{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-text-matching/papers/ran/1","list_of":"/task/image-text-matching","task":"Image-text matching","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,37],"of":37,"counts":{"archive_papers_tagged":188,"with_a_code_link":102,"where_syntology_ran_a_sample":37,"not_listed_spam_title":0,"listed":188,"listed_where_code_ran":37,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":7,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/image-text-matching/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/clip-is-strong-enough-to-fight-back-test-time","slug":"clip-is-strong-enough-to-fight-back-test-time","title":"CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP","date":"2025-03-05","arxiv_id":"2503.03613","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clip-is-strong-enough-to-fight-back-test-time#ran","syntology_url":"https://syntology.ai/paper/2503.03613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.03613"}},"official":{"repos":["Sxing2/CLIP-Test-time-Counterattacks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/clip-under-the-microscope-a-fine-grained","slug":"clip-under-the-microscope-a-fine-grained","title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation","date":"2025-02-27","arxiv_id":"2502.19842","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-under-the-microscope-a-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2502.19842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19842"}},"official":{"repos":["clip-oscope/clip-oscope"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/recon-enhancing-true-correspondence-1","slug":"recon-enhancing-true-correspondence-1","title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","date":"2025-02-27","arxiv_id":"2502.19962","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/recon-enhancing-true-correspondence-1#ran","syntology_url":"https://syntology.ai/paper/2502.19962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19962"}},"official":{"repos":["qxzha/ReCon"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-and-long-tailed-generalization-for","slug":"efficient-and-long-tailed-generalization-for","title":"Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model","date":"2024-06-18","arxiv_id":"2406.12638","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficient-and-long-tailed-generalization-for#ran","syntology_url":"https://syntology.ai/paper/2406.12638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12638"}},"official":{"repos":["shijxcs/candle"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/composing-object-relations-and-attributes-for-1","slug":"composing-object-relations-and-attributes-for-1","title":"Composing Object Relations and Attributes for Image-Text Matching","date":"2024-06-17","arxiv_id":"2406.11820","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/composing-object-relations-and-attributes-for-1#ran","syntology_url":"https://syntology.ai/paper/2406.11820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11820"}},"official":{"repos":["vkhoi/cora_cvpr24"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/magid-an-automated-pipeline-for-generating","slug":"magid-an-automated-pipeline-for-generating","title":"MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets","date":"2024-03-05","arxiv_id":"2403.03194","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/magid-an-automated-pipeline-for-generating#ran","syntology_url":"https://syntology.ai/paper/2403.03194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03194"}},"official":{"repos":["amazon-science/MAGID"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/colorswap-a-color-and-word-order-dataset-for","slug":"colorswap-a-color-and-word-order-dataset-for","title":"ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation","date":"2024-02-07","arxiv_id":"2402.04492","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/colorswap-a-color-and-word-order-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2402.04492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04492"}},"official":{"repos":["top34051/colorswap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/synthesize-diagnose-and-optimize-towards-fine","slug":"synthesize-diagnose-and-optimize-towards-fine","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","date":"2023-11-30","arxiv_id":"2312.00081","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/synthesize-diagnose-and-optimize-towards-fine#ran","syntology_url":"https://syntology.ai/paper/2312.00081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00081"}},"official":{"repos":["wjpoom/spec"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/mmoe-mixture-of-multimodal-interaction","slug":"mmoe-mixture-of-multimodal-interaction","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","date":"2023-11-16","arxiv_id":"2311.09580","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mmoe-mixture-of-multimodal-interaction#ran","syntology_url":"https://syntology.ai/paper/2311.09580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09580"}},"official":{"repos":["lwaekfjlk/mmoe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-active-complementary-learning-1","slug":"cross-modal-active-complementary-learning-1","title":"Cross-modal Active Complementary Learning with Self-refining Correspondence","date":"2023-10-26","arxiv_id":"2310.17468","repositories_listed":1,"syntology":{"n":28,"n_ran":23,"n_constructed":8,"n_ran_checked":17,"n_instrument":6,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":15,"n_pointer_only":28,"phrase":"23 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 2 honoured, 0 violated, 15 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cross-modal-active-complementary-learning-1#ran","syntology_url":"https://syntology.ai/paper/2310.17468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17468"}},"official":{"repos":["qinyang79/crcl"],"state":"official (archive's flag): 22 