{"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":"/dataset/flickr30k","name":"Flickr30k","full_name":"Flickr30k","description_markdown":"The **Flickr30k** dataset contains 31,000 images collected from Flickr, together with 5 reference sentences provided by human annotators.\r\n\r\nSource: [Guiding Long-Short Term Memory for Image Caption Generation](https://arxiv.org/abs/1509.04942)\r\n\r\nImage Source: [Dual-Path Convolutional Image-Text Embedding with Instance Loss\r\n](https://arxiv.org/abs/1711.05535)","description_withheld":null,"homepage":"https://shannon.cs.illinois.edu/DenotationGraph/","introduced_date":"2014-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/from-image-descriptions-to-visual-denotations","title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","first_author":"Peter Young","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"https://shannon.cs.illinois.edu/DenotationGraph/#:~:text=Downloads"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Node Classification","url":"/task/node-classification","datasets_with_task":"/datasets/task/node-classification"},{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Cross-Modal Retrieval","url":"/task/cross-modal-retrieval","datasets_with_task":"/datasets/task/cross-modal-retrieval"},{"name":"Image-to-Text Retrieval","url":"/task/image-to-text-retrieval","datasets_with_task":"/datasets/task/image-to-text-retrieval"},{"name":"Phrase Grounding","url":"/task/phrase-grounding","datasets_with_task":"/datasets/task/phrase-grounding"},{"name":"Zero-shot Text-to-Image Retrieval","url":"/task/zero-shot-text-to-image-retrieval","datasets_with_task":"/datasets/task/zero-shot-text-to-image-retrieval"},{"name":"Zero-Shot Cross-Modal Retrieval","url":"/task/zero-shot-cross-modal-retrieval","datasets_with_task":"/datasets/task/zero-shot-cross-modal-retrieval"},{"name":"Semi Supervised Learning for Image Captioning","url":"/task/semi-supervised-learning-for-image-captioning","datasets_with_task":"/datasets/task/semi-supervised-learning-for-image-captioning"},{"name":"mage-to-Text Retrieval","url":"/task/mage-to-text-retrieval","datasets_with_task":"/datasets/task/mage-to-text-retrieval"},{"name":"Video Description","url":"/task/video-description","datasets_with_task":"/datasets/task/video-description"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Flickr30k","Flickr","Flickr30k Captions test","Flickr30K 1K test"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.Flickr30k.html","frameworks":["pytorch"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#flickr30k","frameworks":["pytorch"]},{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/flickr30k-dataset","frameworks":["tf","pytorch"]}],"num_papers_in_archive":880,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-modal-retrieval-on-flickr30k","task":"Cross-Modal Retrieval","dataset_variant":"Flickr30k","rows":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":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","metrics":{"Image-to-text R@1":"98.8","Image-to-text R@10":"100","Image-to-text R@5":"100","Text-to-image R@1":"91.8","Text-to-image R@10":"99.5","Text-to-image R@5":"98.6"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-flickr30k","task":"Zero-Shot Cross-Modal Retrieval","dataset_variant":"Flickr30k","rows":22,"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":"InternVL-G","paper":"/paper/internvl-scaling-up-vision-foundation-models","metrics":{"Image-to-text R@1":"95.7","Image-to-text R@10":"99.9","Image-to-text R@5":"99.7","Text-to-image R@1":"85.0","Text-to-image R@10":"98.6","Text-to-image R@5":"97.0"},"code_links":[{"title":"opengvlab/internvl","url":"https://github.com/opengvlab/internvl"},{"title":"opengvlab/internvl-mmdetseg","url":"https://github.com/opengvlab/internvl-mmdetseg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-retrieval-on-flickr30k-1k-test","task":"Image Retrieval","dataset_variant":"Flickr30K 1K test","rows":18,"metrics":["R@1","R@5","R@10"],"first_row_in_archive_order":{"model":"X-VLM (base)","paper":"/paper/multi-grained-vision-language-pre-training","metrics":{"R@1":"86.9","R@10":"98.7","R@5":"97.3"},"code_links":[{"title":"zengyan-97/x-vlm","url":"https://github.com/zengyan-97/x-vlm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset_variant":"Flickr30k","rows":11,"metrics":["Recall@1","Recall@5","Recall@10","Recall@Sum"],"first_row_in_archive_order":{"model":"InternVL-G-FT (finetuned, w/o ranking)","paper":"/paper/internvl-scaling-up-vision-foundation-models","metrics":{"Recall@1":"97.9","Recall@10":"100","Recall@5":"100"},"code_links":[{"title":"opengvlab/internvl","url":"https://github.com/opengvlab/internvl"},{"title":"opengvlab/internvl-mmdetseg","url":"https://github.com/opengvlab/internvl-mmdetseg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-retrieval-on-flickr30k","task":"Image Retrieval","dataset_variant":"Flickr30k","rows":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":"/paper/blip-2-bootstrapping-language-image-pre","metrics":{"Recall@1":"89.7","Recall@10":"98.9","Recall@5":"98.1"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/node-classification-on-flickr","task":"Node Classification","dataset_variant":"Flickr","rows":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GCN+GAugM (Zhao et al., 