"syntology":{"n":29,"n_ran":25,"n_constructed":0,"n_ran_checked":24,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":23,"n_pointer_only":1,"phrase":"25 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 0 honoured, 1 violated, 23 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/stacked-capsule-autoencoders#ran","syntology_url":"https://syntology.ai/paper/1906.06818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.06818"}},"official":{"repos":["google-research/google-research","akosiorek/stacked_capsule_autoencoders"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"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/rescaling-egocentric-vision","slug":"rescaling-egocentric-vision","title":"Rescaling Egocentric Vision","date":"2020-06-23","arxiv_id":"2006.13256","repositories_listed":7,"syntology":{"n":18,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/rescaling-egocentric-vision#ran","syntology_url":"https://syntology.ai/paper/2006.13256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13256"}},"official":{"repos":["epic-kitchens/epic-kitchens-100-narrator","epic-kitchens/epic-kitchens-100-annotations"],"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/align-before-fuse-vision-and-language","slug":"align-before-fuse-vision-and-language","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","date":"2021-07-16","arxiv_id":"2107.07651","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/align-before-fuse-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.07651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07651"}},"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/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/scaling-up-visual-and-vision-language","slug":"scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","arxiv_id":"2102.05918","repositories_listed":5,"syntology":{"n":10,"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scaling-up-visual-and-vision-language#ran","syntology_url":"https://syntology.ai/paper/2102.05918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05918"}},"official":null}},{"url":"/paper/a-molecular-multimodal-foundation-model","slug":"a-molecular-multimodal-foundation-model","title":"A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language","date":"2022-09-12","arxiv_id":"2209.05481","repositories_listed":4,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"5 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-molecular-multimodal-foundation-model#ran","syntology_url":"https://syntology.ai/paper/2209.05481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.05481"}},"official":{"repos":["bingsu12/momu"],"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/probabilistic-embeddings-for-cross-modal","slug":"probabilistic-embeddings-for-cross-modal","title":"Probabilistic Embeddings for Cross-Modal Retrieval","date":"2021-01-13","arxiv_id":"2101.05068","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/probabilistic-embeddings-for-cross-modal#ran","syntology_url":"https://syntology.ai/paper/2101.05068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.05068"}},"official":{"repos":["naver-ai/pcme"],"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/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/fine-grained-video-text-retrieval-with","slug":"fine-grained-video-text-retrieval-with","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","date":"2020-03-01","arxiv_id":"2003.00392","repositories_listed":4,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fine-grained-video-text-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2003.00392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00392"}},"official":null}},{"url":"/paper/deep-visual-semantic-alignments-for","slug":"deep-visual-semantic-alignments-for","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","date":"2014-12-07","arxiv_id":"1412.2306","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/deep-visual-semantic-alignments-for#ran","syntology_url":"https://syntology.ai/paper/1412.2306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1412.2306"}},"official":null}},{"url":"/paper/imagebind-one-embedding-space-to-bind-them","slug":"imagebind-one-embedding-space-to-bind-them","title":"ImageBind: One Embedding Space To Bind Them All","date":"2023-05-09","arxiv_id":"2305.05665","repositories_listed":3,"syntology":{"n":34,"n_ran":24,"n_constructed":14,"n_ran_checked":21,"n_instrument":3,"n_unverified":10,"n_honours":1,"n_violates":1,"n_no_contract":19,"n_pointer_only":32,"phrase":"24 ran (of which 14 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 1 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/imagebind-one-embedding-space-to-bind-them#ran","syntology_url":"https://syntology.ai/paper/2305.05665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05665"}},"official":{"repos":["facebookresearch/imagebind"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":10,"n_ran_no_instrument_failure":15,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-channel-mix-method-for-fine-grained-cross","slug":"a-channel-mix-method-for-fine-grained-cross","title":"A