ran","n_ran":22,"n_constructed":8,"n_ran_no_instrument_failure":17,"n_unverified":5,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/prototype-based-aleatoric-uncertainty-1","slug":"prototype-based-aleatoric-uncertainty-1","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","date":"2023-09-29","arxiv_id":"2309.17093","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":10,"n_instrument":7,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":7,"n_pointer_only":8,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prototype-based-aleatoric-uncertainty-1#ran","syntology_url":"https://syntology.ai/paper/2309.17093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17093"}},"official":{"repos":["leolee99/pau"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/your-negative-may-not-be-true-negative","slug":"your-negative-may-not-be-true-negative","title":"Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination","date":"2023-08-08","arxiv_id":"2308.04380","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/your-negative-may-not-be-true-negative#ran","syntology_url":"https://syntology.ai/paper/2308.04380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04380"}},"official":{"repos":["luminosityx/fne"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-unified-text-based-person-retrieval-a","slug":"towards-unified-text-based-person-retrieval-a","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","date":"2023-06-05","arxiv_id":"2306.02898","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/towards-unified-text-based-person-retrieval-a#ran","syntology_url":"https://syntology.ai/paper/2306.02898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02898"}},"official":{"repos":["Shuyu-XJTU/APTM"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improved-probabilistic-image-text","slug":"improved-probabilistic-image-text","title":"Improved Probabilistic Image-Text Representations","date":"2023-05-29","arxiv_id":"2305.18171","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/improved-probabilistic-image-text#ran","syntology_url":"https://syntology.ai/paper/2305.18171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18171"}},"official":{"repos":["naver-ai/pcmepp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/are-diffusion-models-vision-and-language-1","slug":"are-diffusion-models-vision-and-language-1","title":"Are Diffusion Models Vision-And-Language Reasoners?","date":"2023-05-25","arxiv_id":"2305.16397","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/are-diffusion-models-vision-and-language-1#ran","syntology_url":"https://syntology.ai/paper/2305.16397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16397"}},"official":{"repos":["mcgill-nlp/diffusion-itm"],"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":["official"]}}},{"url":"/paper/discriminative-diffusion-models-as-few-shot","slug":"discriminative-diffusion-models-as-few-shot","title":"Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners","date":"2023-05-18","arxiv_id":"2305.10722","repositories_listed":1,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/discriminative-diffusion-models-as-few-shot#ran","syntology_url":"https://syntology.ai/paper/2305.10722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10722"}},"official":{"repos":["eric-ai-lab/dsd"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/structure-clip-enhance-multi-modal-language","slug":"structure-clip-enhance-multi-modal-language","title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations","date":"2023-05-06","arxiv_id":"2305.06152","repositories_listed":3,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/structure-clip-enhance-multi-modal-language#ran","syntology_url":"https://syntology.ai/paper/2305.06152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06152"}},"official":{"repos":["zjukg/structure-clip"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/bicro-noisy-correspondence-rectification-for","slug":"bicro-noisy-correspondence-rectification-for","title":"BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency","date":"2023-03-22","arxiv_id":"2303.12419","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":5,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bicro-noisy-correspondence-rectification-for#ran","syntology_url":"https://syntology.ai/paper/2303.12419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12419"}},"official":{"repos":["xu5zhao/bicro"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-implicit-relation-reasoning-and","slug":"cross-modal-implicit-relation-reasoning-and","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","date":"2023-03-22","arxiv_id":"2303.12501","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cross-modal-implicit-relation-reasoning-and#ran","syntology_url":"https://syntology.ai/paper/2303.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12501"}},"official":{"repos":["anosorae/irra"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-vision-language-pretraining","slug":"self-supervised-vision-language-pretraining","title":"Self-supervised vision-language pretraining for Medical visual question answering","date":"2022-11-24","arxiv_id":"2211.13594","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/self-supervised-vision-language-pretraining#ran","syntology_url":"https://syntology.ai/paper/2211.13594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13594"}},"official":{"repos":["pengfeiliheu/m2i2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/grit-vlp-grouped-mini-batch-sampling-for","slug":"grit-vlp-grouped-mini-batch-sampling-for","title":"GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training","date":"2022-08-08","arxiv_id":"2208.04060","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grit-vlp-grouped-mini-batch-sampling-for#ran","syntology_url":"https://syntology.ai/paper/2208.04060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.04060"}},"official":{"repos":["jaeseokbyun/grit-vlp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/open-vocabulary-multi-label-classification","slug":"open-vocabulary-multi-label-classification","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","date":"2022-07-05","arxiv_id":"2207.01887","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/open-vocabulary-multi-label-classification#ran","syntology_url":"https://syntology.ai/paper/2207.01887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01887"}},"official":{"repos":["sunanhe/mkt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-and-r2d2-a-large-scale-chinese-cross","slug":"zero-and-r2d2-a-large-scale-chinese-cross","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","date":"2022-05-08","arxiv_id":"2205.03860","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zero-and-r2d2-a-large-scale-chinese-cross#ran","syntology_url":"https://syntology.ai/paper/2205.03860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.03860"}},"official":{"repos":["yuxie11/R2D2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/language-models-can-see-plugging-visual","slug":"language-models-can-see-plugging-visual","title":"Language