2021)","paper":"/paper/data-augmentation-for-graph-neural-networks","metrics":{"Accuracy":"0.682"},"code_links":[{"title":"zhao-tong/GAug","url":"https://github.com/zhao-tong/GAug"},{"title":"andyjzhao/wsdm23-gsr","url":"https://github.com/andyjzhao/wsdm23-gsr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-flickr30k-captions-test","task":"Image Captioning","dataset_variant":"Flickr30k Captions test","rows":7,"metrics":["BLEU-4","CIDEr","METEOR","SPICE"],"first_row_in_archive_order":{"model":"Unified VLP","paper":"/paper/unified-vision-language-pre-training-for","metrics":{"BLEU-4":"30.1","CIDEr":"67.4","METEOR":"23","SPICE":"17"},"code_links":[{"title":"rmokady/clip_prefix_caption","url":"https://github.com/rmokady/clip_prefix_caption"},{"title":"LuoweiZhou/VLP","url":"https://github.com/LuoweiZhou/VLP"},{"title":"WebQnA/WebQA_Baseline","url":"https://github.com/WebQnA/WebQA_Baseline"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/phrase-grounding-on-flickr30k","task":"Phrase Grounding","dataset_variant":"Flickr30k","rows":3,"metrics":["Pointing Game Accuracy"],"first_row_in_archive_order":{"model":"GBS Ensemble + 12-in-1","paper":"/paper/detector-free-weakly-supervised-grounding-by","metrics":{"Pointing Game Accuracy":"85.9"},"code_links":[{"title":"aarbelle/GroundingBySeparation","url":"https://github.com/aarbelle/GroundingBySeparation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-learning-for-image-captioning-2","task":"Semi Supervised Learning for Image Captioning","dataset_variant":"Flickr30k","rows":1,"metrics":["CIDEr"],"first_row_in_archive_order":{"model":"CapDec","paper":"/paper/text-only-training-for-image-captioning-using","metrics":{"CIDEr":"39.1"},"code_links":[{"title":"davidhuji/capdec","url":"https://github.com/davidhuji/capdec"},{"title":"zelaki/wsac","url":"https://github.com/zelaki/wsac"},{"title":"avitej-iyer/CapDec-Recreation","url":"https://github.com/avitej-iyer/CapDec-Recreation"},{"title":"uriberger/re_cap","url":"https://github.com/uriberger/re_cap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":69,"of":69,"counts":{"papers_with_a_benchmark_row":69,"with_a_code_link":62,"where_syntology_ran_a_sample":36,"not_listed_spam_title":0,"listed":69,"listed_where_code_ran":36,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":28,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":28,"listed_every_run_a_failure_of_syntologys_instrument":8,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/cosmos-cross-modality-self-distillation-for","slug":"cosmos-cross-modality-self-distillation-for","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","date":"2024-12-02","arxiv_id":"2412.01814","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boldsymbol-m-2-encoder-advancing-bilingual","slug":"boldsymbol-m-2-encoder-advancing-bilingual","title":"M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining","date":"2024-01-29","arxiv_id":"2401.15896","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/implicit-differentiable-outlier-detection","slug":"implicit-differentiable-outlier-detection","title":"Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-09-21","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"samples_unverified":7,"pointer_only_for_licence":8,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}}}},{"paper":"/paper/region-aware-pretraining-for-open-vocabulary","slug":"region-aware-pretraining-for-open-vocabulary","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","date":"2023-05-11","arxiv_id":"2305.07011","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["mcahny/rovit","google-research/google-research"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/region-aware-pretraining-for-open-vocabulary#ran","syntology_url":"https://syntology.ai/paper/2305.07011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07011"}}}},{"paper":"/paper/mammut-a-simple-architecture-for-joint","slug":"mammut-a-simple-architecture-for-joint","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","date":"2023-03-29","arxiv_id":"2303.16839","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mammut-a-simple-architecture-for-joint#ran","syntology_url":"https://syntology.ai/paper/2303.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16839"}}}},{"paper":"/paper/plug-and-play-regulators-for-image-text","slug":"plug-and-play-regulators-for-image-text","title":"Plug-and-Play Regulators for Image-Text Matching","date":"2023-03-23","arxiv_id":"2303.13371","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":4,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/napreg-nouns-as-proxies-regularization-for","slug":"napreg-nouns-as-proxies-regularization-for","title":"NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings","date":"2023-01-07","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/position-guided-text-prompt-for-vision","slug":"position-guided-text-prompt-for-vision","title":"Position-guided Text Prompt for Vision-Language Pre-training","date":"2022-12-19","arxiv_id":"2212.09737","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["sail-sg/ptp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/position-guided-text-prompt-for-vision#ran","syntology_url":"https://syntology.ai/paper/2212.09737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09737"}}}},{"paper":"/paper/reproducible-scaling-laws-for-contrastive","slug":"reproducible-scaling-laws-for-contrastive","title":"Reproducible scaling laws for contrastive language-image learning","date":"2022-12-14","arxiv_id":"2212.07143","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["laion-ai/scaling-laws-openclip"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/reproducible-scaling-laws-for-contrastive#ran","syntology_url":"https://syntology.ai/paper/2212.