Channel Mix Method for Fine-Grained Cross-Modal Retrieval","date":"2022-08-26","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/iglue-a-benchmark-for-transfer-learning","slug":"iglue-a-benchmark-for-transfer-learning","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","date":"2022-01-27","arxiv_id":"2201.11732","repositories_listed":3,"syntology":{"n":21,"n_ran":17,"n_constructed":2,"n_ran_checked":11,"n_instrument":6,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/iglue-a-benchmark-for-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/2201.11732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11732"}},"official":{"repos":["e-bug/iglue","e-bug/volta"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":2,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-of-training-end-to-end","slug":"an-empirical-study-of-training-end-to-end","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","date":"2021-11-03","arxiv_id":"2111.02387","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":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/an-empirical-study-of-training-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2111.02387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02387"}},"official":{"repos":["zdou0830/meter"],"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/unimo-towards-unified-modal-understanding-and","slug":"unimo-towards-unified-modal-understanding-and","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","date":"2020-12-31","arxiv_id":"2012.15409","repositories_listed":3,"syntology":null},{"url":"/paper/fashionbert-text-and-image-matching-with","slug":"fashionbert-text-and-image-matching-with","title":"FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval","date":"2020-05-20","arxiv_id":"2005.09801","repositories_listed":3,"syntology":null},{"url":"/paper/derm1m-a-million-scale-vision-language","slug":"derm1m-a-million-scale-vision-language","title":"Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology","date":"2025-03-19","arxiv_id":"2503.14911","repositories_listed":2,"syntology":null},{"url":"/paper/multimodal-whole-slide-foundation-model-for","slug":"multimodal-whole-slide-foundation-model-for","title":"Multimodal Whole Slide Foundation Model for Pathology","date":"2024-11-29","arxiv_id":"2411.19666","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/multimodal-whole-slide-foundation-model-for#ran","syntology_url":"https://syntology.ai/paper/2411.19666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19666"}},"official":{"repos":["mahmoodlab/titan"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/procedure-aware-surgical-video-language","slug":"procedure-aware-surgical-video-language","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","date":"2024-09-30","arxiv_id":"2410.00263","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":1,"n_ran_checked":7,"n_instrument":2,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":15,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/procedure-aware-surgical-video-language#ran","syntology_url":"https://syntology.ai/paper/2410.00263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00263"}},"official":null}},{"url":"/paper/merlin-a-vision-language-foundation-model-for","slug":"merlin-a-vision-language-foundation-model-for","title":"Merlin: A Vision Language Foundation Model for 3D Computed Tomography","date":"2024-06-10","arxiv_id":"2406.06512","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/merlin-a-vision-language-foundation-model-for#ran","syntology_url":"https://syntology.ai/paper/2406.06512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06512"}},"official":null}},{"url":"/paper/leanvec-search-your-vectors-faster-by-making","slug":"leanvec-search-your-vectors-faster-by-making","title":"LeanVec: Searching vectors faster by making them fit","date":"2023-12-26","arxiv_id":"2312.16335","repositories_listed":2,"syntology":null},{"url":"/paper/quilt-1m-one-million-image-text-pairs-for-1","slug":"quilt-1m-one-million-image-text-pairs-for-1","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","date":"2023-06-20","arxiv_id":"2306.11207","repositories_listed":2,"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/quilt-1m-one-million-image-text-pairs-for-1#ran","syntology_url":"https://syntology.ai/paper/2306.11207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11207"}},"official":{"repos":["wisdomikezogwo/quilt1m"],"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/reducing-semantic-confusion-scene-aware","slug":"reducing-semantic-confusion-scene-aware","title":"Reducing Semantic Confusion: Scene-aware Aggregation Network for Remote Sensing Cross-modal Retrieval","date":"2023-06-12","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/molfm-a-multimodal-molecular-foundation-model","slug":"molfm-a-multimodal-molecular-foundation-model","title":"MolFM: A Multimodal Molecular Foundation Model","date":"2023-06-06","arxiv_id":"2307.09484","repositories_listed":2,"syntology":null},{"url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","repositories_listed":2,"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/atomic-an-image-text-retrieval-test","slug":"atomic-an-image-text-retrieval-test","title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","date":"2023-04-04","arxiv_id":"2304.01961","repositories_listed":2,"syntology":null},{"url":"/paper/a-differentiable-semantic-metric","slug":"a-differentiable-semantic-metric","title":"A Differentiable Semantic Metric Approximation in Probabilistic Embedding for Cross-Modal Retrieval","date":"2022-12-06","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/semantic-conditional-diffusion-networks-for","slug":"semantic-conditional-diffusion-networks-for","title":"Semantic-Conditional Diffusion Networks for Image Captioning","date":"2022-12-06","arxiv_id":"2212.03099","repositories_listed":2,"syntology":null},{"url":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","slug":"x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","date":"2022-11-22","arxiv_id":"2211.12402","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/x-2-vlm-all-in-one-pre-trained-model-for#ran","syntology_url":"https://syntology.ai/paper/2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}},"official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"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/dissecting-deep-metric-learning-losses-for","slug":"dissecting-deep-metric-learning-losses-for","title":"Dissecting Deep Metric Learning Losses for Image-Text Retrieval","date":"2022-10-21","arxiv_id":"2210.13188","repositories_listed":2,"syntology":null},{"url":"/paper/image-as-a-foreign-language-beit-pretraining","slug":"image-as-a-foreign-language-beit-pretraining","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","date":"2022-08-22","arxiv_id":"2208.10442","repositories_listed":2,"syntology":null},{"url":"/paper/fusion-and-orthogonal-projection-for-improved","slug":"fusion-and-orthogonal-projection-for-improved","title":"Fusion and Orthogonal Projection for Improved Face-Voice Association","date":"2021-12-20","arxiv_id":"2112.10483","repositories_listed":2,"syntology":null},{"url":"/paper/florence-a-new-foundation-model-for-computer","slug":"florence-a-new-foundation-model-for-computer","title":"Florence: A New Foundation Model for Computer Vision","date":"2021-11-22","arxiv_id":"2111.11432","repositories_listed":2,"syntology":null},{"url":"/paper/visual-spatio-temporal-relation-enhanced","slug":"visual-spatio-temporal-relation-enhanced","title":"BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval","date":"2021-10-29","arxiv_id":"2110.15609","repositories_listed":2,"syntology":null},{"url":"/paper/x-modaler-a-versatile-and-high-performance","slug":"x-modaler-a-versatile-and-high-performance","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","date":"2021-08-18","arxiv_id":"2108.08217","repositories_listed":2,"syntology":null},{"url":"/paper/opt-omni-perception-pre-trainer-for-cross","slug":"opt-omni-perception-pre-trainer-for-cross","title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","date":"2021-07-01","arxiv_id":"2107.00249","repositories_listed":2,"syntology":null},{"url":"/paper/visual-semantic-reasoning-for-image-text","slug":"visual-semantic-reasoning-for-image-text","title":"Visual Semantic Reasoning for Image-Text Matching","date":"2019-09-06","arxiv_id":"1909.02701","repositories_listed":2,"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/visual-semantic-reasoning-for-image-text#ran","syntology_url":"https://syntology.ai/paper/1909.02701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02701"}},"official":{"repos":["KunpengLi1994/VSRN"],"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/deep-triplet-neural-networks-with-cluster-cca","slug":"deep-triplet-neural-networks-with-cluster-cca","title":"Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval","date":"2019-08-10","arxiv_id":"1908.03737","repositories_listed":2,"syntology":null},{"url":"/paper/learning-cross-modal-embeddings-with","slug":"learning-cross-modal-embeddings-with","title":"Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images","date":"2019-05-03","arxiv_id":"1905.01273","repositories_listed":2,"syntology":null},{"url":"/paper/dual-path-convolutional-image-text-embedding","slug":"dual-path-convolutional-image-text-embedding","title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","date":"2017-11-15","arxiv_id":"1711.05535","repositories_listed":2,"syntology":null},{"url":"/paper/content-based-video-music-retrieval-using","slug":"content-based-video-music-retrieval-using","title":"Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint","date":"2017-04-22","arxiv_id":"1704.06761","repositories_listed":2,"syntology":null},{"url":"/paper/picture-it-in-your-mind-generating-high-level","slug":"picture-it-in-your-mind-generating-high-level","title":"Picture