Models Can See: Plugging Visual Controls in Text Generation","date":"2022-05-05","arxiv_id":"2205.02655","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-models-can-see-plugging-visual#ran","syntology_url":"https://syntology.ai/paper/2205.02655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.02655"}},"official":{"repos":["yxuansu/magic"],"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":["official"]}}},{"url":"/paper/eccv-caption-correcting-false-negatives-by","slug":"eccv-caption-correcting-false-negatives-by","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","date":"2022-04-07","arxiv_id":"2204.03359","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/eccv-caption-correcting-false-negatives-by#ran","syntology_url":"https://syntology.ai/paper/2204.03359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03359"}},"official":{"repos":["naver-ai/eccv-caption"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/align-before-fuse-vision-and-language","slug":"align-before-fuse-vision-and-language","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","date":"2021-07-16","arxiv_id":"2107.07651","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/align-before-fuse-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.07651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07651"}},"official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/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","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":6,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/vinvl-making-visual-representations-matter-in","slug":"vinvl-making-visual-representations-matter-in","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","date":"2021-01-02","arxiv_id":"2101.00529","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vinvl-making-visual-representations-matter-in#ran","syntology_url":"https://syntology.ai/paper/2101.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00529"}},"official":{"repos":["pzzhang/VinVL"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/universal-weighting-metric-learning-for-cross-1","slug":"universal-weighting-metric-learning-for-cross-1","title":"Universal Weighting Metric Learning for Cross-Modal Matching","date":"2020-10-07","arxiv_id":"2010.03403","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/universal-weighting-metric-learning-for-cross-1#ran","syntology_url":"https://syntology.ai/paper/2010.03403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03403"}},"official":{"repos":["wayne980/PolyLoss"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/transformer-reasoning-network-for-image-text","slug":"transformer-reasoning-network-for-image-text","title":"Transformer Reasoning Network for Image-Text Matching and Retrieval","date":"2020-04-20","arxiv_id":"2004.09144","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/transformer-reasoning-network-for-image-text#ran","syntology_url":"https://syntology.ai/paper/2004.09144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.09144"}},"official":{"repos":["mesnico/TERN"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/oscar-object-semantics-aligned-pre-training","slug":"oscar-object-semantics-aligned-pre-training","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","date":"2020-04-13","arxiv_id":"2004.06165","repositories_listed":4,"syntology":{"n":23,"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/oscar-object-semantics-aligned-pre-training#ran","syntology_url":"https://syntology.ai/paper/2004.06165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06165"}},"official":{"repos":["microsoft/Oscar"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/more-grounded-image-captioning-by-distilling","slug":"more-grounded-image-captioning-by-distilling","title":"More Grounded Image Captioning by Distilling Image-Text Matching Model","date":"2020-04-01","arxiv_id":"2004.00390","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/more-grounded-image-captioning-by-distilling#ran","syntology_url":"https://syntology.ai/paper/2004.00390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.00390"}},"official":{"repos":["YuanEZhou/Grounded-Image-Captioning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/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","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/visual-semantic-reasoning-for-image-text","slug":"visual-semantic-reasoning-for-image-text","title":"Visual Semantic Reasoning for Image-Text Matching","date":"2019-09-06","arxiv_id":"1909.02701","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-semantic-reasoning-for-image-text#ran","syntology_url":"https://syntology.ai/paper/1909.02701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02701"}},"official":{"repos":["KunpengLi1994/VSRN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vl-bert-pre-training-of-generic-visual","slug":"vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vl-bert-pre-training-of-generic-visual#ran","syntology_url":"https://syntology.ai/paper/1908.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08530"}},"official":{"repos":["jackroos/VL-BERT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stacked-cross-attention-for-image-text","slug":"stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","arxiv_id":"1803.08024","repositories_listed":6,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stacked-cross-attention-for-image-text#ran","syntology_url":"https://syntology.ai/paper/1803.08024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08024"}},"official":{"repos":["kuanghuei/SCAN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/attngan-fine-grained-text-to-image-generation","slug":"attngan-fine-grained-text-to-image-generation","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","date":"2017-11-28","arxiv_id":"1711.10485","repositories_listed":20,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/attngan-fine-grained-text-to-image-generation#ran","syntology_url":"https://syntology.ai/paper/1711.10485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10485"}},"official":null}}],"record_sha256":"2fb38012b8b30d9afa5f121c1ea15278e9cda500e7425d64d0d920605d2dce6a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}