{"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","name":"Image-text matching","slug":"image-text-matching","description_markdown":"**Image-Text Matching** is a subtask within *Cross-Modal Retrieval (CMR)* that involves establishing associations between images and corresponding textual descriptions. The goal is to retrieve an image given a textual query or, conversely, retrieve a textual description given an image query. This task is challenging due to *the heterogeneity gap* between image and text data representations. Image-text matching is used in applications such as content-based image search, visual question answering, and multimodal summarization.\r\n\r\n<span class=\"description-source\">[Assessing Brittleness of Image-Text Retrieval Benchmarks from Vision-Language Models Perspective](https://arxiv.org/abs/2407.15239)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":188,"papers_with_code":102,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/image-text-matching-on-commercialadsdataset","slug":"image-text-matching-on-commercialadsdataset","dataset":"CommercialAdsDataset","dataset_url":"/dataset/commercialadsdataset","rows_in_archive":8,"metrics":["ADD(S) AUC"],"first_row_in_archive_order":{"model":"AlignCMSS","paper_title":"Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search","paper_url":"/paper/align-before-search-aligning-ads-image-to","paper_date":"2023-09-28","arxiv_id":"2309.16141","code_links":[{"title":"pter61/aligncmss","url":"https://github.com/pter61/aligncmss"}],"syntology":null}}],"datasets":[{"url":"/dataset/commercialadsdataset","name":"CommercialAdsDataset","full_name":"CommercialAdsDataset","num_papers_in_archive":8}],"subtasks":[],"parent_tasks":[{"url":"/task/cross-modal-retrieval","name":"Cross-Modal Retrieval"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":188,"of_with_code":102,"tagged_in_all":188,"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":29,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":29,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/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}},{"url":"/paper/blip-bootstrapping-language-image-pre","slug":"blip-bootstrapping-language-image-pre","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","date":"2022-01-28","arxiv_id":"2201.12086","repositories_listed":9,"syntology":null},{"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/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/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/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/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/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/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/negative-pre-aware-for-noisy-cross-modal","slug":"negative-pre-aware-for-noisy-cross-modal","title":"Negative Pre-aware for Noisy Cross-modal Matching","date":"2023-12-10","arxiv_id":"2312.05777","repositories_listed":2,"syntology":null},{"url":"/paper/a-systematic-survey-of-prompt-engineering-on","slug":"a-systematic-survey-of-prompt-engineering-on","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","date":"2023-07-24","arxiv_id":"2307.12980","repositories_listed":2,"syntology":null},{"url":"/paper/a-differentiable-semantic-metric","slug":"a-differentiable-semantic-metric","title":"A Differentiable Semantic Metric Approximation in Probabilistic Embedding for Cross-Modal Retrieval","date":"2022-12-06","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/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":0,"n_instrument":6,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"6 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; 6 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":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/dissecting-deep-metric-learning-losses-for","slug":"dissecting-deep-metric-learning-losses-for","title":"Dissecting Deep Metric Learning Losses for Image-Text Retrieval","date":"2022-10-21","arxiv_id":"2210.13188","repositories_listed":2,"syntology":null},{"url":"/paper/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/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/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/matching-images-and-text-with-multi-modal","slug":"matching-images-and-text-with-multi-modal","title":"Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking","date":"2019-08-12","arxiv_id":"1908.04011","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-medical-vision-language-alignment","slug":"efficient-medical-vision-language-alignment","title":"Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models","date":"2025-06-10","arxiv_id":"2506.08990","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-information-capacity-between-vision","slug":"aligning-information-capacity-between-vision","title":"Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching","date":"2025-03-19","arxiv_id":"2503.14953","repositories_listed":1,"syntology":null},{"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/iterprime-zero-shot-referring-image","slug":"iterprime-zero-shot-referring-image","title":"IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis","date":"2025-03-02","arxiv_id":"2503.00936","repositories_listed":1,"syntology":null},{"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/filo-zero-few-shot-anomaly-detection-by-fused","slug":"filo-zero-few-shot-anomaly-detection-by-fused","title":"FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization","date":"2025-01-17","arxiv_id":"2501.10067","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-attribute-comprehension-in-large","slug":"evaluating-attribute-comprehension-in-large","title":"Evaluating