It In Your Mind: Generating High Level Visual Representations From Textual Descriptions","date":"2016-06-23","arxiv_id":"1606.07287","repositories_listed":2,"syntology":null},{"url":"/paper/deep-cross-modal-hashing-1","slug":"deep-cross-modal-hashing-1","title":"Deep Cross-Modal Hashing","date":"2016-02-15","arxiv_id":"1602.02255","repositories_listed":2,"syntology":null},{"url":"/paper/order-embeddings-of-images-and-language","slug":"order-embeddings-of-images-and-language","title":"Order-Embeddings of Images and Language","date":"2015-11-19","arxiv_id":"1511.06361","repositories_listed":2,"syntology":null},{"url":"/paper/contextrefine-clip-for-epic-kitchens-100","slug":"contextrefine-clip-for-epic-kitchens-100","title":"ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025","date":"2025-06-12","arxiv_id":"2506.10550","repositories_listed":1,"syntology":null},{"url":"/paper/smotext-smote-meets-large-language-models","slug":"smotext-smote-meets-large-language-models","title":"SMOTExT: SMOTE meets Large Language Models","date":"2025-05-19","arxiv_id":"2505.13434","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11404","slug":"2505-11404","title":"Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner","date":"2025-05-16","arxiv_id":"2505.11404","repositories_listed":1,"syntology":null},{"url":"/paper/make-multi-aspect-knowledge-enhanced-vision","slug":"make-multi-aspect-knowledge-enhanced-vision","title":"MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment","date":"2025-05-14","arxiv_id":"2505.09372","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-embeddings-for-frozen-vision","slug":"probabilistic-embeddings-for-frozen-vision","title":"Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models","date":"2025-05-08","arxiv_id":"2505.05163","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-and-generating-modalities-for","slug":"disentangling-and-generating-modalities-for","title":"Disentangling and Generating Modalities for Recommendation in Missing Modality Scenarios","date":"2025-04-23","arxiv_id":"2504.16352","repositories_listed":1,"syntology":null},{"url":"/paper/lrsclip-a-vision-language-foundation-model","slug":"lrsclip-a-vision-language-foundation-model","title":"LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text","date":"2025-03-25","arxiv_id":"2503.19311","repositories_listed":1,"syntology":null},{"url":"/paper/neighborretr-balancing-hub-centrality-in","slug":"neighborretr-balancing-hub-centrality-in","title":"NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval","date":"2025-03-13","arxiv_id":"2503.10526","repositories_listed":1,"syntology":null},{"url":"/paper/composed-multi-modal-retrieval-a-survey-of","slug":"composed-multi-modal-retrieval-a-survey-of","title":"Composed Multi-modal Retrieval: A Survey of Approaches and Applications","date":"2025-03-03","arxiv_id":"2503.01334","repositories_listed":1,"syntology":null},{"url":"/paper/recurrence-enhanced-vision-and-language","slug":"recurrence-enhanced-vision-and-language","title":"Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval","date":"2025-03-03","arxiv_id":"2503.01980","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/recurrence-enhanced-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2503.01980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01980"}},"official":{"repos":["aimagelab/ret"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/recon-enhancing-true-correspondence-1","slug":"recon-enhancing-true-correspondence-1","title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","date":"2025-02-27","arxiv_id":"2502.19962","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 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) · 2 unverified","sample_list":"/paper/recon-enhancing-true-correspondence-1#ran","syntology_url":"https://syntology.ai/paper/2502.19962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19962"}},"official":{"repos":["qxzha/ReCon"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/gaia-a-global-multi-modal-multi-scale-vision","slug":"gaia-a-global-multi-modal-multi-scale-vision","title":"GAIA: A Global, Multi-modal, Multi-scale Vision-Language Dataset for Remote Sensing Image Analysis","date":"2025-02-13","arxiv_id":"2502.09598","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reversible-consistency-learning-for","slug":"deep-reversible-consistency-learning-for","title":"Deep Reversible Consistency Learning for Cross-modal Retrieval","date":"2025-01-10","arxiv_id":"2501.05686","repositories_listed":1,"syntology":null},{"url":"/paper/robust-self-paced-hashing-for-cross-modal","slug":"robust-self-paced-hashing-for-cross-modal","title":"Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels","date":"2025-01-03","arxiv_id":"2501.01699","repositories_listed":1,"syntology":null},{"url":"/paper/fuzzy-multimodal-learning-for-trusted-cross","slug":"fuzzy-multimodal-learning-for-trusted-cross","title":"Fuzzy