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07143"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":6,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["davidhuji/capdec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/text-only-training-for-image-captioning-using#ran","syntology_url":"https://syntology.ai/paper/2211.00575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00575"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/a-comprehensive-study-on-large-scale-graph","slug":"a-comprehensive-study-on-large-scale-graph","title":"A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking","date":"2022-10-14","arxiv_id":"2210.07494","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["vita-group/large_scale_gcn_benchmarking"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-comprehensive-study-on-large-scale-graph#ran","syntology_url":"https://syntology.ai/paper/2210.07494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07494"}}}},{"paper":"/paper/ernie-vil-2-0-multi-view-contrastive-learning","slug":"ernie-vil-2-0-multi-view-contrastive-learning","title":"ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training","date":"2022-09-30","arxiv_id":"2209.15270","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/omnivl-one-foundation-model-for-image","slug":"omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","arxiv_id":"2209.07526","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/language-models-are-general-purpose","slug":"language-models-are-general-purpose","title":"Language Models are General-Purpose Interfaces","date":"2022-06-13","arxiv_id":"2206.06336","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"paper":"/paper/flamingo-a-visual-language-model-for-few-shot-1","slug":"flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":18,"samples_constructed":6,"samples_ran_checked":11,"samples_ran_instrument_failed":7,"samples_unverified":6,"pointer_only_for_licence":8,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/flamingo-a-visual-language-model-for-few-shot-1#ran","syntology_url":"https://syntology.ai/paper/2204.14198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14198"}}}},{"paper":"/paper/vista-vision-and-scene-text-aggregation-for","slug":"vista-vision-and-scene-text-aggregation-for","title":"ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval","date":"2022-03-31","arxiv_id":"2203.16778","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/multi-grained-vision-language-pre-training","slug":"multi-grained-vision-language-pre-training","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","date":"2021-11-16","arxiv_id":"2111.08276","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/a-good-prompt-is-worth-millions-of-parameters","slug":"a-good-prompt-is-worth-millions-of-parameters","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","date":"2021-10-16","arxiv_id":"2110.08484","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/a-deep-local-and-global-scene-graph-matching","slug":"a-deep-local-and-global-scene-graph-matching","title":"A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval","date":"2021-06-04","arxiv_id":"2106.02400","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/learning-relation-alignment-for-calibrated","slug":"learning-relation-alignment-for-calibrated","title":"Learning Relation Alignment for Calibrated Cross-modal Retrieval","date":"2021-05-28","arxiv_id":"2105.13868","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["lancopku/IAIS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-relation-alignment-for-calibrated#ran","syntology_url":"https://syntology.ai/paper/2105.13868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13868"}}}},{"paper":"/paper/detector-free-weakly-supervised-grounding-by","slug":"detector-free-weakly-supervised-grounding-by","title":"Detector-Free Weakly Supervised Grounding by Separation","date":"2021-04-20","arxiv_id":"2104.09829","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","rows_on_this_dataset":1,"code_links":82,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":14,"samples_unverified":4,"pointer_only_for_licence":16,"official":{"repos":["openai/CLIP"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":6,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":9,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":10,"pointer_only_for_licence":0,"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}}}},{"paper":"/paper/similarity-reasoning-and-filtration-for-image","slug":"similarity-reasoning-and-filtration-for-image","title":"Similarity Reasoning and Filtration for Image-Text