Attribute Comprehension in Large Vision-Language Models","date":"2024-08-25","arxiv_id":"2408.13898","repositories_listed":1,"syntology":null},{"url":"/paper/image-text-matching-for-large-scale-book","slug":"image-text-matching-for-large-scale-book","title":"Image-text matching for large-scale book collections","date":"2024-07-29","arxiv_id":"2407.19812","repositories_listed":1,"syntology":null},{"url":"/paper/ugncl-uncertainty-guided-noisy-correspondence","slug":"ugncl-uncertainty-guided-noisy-correspondence","title":"UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching","date":"2024-07-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/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/generative-visual-instruction-tuning","slug":"generative-visual-instruction-tuning","title":"Generative Visual Instruction Tuning","date":"2024-06-17","arxiv_id":"2406.11262","repositories_listed":1,"syntology":null},{"url":"/paper/deep-boosting-learning-a-brand-new","slug":"deep-boosting-learning-a-brand-new","title":"Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matching","date":"2024-04-28","arxiv_id":"2404.18114","repositories_listed":1,"syntology":null},{"url":"/paper/radclip-enhancing-radiologic-image-analysis","slug":"radclip-enhancing-radiologic-image-analysis","title":"RadCLIP: Enhancing Radiologic Image Analysis through Contrastive Language-Image Pre-training","date":"2024-03-15","arxiv_id":"2403.09948","repositories_listed":1,"syntology":null},{"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":2,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"11 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; 9 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":2,"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/mousi-poly-visual-expert-vision-language","slug":"mousi-poly-visual-expert-vision-language","title":"MouSi: Poly-Visual-Expert Vision-Language Models","date":"2024-01-30","arxiv_id":"2401.17221","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-image-text-matching-verb-understanding","slug":"beyond-image-text-matching-verb-understanding","title":"Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking","date":"2024-01-29","arxiv_id":"2401.16575","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-image-text-matching-with-adaptive","slug":"enhancing-image-text-matching-with-adaptive","title":"Enhancing Image-Text Matching with Adaptive Feature Aggregation","date":"2024-01-18","arxiv_id":"2401.09725","repositories_listed":1,"syntology":null},{"url":"/paper/backdoor-attack-on-unpaired-medical-image","slug":"backdoor-attack-on-unpaired-medical-image","title":"Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP","date":"2024-01-01","arxiv_id":"2401.01911","repositories_listed":1,"syntology":null},{"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/plug-and-play-dense-label-free-extraction-of","slug":"plug-and-play-dense-label-free-extraction-of","title":"Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models","date":"2023-11-28","arxiv_id":"2311.17095","repositories_listed":1,"syntology":null},{"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":9,"n_instrument":8,"n_unverified":2,"n_honours":5,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 1 violated, 3 with no contract checked; 8 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":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/align-before-search-aligning-ads-image-to","slug":"align-before-search-aligning-ads-image-to","title":"Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search","date":"2023-09-28","arxiv_id":"2309.16141","repositories_listed":1,"syntology":null},{"url":"/paper/improving-multimodal-classification-of-social","slug":"improving-multimodal-classification-of-social","title":"Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks","date":"2023-09-14","arxiv_id":"2309.07794","repositories_listed":1,"syntology":null},{"url":"/paper/towards-better-multi-modal-keyphrase","slug":"towards-better-multi-modal-keyphrase","title":"Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering","date":"2023-09-09","arxiv_id":"2309.04734","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-transfer-learning-for-1","slug":"parameter-efficient-transfer-learning-for-1","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","date":"2023-08-24","arxiv_id":"2308.12509","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/parameter-efficient-transfer-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2308.12509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12509"}},"official":{"repos":["ZhanYang-nwpu/PE-RSITR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/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":5,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 