Multimodal Learning for Trusted Cross-modal Retrieval","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-identity-aware-cross-modal-retrieval","slug":"towards-identity-aware-cross-modal-retrieval","title":"Towards Identity-Aware Cross-Modal Retrieval: a Dataset and a Baseline","date":"2024-12-30","arxiv_id":"2412.21009","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-adapter-with-semantics-disentangling","slug":"dynamic-adapter-with-semantics-disentangling","title":"Dynamic Adapter with Semantics Disentangling for Cross-lingual Cross-modal Retrieval","date":"2024-12-18","arxiv_id":"2412.13510","repositories_listed":1,"syntology":null},{"url":"/paper/impact-a-large-scale-integrated-multimodal","slug":"impact-a-large-scale-integrated-multimodal","title":"IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents","date":"2024-12-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/taxabind-a-unified-embedding-space-for","slug":"taxabind-a-unified-embedding-space-for","title":"TaxaBind: A Unified Embedding Space for Ecological Applications","date":"2024-11-01","arxiv_id":"2411.00683","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/taxabind-a-unified-embedding-space-for#ran","syntology_url":"https://syntology.ai/paper/2411.00683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00683"}},"official":{"repos":["mvrl/taxabind"],"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"]}}},{"url":"/paper/nearest-neighbor-normalization-improves","slug":"nearest-neighbor-normalization-improves","title":"Nearest Neighbor Normalization Improves Multimodal Retrieval","date":"2024-10-31","arxiv_id":"2410.24114","repositories_listed":1,"syntology":null},{"url":"/paper/towards-cross-modal-text-molecule-retrieval","slug":"towards-cross-modal-text-molecule-retrieval","title":"Towards Cross-Modal Text-Molecule Retrieval with Better Modality Alignment","date":"2024-10-31","arxiv_id":"2410.23715","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-vision-language-pre-training-for","slug":"multilingual-vision-language-pre-training-for","title":"Multilingual Vision-Language Pre-training for the Remote Sensing Domain","date":"2024-10-30","arxiv_id":"2410.23370","repositories_listed":1,"syntology":null},{"url":"/paper/deep-class-guided-hashing-for-multi-label","slug":"deep-class-guided-hashing-for-multi-label","title":"Deep Class-guided Hashing for Multi-label Cross-modal Retrieval","date":"2024-10-20","arxiv_id":"2410.15387","repositories_listed":1,"syntology":null},{"url":"/paper/badcm-invisible-backdoor-attack-against-cross","slug":"badcm-invisible-backdoor-attack-against-cross","title":"BadCM: Invisible Backdoor Attack Against Cross-Modal Learning","date":"2024-10-03","arxiv_id":"2410.02182","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-llm-enhanced-cross-lingual-cross","slug":"multimodal-llm-enhanced-cross-lingual-cross","title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval","date":"2024-09-30","arxiv_id":"2409.19961","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"9 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multimodal-llm-enhanced-cross-lingual-cross#ran","syntology_url":"https://syntology.ai/paper/2409.19961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19961"}},"official":{"repos":["lijiabei-7/leccr"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/eyeclip-a-visual-language-foundation-model","slug":"eyeclip-a-visual-language-foundation-model","title":"EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis","date":"2024-09-10","arxiv_id":"2409.06644","repositories_listed":1,"syntology":null},{"url":"/paper/alt-moe-multimodal-alignment-via-alternating","slug":"alt-moe-multimodal-alignment-via-alternating","title":"M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework","date":"2024-09-09","arxiv_id":"2409.05929","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alt-moe-multimodal-alignment-via-alternating#ran","syntology_url":"https://syntology.ai/paper/2409.05929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05929"}},"official":{"repos":["HongyangLL/M3-JEPA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dac-2d-3d-retrieval-with-noisy-labels-via","slug":"dac-2d-3d-retrieval-with-noisy-labels-via","title":"DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correction","date":"2024-07-25","arxiv_id":"2407.17779","repositories_listed":1,"syntology":null},{"url":"/paper/unified-lexical-representation-for","slug":"unified-lexical-representation-for","title":"Unified Lexical Representation for Interpretable Visual-Language