Matching","date":"2021-01-05","arxiv_id":"2101.01368","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":12,"official":{"repos":["Paranioar/SGRAF"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/similarity-reasoning-and-filtration-for-image#ran","syntology_url":"https://syntology.ai/paper/2101.01368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.01368"}}}},{"paper":"/paper/visualsparta-sparse-transformer-fragment","slug":"visualsparta-sparse-transformer-fragment","title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","date":"2021-01-01","arxiv_id":"2101.00265","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/fine-grained-visual-textual-alignment-for","slug":"fine-grained-visual-textual-alignment-for","title":"Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders","date":"2020-08-12","arxiv_id":"2008.05231","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["mesnico/TERAN"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fine-grained-visual-textual-alignment-for#ran","syntology_url":"https://syntology.ai/paper/2008.05231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.05231"}}}},{"paper":"/paper/data-augmentation-for-graph-neural-networks","slug":"data-augmentation-for-graph-neural-networks","title":"Data Augmentation for Graph Neural Networks","date":"2020-06-11","arxiv_id":"2006.06830","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["zhao-tong/GAug"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/data-augmentation-for-graph-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2006.06830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06830"}}}},{"paper":"/paper/graph-structured-network-for-image-text","slug":"graph-structured-network-for-image-text","title":"Graph Structured Network for Image-Text Matching","date":"2020-04-01","arxiv_id":"2004.00277","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/imram-iterative-matching-with-recurrent","slug":"imram-iterative-matching-with-recurrent","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","date":"2020-03-08","arxiv_id":"2003.03772","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["HuiChen24/IMRAM"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/imram-iterative-matching-with-recurrent#ran","syntology_url":"https://syntology.ai/paper/2003.03772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.03772"}}}},{"paper":"/paper/imagebert-cross-modal-pre-training-with-large","slug":"imagebert-cross-modal-pre-training-with-large","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","date":"2020-01-22","arxiv_id":"2001.07966","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["ChenRocks/UNITER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}}}},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":14,"official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-vision-language-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}}}},{"paper":"/paper/camp-cross-modal-adaptive-message-passing-for","slug":"camp-cross-modal-adaptive-message-passing-for","title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval","date":"2019-09-12","arxiv_id":"1909.05506","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["ZihaoWang-CV/CAMP_iccv19"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/camp-cross-modal-adaptive-message-passing-for#ran","syntology_url":"https://syntology.ai/paper/1909.05506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05506"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/demo-net-degree-specific-graph-neural","slug":"demo-net-degree-specific-graph-neural","title":"DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification","date":"2019-06-05","arxiv_id":"1906.02319","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-level-multimodal-common-semantic-space","slug":"multi-level-multimodal-common-semantic-space","title":"Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding","date":"2018-11-28","arxiv_id":"1811.11683","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-cross-modal-projection-learning-for","slug":"deep-cross-modal-projection-learning-for","title":"Deep Cross-Modal Projection Learning for Image-Text Matching","date":"2018-09-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":6,"samples_unverified":3,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/deeper-insights-into-graph-convolutional","slug":"deeper-insights-into-graph-convolutional","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","date":"2018-01-22","arxiv_id":"1801.07606","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-semantic-concepts-and-order-for","slug":"learning-semantic-concepts-and-order-for","title":"Learning Semantic Concepts and Order for Image and Sentence Matching","date":"2017-12-06","arxiv_id":"1712.02036","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/graph-attention-networks","slug":"graph-attention-networks","title":"Graph Attention Networks","date":"2017-10-30","arxiv_id":"1710.10903","rows_on_this_dataset":1,"code_links":93,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":106,"samples_ran":61,"samples_constructed":28,"samples_ran_checked":52,"samples_ran_instrument_failed":9,"samples_unverified":45,"pointer_only_for_licence":46,"official":{"repos":["PetarV-/GAT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/graph-attention-networks#ran","syntology_url":"https://syntology.ai/paper/1710.10903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10903"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/paying-more-attention-to-saliency-image","slug":"paying-more-attention-to-saliency-image","title":"Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention","date":"2017-06-26","arxiv_id":"1706.08474","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/inductive-representation-learning-on-large","slug":"inductive-representation-learning-on-large","title":"Inductive