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":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/advancing-visual-grounding-with-scene-1","slug":"advancing-visual-grounding-with-scene-1","title":"Advancing Visual Grounding with Scene Knowledge: Benchmark and Method","date":"2023-07-21","arxiv_id":"2307.11558","repositories_listed":1,"syntology":null},{"url":"/paper/unifine-a-unified-and-fine-grained-approach","slug":"unifine-a-unified-and-fine-grained-approach","title":"UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding","date":"2023-07-03","arxiv_id":"2307.00862","repositories_listed":1,"syntology":null},{"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":3,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/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":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/visualgptscore-visio-linguistic-reasoning","slug":"visualgptscore-visio-linguistic-reasoning","title":"Revisiting the Role of Language Priors in Vision-Language Models","date":"2023-06-02","arxiv_id":"2306.01879","repositories_listed":1,"syntology":null},{"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/llmscore-unveiling-the-power-of-large-1","slug":"llmscore-unveiling-the-power-of-large-1","title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","date":"2023-05-18","arxiv_id":"2305.11116","repositories_listed":1,"syntology":null},{"url":"/paper/malm-mask-augmentation-based-local-matching","slug":"malm-mask-augmentation-based-local-matching","title":"MALM: Mask Augmentation based Local Matching for Food-Recipe Retrieval","date":"2023-05-18","arxiv_id":"2305.11327","repositories_listed":1,"syntology":null},{"url":"/paper/vision-meets-definitions-unsupervised-visual","slug":"vision-meets-definitions-unsupervised-visual","title":"Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information","date":"2023-05-02","arxiv_id":"2305.01788","repositories_listed":1,"syntology":null},{"url":"/paper/rococo-robust-benchmark-ms-coco-to-stress","slug":"rococo-robust-benchmark-ms-coco-to-stress","title":"RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models","date":"2023-04-21","arxiv_id":"2304.10727","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-image-text-matching-improves","slug":"multimodal-image-text-matching-improves","title":"Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generation","date":"2023-03-29","arxiv_id":"2303.17579","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-language-guidance-into-image-text","slug":"integrating-language-guidance-into-image-text","title":"Integrating Language Guidance Into Image-Text Matching for Correcting False Negatives","date":"2023-03-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/increasing-textual-context-size-boosts","slug":"increasing-textual-context-size-boosts","title":"Increasing Textual Context Size Boosts Medical Image-Text Matching","date":"2023-03-23","arxiv_id":"2303.13340","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"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/brainclip-bridging-brain-and-visual","slug":"brainclip-bridging-brain-and-visual","title":"BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding","date":"2023-02-25","arxiv_id":"2302.12971","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-image-text-matching-by-cross","slug":"fine-grained-image-text-matching-by-cross","title":"Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-semantic-relationship-among","slug":"learning-semantic-relationship-among","title":"Learning Semantic Relationship Among Instances for Image-Text Matching","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/comclip-training-free-compositional-image-and","slug":"comclip-training-free-compositional-image-and","title":"ComCLIP: Training-Free Compositional Image and Text Matching","date":"2022-11-25","arxiv_id":"2211.13854","repositories_listed":1,"syntology":null},{"url":"/paper/do-vision-and-language-transformers-learn","slug":"do-vision-and-language-transformers-learn","title":"Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?","date":"2022-10-21","arxiv_id":"2210.12079","repositories_listed":1,"syntology":null},{"url":"/paper/map-modality-agnostic-uncertainty-aware","slug":"map-modality-agnostic-uncertainty-aware","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model","date":"2022-10-11","arxiv_id":"2210.05335","repositories_listed":1,"syntology":null},{"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/aladin-distilling-fine-grained-alignment","slug":"aladin-distilling-fine-grained-alignment","title":"ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval","date":"2022-07-29","arxiv_id":"2207.14757","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-video-captioning-with-evolving","slug":"zero-shot-video-captioning-with-evolving","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","date":"2022-07-22","arxiv_id":"2207.11100","repositories_listed":1,"syntology":null},{"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/gr-gan-gradual-refinement-text-to-image","slug":"gr-gan-gradual-refinement-text-to-image","title":"GR-GAN: Gradual Refinement Text-to-image Generation","date":"2022-05-23","arxiv_id":"2205.11273","repositories_listed":1,"syntology":null},{"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/declaration-based-prompt-tuning-for-visual","slug":"declaration-based-prompt-tuning-for-visual","title":"Declaration-based Prompt Tuning for Visual Question Answering","date":"2022-05-05","arxiv_id":"2205.02456","repositories_listed":1,"syntology":null},{"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/no-token-left-behind-explainability-aided","slug":"no-token-left-behind-explainability-aided","title":"No Token Left Behind: Explainability-Aided Image Classification and Generation","date":"2022-04-11","arxiv_id":"2204.04908","repositories_listed":1,"syntology":null},{"url":"/paper/mvp-multi-stage-vision-language-pre-training","slug":"mvp-multi-stage-vision-language-pre-training","title":"MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning","date":"2022-01-29","arxiv_id":"2201.12596","repositories_listed":1,"syntology":null},{"url":"/paper/negative-aware-attention-framework-for-image","slug":"negative-aware-attention-framework-for-image","title":"Negative-Aware Attention Framework for Image-Text Matching","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/denseclip-language-guided-dense-prediction","slug":"denseclip-language-guided-dense-prediction","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","date":"2021-12-02","arxiv_id":"2112.01518","repositories_listed":1,"syntology":null},{"url":"/paper/learning-with-noisy-correspondence-for-cross","slug":"learning-with-noisy-correspondence-for-cross","title":"Learning with Noisy Correspondence for Cross-modal Matching","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"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/learning-dual-semantic-relations-with-graph","slug":"learning-dual-semantic-relations-with-graph","title":"Learning Dual Semantic Relations with Graph Attention for Image-Text Matching","date":"2020-10-22","arxiv_id":"2010.11550","repositories_listed":1,"syntology":null},{"url":"/paper/medicat-a-dataset-of-medical-images-captions","slug":"medicat-a-dataset-of-medical-images-captions","title":"MedICaT: A Dataset of Medical Images, Captions, and Textual References","date":"2020-10-12","arxiv_id":"2010.06000","repositories_listed":1,"syntology":null},{"url":"/paper/consensus-aware-visual-semantic-embedding-for","slug":"consensus-aware-visual-semantic-embedding-for","title":"Consensus-Aware Visual-Semantic Embedding for Image-Text Matching","date":"2020-07-17","arxiv_id":"2007.08883","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/consensus-aware-visual-semantic-embedding-for#ran","syntology_url":"https://syntology.ai/paper/2007.08883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08883"}},"official":{"repos":["BruceW91/CVSE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/deep-multimodal-neural-architecture-search","slug":"deep-multimodal-neural-architecture-search","title":"Deep Multimodal Neural Architecture Search","date":"2020-04-25","arxiv_id":"2004.12070","repositories_listed":1,"syntology":null},{"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/neural-image-inpainting-guided-with","slug":"neural-image-inpainting-guided-with","title":"Text-Guided Neural Image Inpainting","date":"2020-04-07","arxiv_id":"2004.03212","repositories_listed":1,"syntology":null},{"url":"/paper/pixel-bert-aligning-image-pixels-with-text-by","slug":"pixel-bert-aligning-image-pixels-with-text-by","title":"Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers","date":"2020-04-02","arxiv_id":"2004.00849","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"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/adaptive-offline-quintuplet-loss-for-image","slug":"adaptive-offline-quintuplet-loss-for-image","title":"Adaptive Offline Quintuplet Loss for Image-Text Matching","date":"2020-03-07","arxiv_id":"2003.03669","repositories_listed":1,"syntology":null},{"url":"/paper/learning-fragment-self-attention-embeddings","slug":"learning-fragment-self-attention-embeddings","title":"Learning fragment self-attention embeddings for image-text matching","date":"2019-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/position-focused-attention-network-for-image","slug":"position-focused-attention-network-for-image","title":"Position Focused Attention Network for Image-Text Matching","date":"2019-07-23","arxiv_id":"1907.09748","repositories_listed":1,"syntology":null}],"syntology_records":39,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":37,"papers_where_code_ran_first_page":"/task/image-text-matching/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/image-text-matching/papers/2","json":"/task/image-text-matching/papers/2.json","rows":88},{"order":"ran","page":1,"of":1,"url":"/task/image-text-matching/papers/ran/1","json":"/task/image-text-matching/papers/ran/1.json","rows":37}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"fed3615800498d2696e7e16c6d7a23aa00e2f57bf00c854b0ec3e6fdfd05d7a3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}