Alignment","date":"2024-07-25","arxiv_id":"2407.17827","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-sight-and-sound-advanced-sound","slug":"aligning-sight-and-sound-advanced-sound","title":"Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment","date":"2024-07-18","arxiv_id":"2407.13676","repositories_listed":1,"syntology":null},{"url":"/paper/modalchorus-visual-probing-and-alignment-of","slug":"modalchorus-visual-probing-and-alignment-of","title":"ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map","date":"2024-07-17","arxiv_id":"2407.12315","repositories_listed":1,"syntology":null},{"url":"/paper/ugncl-uncertainty-guided-noisy-correspondence","slug":"ugncl-uncertainty-guided-noisy-correspondence","title":"UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching","date":"2024-07-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-consistency-in-cross-lingual","slug":"improving-the-consistency-in-cross-lingual","title":"Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning","date":"2024-06-26","arxiv_id":"2406.18254","repositories_listed":1,"syntology":null},{"url":"/paper/deep-sketched-output-kernel-regression-for","slug":"deep-sketched-output-kernel-regression-for","title":"Deep Sketched Output Kernel Regression for Structured Prediction","date":"2024-06-13","arxiv_id":"2406.09253","repositories_listed":1,"syntology":null},{"url":"/paper/separating-the-chirp-from-the-chat-self","slug":"separating-the-chirp-from-the-chat-self","title":"Separating the \"Chirp\" from the \"Chat\": Self-supervised Visual Grounding of Sound and Language","date":"2024-06-09","arxiv_id":"2406.05629","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 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) · 1 unverified","sample_list":"/paper/separating-the-chirp-from-the-chat-self#ran","syntology_url":"https://syntology.ai/paper/2406.05629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05629"}},"official":{"repos":["mhamilton723/DenseAV"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cala-complementary-association-learning-for","slug":"cala-complementary-association-learning-for","title":"CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval","date":"2024-05-29","arxiv_id":"2405.19149","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-remote-sensing-with-harmonized","slug":"efficient-remote-sensing-with-harmonized","title":"Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment","date":"2024-04-28","arxiv_id":"2404.18253","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/efficient-remote-sensing-with-harmonized#ran","syntology_url":"https://syntology.ai/paper/2404.18253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18253"}},"official":{"repos":["seekerhuang/harma"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/3shnet-boosting-image-sentence-retrieval-via","slug":"3shnet-boosting-image-sentence-retrieval-via","title":"3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting","date":"2024-04-26","arxiv_id":"2404.17273","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/3shnet-boosting-image-sentence-retrieval-via#ran","syntology_url":"https://syntology.ai/paper/2404.17273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.17273"}},"official":{"repos":["xurige1995/3shnet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-self-adaptive-multiscale-distillation","slug":"dynamic-self-adaptive-multiscale-distillation","title":"Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning","date":"2024-04-16","arxiv_id":"2404.10838","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-vision-and-language-spaces-with","slug":"bridging-vision-and-language-spaces-with","title":"Bridging Vision and Language Spaces with Assignment Prediction","date":"2024-04-15","arxiv_id":"2404.09632","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/bridging-vision-and-language-spaces-with#ran","syntology_url":"https://syntology.ai/paper/2404.09632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09632"}},"official":{"repos":["park-jungin/vlap"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-enhanced-visual-language","slug":"knowledge-enhanced-visual-language","title":"Knowledge-enhanced Visual-Language Pretraining for Computational Pathology","date":"2024-04-15","arxiv_id":"2404.09942","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-retrieval-with-noisy","slug":"cross-modal-retrieval-with-noisy","title":"Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining","date":"2024-03-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vxp-voxel-cross-pixel-large-scale-image-lidar","slug":"vxp-voxel-cross-pixel-large-scale-image-lidar","title":"VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognition","date":"2024-03-21","arxiv_id":"2403.14594","repositories_listed":1,"syntology":null},{"url":"/paper/improving-medical-multi-modal-contrastive","slug":"improving-medical-multi-modal-contrastive","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","date":"2024-03-15","arxiv_id":"2403.10153","repositories_listed":1,"syntology":{"n":12,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"5 