Representation Learning on Large Graphs","date":"2017-06-07","arxiv_id":"1706.02216","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":5,"official":{"repos":["williamleif/GraphSAGE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/inductive-representation-learning-on-large#ran","syntology_url":"https://syntology.ai/paper/1706.02216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02216"}}}},{"paper":"/paper/instance-aware-image-and-sentence-matching","slug":"instance-aware-image-and-sentence-matching","title":"Instance-aware Image and Sentence Matching with Selective Multimodal LSTM","date":"2016-11-17","arxiv_id":"1611.05588","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dual-attention-networks-for-multimodal","slug":"dual-attention-networks-for-multimodal","title":"Dual Attention Networks for Multimodal Reasoning and Matching","date":"2016-11-02","arxiv_id":"1611.00471","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/semi-supervised-classification-with-graph","slug":"semi-supervised-classification-with-graph","title":"Semi-Supervised Classification with Graph Convolutional Networks","date":"2016-09-09","arxiv_id":"1609.02907","rows_on_this_dataset":2,"code_links":55,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":39,"samples_constructed":13,"samples_ran_checked":34,"samples_ran_instrument_failed":5,"samples_unverified":19,"pointer_only_for_licence":23,"official":{"repos":["tkipf/pygcn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/semi-supervised-classification-with-graph#ran","syntology_url":"https://syntology.ai/paper/1609.02907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.02907"}}}},{"paper":"/paper/linking-image-and-text-with-2-way-nets","slug":"linking-image-and-text-with-2-way-nets","title":"Linking Image and Text with 2-Way Nets","date":"2016-08-29","arxiv_id":"1608.07973","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-deep-structure-preserving-image-text","slug":"learning-deep-structure-preserving-image-text","title":"Learning Deep Structure-Preserving Image-Text Embeddings","date":"2015-11-19","arxiv_id":"1511.06078","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/flickr30k-entities-collecting-region-to","slug":"flickr30k-entities-collecting-region-to","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","date":"2015-05-19","arxiv_id":"1505.04870","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/flickr30k-entities-collecting-region-to#ran","syntology_url":"https://syntology.ai/paper/1505.04870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.04870"}}}},{"paper":"/paper/multimodal-convolutional-neural-networks-for","slug":"multimodal-convolutional-neural-networks-for","title":"Multimodal Convolutional Neural Networks for Matching Image and Sentence","date":"2015-04-23","arxiv_id":"1504.06063","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/cosmos-cross-modality-self-distillation-for","slug":"cosmos-cross-modality-self-distillation-for","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","date":"2024-12-02","arxiv_id":"2412.01814","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boldsymbol-m-2-encoder-advancing-bilingual","slug":"boldsymbol-m-2-encoder-advancing-bilingual","title":"M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining","date":"2024-01-29","arxiv_id":"2401.15896","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/implicit-differentiable-outlier-detection","slug":"implicit-differentiable-outlier-detection","title":"Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-09-21","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"samples_unverified":7,"pointer_only_for_licence":8,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}}}},{"paper":"/paper/region-aware-pretraining-for-open-vocabulary","slug":"region-aware-pretraining-for-open-vocabulary","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","date":"2023-05-11","arxiv_id":"2305.07011","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["mcahny/rovit","google-research/google-research"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/region-aware-pretraining-for-open-vocabulary#ran","syntology_url":"https://syntology.ai/paper/2305.07011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07011"}}}},{"paper":"/paper/mammut-a-simple-architecture-for-joint","slug":"mammut-a-simple-architecture-for-joint","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","date":"2023-03-29","arxiv_id":"2303.16839","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mammut-a-simple-architecture-for-joint#ran","syntology_url":"https://syntology.ai/paper/2303.