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; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/improving-medical-multi-modal-contrastive#ran","syntology_url":"https://syntology.ai/paper/2403.10153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10153"}},"official":{"repos":["ykumards/eclip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/training-small-multimodal-models-to-bridge","slug":"training-small-multimodal-models-to-bridge","title":"Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation","date":"2024-03-12","arxiv_id":"2403.08002","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/training-small-multimodal-models-to-bridge#ran","syntology_url":"https://syntology.ai/paper/2403.08002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08002"}},"official":{"repos":["microsoft/llava-rad"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-rematch-mismatched-pairs-for","slug":"learning-to-rematch-mismatched-pairs-for","title":"Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval","date":"2024-03-08","arxiv_id":"2403.05105","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":6,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-to-rematch-mismatched-pairs-for#ran","syntology_url":"https://syntology.ai/paper/2403.05105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05105"}},"official":{"repos":["hhc1997/l2rm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-are-in-context-molecule","slug":"large-language-models-are-in-context-molecule","title":"Large Language Models are In-Context Molecule Learners","date":"2024-03-07","arxiv_id":"2403.04197","repositories_listed":1,"syntology":null},{"url":"/paper/impression-clip-contrastive-shape-impression","slug":"impression-clip-contrastive-shape-impression","title":"Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts","date":"2024-02-26","arxiv_id":"2402.16350","repositories_listed":1,"syntology":null},{"url":"/paper/distinctive-image-captioning-leveraging","slug":"distinctive-image-captioning-leveraging","title":"Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement Learning","date":"2024-02-21","arxiv_id":"2402.13936","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-sketch-based-remote-sensing-image","slug":"zero-shot-sketch-based-remote-sensing-image","title":"Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization","date":"2024-02-03","arxiv_id":"2402.02141","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-retrieval-for-knowledge-based","slug":"cross-modal-retrieval-for-knowledge-based","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","date":"2024-01-11","arxiv_id":"2401.05736","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"phrase":"4 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; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/cross-modal-retrieval-for-knowledge-based#ran","syntology_url":"https://syntology.ai/paper/2401.05736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05736"}},"official":{"repos":["paullerner/viquae"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/linguistic-aware-patch-slimming-framework-for","slug":"linguistic-aware-patch-slimming-framework-for","title":"Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/skyscript-a-large-and-semantically-diverse","slug":"skyscript-a-large-and-semantically-diverse","title":"SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing","date":"2023-12-20","arxiv_id":"2312.12856","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/skyscript-a-large-and-semantically-diverse#ran","syntology_url":"https://syntology.ai/paper/2312.12856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12856"}},"official":{"repos":["wangzhecheng/skyscript"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}],"syntology_records":37,"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":1,"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/cross-modal-retrieval-on-flickr30k","since_archive":"/sota/cross-modal-retrieval-on-flickr30k#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":70,"papers_where_code_ran_first_page":"/task/cross-modal-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":6,"url":"/task/cross-modal-retrieval/papers/2","json":"/task/cross-modal-retrieval/papers/2.json","rows":100},{"order":"archive","page":3,"of":6,"url":"/task/cross-modal-retrieval/papers/3","json":"/task/cross-modal-retrieval/papers/3.json","rows":100},{"order":"archive","page":4,"of":6,"url":"/task/cross-modal-retrieval/papers/4","json":"/task/cross-modal-retrieval/papers/4.json","rows":100},{"order":"archive","page":5,"of":6,"url":"/task/cross-modal-retrieval/papers/5","json":"/task/cross-modal-retrieval/papers/5.json","rows":100},{"order":"archive","page":6,"of":6,"url":"/task/cross-modal-retrieval/papers/6","json":"/task/cross-modal-retrieval/papers/6.json","rows":22},{"order":"ran","page":1,"of":1,"url":"/task/cross-modal-retrieval/papers/ran/1","json":"/task/cross-modal-retrieval/papers/ran/1.json","rows":70}],"description_links":{"kept":0,"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":"954c5d9c6dc3ee33732ed733847b825ca6d129dc0d46c838bb9dc7f99f6c41d3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}