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16839"}}}},{"paper":"/paper/plug-and-play-regulators-for-image-text","slug":"plug-and-play-regulators-for-image-text","title":"Plug-and-Play Regulators for Image-Text Matching","date":"2023-03-23","arxiv_id":"2303.13371","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":4,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/napreg-nouns-as-proxies-regularization-for","slug":"napreg-nouns-as-proxies-regularization-for","title":"NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings","date":"2023-01-07","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/position-guided-text-prompt-for-vision","slug":"position-guided-text-prompt-for-vision","title":"Position-guided Text Prompt for Vision-Language Pre-training","date":"2022-12-19","arxiv_id":"2212.09737","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["sail-sg/ptp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/position-guided-text-prompt-for-vision#ran","syntology_url":"https://syntology.ai/paper/2212.09737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09737"}}}},{"paper":"/paper/reproducible-scaling-laws-for-contrastive","slug":"reproducible-scaling-laws-for-contrastive","title":"Reproducible scaling laws for contrastive language-image learning","date":"2022-12-14","arxiv_id":"2212.07143","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["laion-ai/scaling-laws-openclip"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/reproducible-scaling-laws-for-contrastive#ran","syntology_url":"https://syntology.ai/paper/2212.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07143"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":6,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["davidhuji/capdec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/text-only-training-for-image-captioning-using#ran","syntology_url":"https://syntology.ai/paper/2211.00575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00575"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/a-comprehensive-study-on-large-scale-graph","slug":"a-comprehensive-study-on-large-scale-graph","title":"A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking","date":"2022-10-14","arxiv_id":"2210.07494","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["vita-group/large_scale_gcn_benchmarking"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-comprehensive-study-on-large-scale-graph#ran","syntology_url":"https://syntology.ai/paper/2210.07494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07494"}}}},{"paper":"/paper/ernie-vil-2-0-multi-view-contrastive-learning","slug":"ernie-vil-2-0-multi-view-contrastive-learning","title":"ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training","date":"2022-09-30","arxiv_id":"2209.15270","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/omnivl-one-foundation-model-for-image","slug":"omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","arxiv_id":"2209.07526","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/language-models-are-general-purpose","slug":"language-models-are-general-purpose","title":"Language Models are General-Purpose Interfaces","date":"2022-06-13","arxiv_id":"2206.06336","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"paper":"/paper/flamingo-a-visual-language-model-for-few-shot-1","slug":"flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":18,"samples_constructed":6,"samples_ran_checked":11,"samples_ran_instrument_failed":7,"samples_unverified":6,"pointer_only_for_licence":8,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/flamingo-a-visual-language-model-for-few-shot-1#ran","syntology_url":"https://syntology.ai/paper/2204.14198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14198"}}}},{"paper":"/paper/vista-vision-and-scene-text-aggregation-for","slug":"vista-vision-and-scene-text-aggregation-for","title":"ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval","date":"2022-03-31","arxiv_id":"2203.16778","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/multi-grained-vision-language-pre-training","slug":"multi-grained-vision-language-pre-training","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","date":"2021-11-16","arxiv_id":"2111.08276","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/a-good-prompt-is-worth-millions-of-parameters","slug":"a-good-prompt-is-worth-millions-of-parameters","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","date":"2021-10-16","arxiv_id":"2110.08484","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/a-deep-local-and-global-scene-graph-matching","slug":"a-deep-local-and-global-scene-graph-matching","title":"A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval","date":"2021-06-04","arxiv_id":"2106.02400","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/learning-relation-alignment-for-calibrated","slug":"learning-relation-alignment-for-calibrated","title":"Learning Relation Alignment for Calibrated Cross-modal Retrieval","date":"2021-05-28","arxiv_id":"2105.13868","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["lancopku/IAIS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-relation-alignment-for-calibrated#ran","syntology_url":"https://syntology.ai/paper/2105.13868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13868"}}}},{"paper":"/paper/detector-free-weakly-supervised-grounding-by","slug":"detector-free-weakly-supervised-grounding-by","title":"Detector-Free Weakly Supervised Grounding by Separation","date":"2021-04-20","arxiv_id":"2104.09829","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","rows_on_this_dataset":1,"code_links":82,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":14,"samples_unverified":4,"pointer_only_for_licence":16,"official":{"repos":["openai/CLIP"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":6,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":9,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":10,"pointer_only_for_licence":0,"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}}}},{"paper":"/paper/similarity-reasoning-and-filtration-for-image","slug":"similarity-reasoning-and-filtration-for-image","title":"Similarity Reasoning and Filtration for Image-Text Matching","date":"2021-01-05","arxiv_id":"2101.01368","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":12,"official":{"repos":["Paranioar/SGRAF"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/similarity-reasoning-and-filtration-for-image#ran","syntology_url":"https://syntology.ai/paper/2101.01368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.01368"}}}},{"paper":"/paper/visualsparta-sparse-transformer-fragment","slug":"visualsparta-sparse-transformer-fragment","title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","date":"2021-01-01","arxiv_id":"2101.00265","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/fine-grained-visual-textual-alignment-for","slug":"fine-grained-visual-textual-alignment-for","title":"Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders","date":"2020-08-12","arxiv_id":"2008.05231","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["mesnico/TERAN"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fine-grained-visual-textual-alignment-for#ran","syntology_url":"https://syntology.ai/paper/2008.05231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.05231"}}}},{"paper":"/paper/data-augmentation-for-graph-neural-networks","slug":"data-augmentation-for-graph-neural-networks","title":"Data Augmentation for Graph Neural Networks","date":"2020-06-11","arxiv_id":"2006.06830","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["zhao-tong/GAug"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/data-augmentation-for-graph-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2006.06830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06830"}}}},{"paper":"/paper/graph-structured-network-for-image-text","slug":"graph-structured-network-for-image-text","title":"Graph Structured Network for Image-Text Matching","date":"2020-04-01","arxiv_id":"2004.00277","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/imram-iterative-matching-with-recurrent","slug":"imram-iterative-matching-with-recurrent","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","date":"2020-03-08","arxiv_id":"2003.03772","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["HuiChen24/IMRAM"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/imram-iterative-matching-with-recurrent#ran","syntology_url":"https://syntology.ai/paper/2003.03772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.03772"}}}},{"paper":"/paper/imagebert-cross-modal-pre-training-with-large","slug":"imagebert-cross-modal-pre-training-with-large","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","date":"2020-01-22","arxiv_id":"2001.07966","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["ChenRocks/UNITER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}}}},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":14,"official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-vision-language-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}}}},{"paper":"/paper/camp-cross-modal-adaptive-message-passing-for","slug":"camp-cross-modal-adaptive-message-passing-for","title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval","date":"2019-09-12","arxiv_id":"1909.05506","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["ZihaoWang-CV/CAMP_iccv19"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/camp-cross-modal-adaptive-message-passing-for#ran","syntology_url":"https://syntology.ai/paper/1909.05506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05506"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/demo-net-degree-specific-graph-neural","slug":"demo-net-degree-specific-graph-neural","title":"DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification","date":"2019-06-05","arxiv_id":"1906.02319","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-level-multimodal-common-semantic-space","slug":"multi-level-multimodal-common-semantic-space","title":"Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding","date":"2018-11-28","arxiv_id":"1811.11683","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-cross-modal-projection-learning-for","slug":"deep-cross-modal-projection-learning-for","title":"Deep Cross-Modal Projection Learning for Image-Text Matching","date":"2018-09-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":6,"samples_unverified":3,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/deeper-insights-into-graph-convolutional","slug":"deeper-insights-into-graph-convolutional","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","date":"2018-01-22","arxiv_id":"1801.07606","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-semantic-concepts-and-order-for","slug":"learning-semantic-concepts-and-order-for","title":"Learning Semantic Concepts and Order for Image and Sentence Matching","date":"2017-12-06","arxiv_id":"1712.02036","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/graph-attention-networks","slug":"graph-attention-networks","title":"Graph Attention Networks","date":"2017-10-30","arxiv_id":"1710.10903","rows_on_this_dataset":1,"code_links":93,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":106,"samples_ran":61,"samples_constructed":28,"samples_ran_checked":52,"samples_ran_instrument_failed":9,"samples_unverified":45,"pointer_only_for_licence":46,"official":{"repos":["PetarV-/GAT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/graph-attention-networks#ran","syntology_url":"https://syntology.ai/paper/1710.10903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10903"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/paying-more-attention-to-saliency-image","slug":"paying-more-attention-to-saliency-image","title":"Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention","date":"2017-06-26","arxiv_id":"1706.08474","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/inductive-representation-learning-on-large","slug":"inductive-representation-learning-on-large","title":"Inductive Representation Learning on Large Graphs","date":"2017-06-07","arxiv_id":"1706.02216","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":5,"official":{"repos":["williamleif/GraphSAGE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/inductive-representation-learning-on-large#ran","syntology_url":"https://syntology.ai/paper/1706.02216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02216"}}}},{"paper":"/paper/instance-aware-image-and-sentence-matching","slug":"instance-aware-image-and-sentence-matching","title":"Instance-aware Image and Sentence Matching with Selective Multimodal LSTM","date":"2016-11-17","arxiv_id":"1611.05588","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dual-attention-networks-for-multimodal","slug":"dual-attention-networks-for-multimodal","title":"Dual Attention Networks for Multimodal Reasoning and Matching","date":"2016-11-02","arxiv_id":"1611.00471","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/semi-supervised-classification-with-graph","slug":"semi-supervised-classification-with-graph","title":"Semi-Supervised Classification with Graph Convolutional Networks","date":"2016-09-09","arxiv_id":"1609.02907","rows_on_this_dataset":2,"code_links":55,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":39,"samples_constructed":13,"samples_ran_checked":34,"samples_ran_instrument_failed":5,"samples_unverified":19,"pointer_only_for_licence":23,"official":{"repos":["tkipf/pygcn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/semi-supervised-classification-with-graph#ran","syntology_url":"https://syntology.ai/paper/1609.02907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.02907"}}}},{"paper":"/paper/linking-image-and-text-with-2-way-nets","slug":"linking-image-and-text-with-2-way-nets","title":"Linking Image and Text with 2-Way Nets","date":"2016-08-29","arxiv_id":"1608.07973","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-deep-structure-preserving-image-text","slug":"learning-deep-structure-preserving-image-text","title":"Learning Deep Structure-Preserving Image-Text Embeddings","date":"2015-11-19","arxiv_id":"1511.06078","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/flickr30k-entities-collecting-region-to","slug":"flickr30k-entities-collecting-region-to","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","date":"2015-05-19","arxiv_id":"1505.04870","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/flickr30k-entities-collecting-region-to#ran","syntology_url":"https://syntology.ai/paper/1505.04870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.04870"}}}},{"paper":"/paper/multimodal-convolutional-neural-networks-for","slug":"multimodal-convolutional-neural-networks-for","title":"Multimodal Convolutional Neural Networks for Matching Image and Sentence","date":"2015-04-23","arxiv_id":"1504.06063","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"papers_where_code_ran":36,"papers_where_code_ran_first_page":"/dataset/flickr30k/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/flickr30k/papers/ran/1","json":"/dataset/flickr30k/papers/ran/1.json","rows":36}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":37,"samples_harvested":463,"samples_ran":322,"samples_constructed":88,"samples_ran_checked":228,"samples_ran_instrument_failed":94,"samples_unverified":141,"pointer_only_for_licence":182,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":36,"papers_with_a_run_with_no_instrument_failure":28,"papers_where_every_run_was_an_instrument_failure":8,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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":10,"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},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-flickr30k","since_archive":"/sota/zero-shot-cross-modal-retrieval-on-flickr30k#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","since_archive":"/sota/image-to-text-retrieval-on-flickr30k#since-judged","papers_judged":3,"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-captioning-on-flickr30k-captions-test","since_archive":"/sota/image-captioning-on-flickr30k-captions-test#since-judged","papers_judged":3,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"f9d24ced46348bae4245ff78910a78470f1e073dd4362366b8f7b0e9979800ca","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}