{"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/phrase-grounding","name":"Phrase Grounding","slug":"phrase-grounding","description_markdown":"Given an image and a corresponding caption, the **Phrase Grounding** task aims to ground each entity mentioned by a noun phrase in the caption to a region in the image.\n\n\n<span class=\"description-source\">Source: [Phrase Grounding by Soft-Label Chain Conditional Random Field ](https://arxiv.org/abs/1909.00301)</span>","categories":[{"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":88,"papers_with_code":51,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":6,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/phrase-grounding-on-flickr30k-entities-test","slug":"phrase-grounding-on-flickr30k-entities-test","dataset":"Flickr30k Entities Test","dataset_url":"/dataset/flickr30k-entities","rows_in_archive":18,"metrics":["R@1","R@5","R@10"],"first_row_in_archive_order":{"model":"GLIPv2","paper_title":"GLIPv2: Unifying Localization and Vision-Language Understanding","paper_url":"/paper/glipv2-unifying-localization-and-vision","paper_date":"2022-06-12","arxiv_id":"2206.05836","code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"}],"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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glipv2-unifying-localization-and-vision#ran","syntology_url":"https://syntology.ai/paper/2206.05836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05836"}},"official":{"repos":["microsoft/GLIP"],"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"]}}}},{"leaderboard":"/sota/phrase-grounding-on-flickr30k","slug":"phrase-grounding-on-flickr30k","dataset":"Flickr30k","dataset_url":"/dataset/flickr30k","rows_in_archive":3,"metrics":["Pointing Game Accuracy"],"first_row_in_archive_order":{"model":"GBS Ensemble + 12-in-1","paper_title":"Detector-Free Weakly Supervised Grounding by Separation","paper_url":"/paper/detector-free-weakly-supervised-grounding-by","paper_date":"2021-04-20","arxiv_id":"2104.09829","code_links":[{"title":"aarbelle/GroundingBySeparation","url":"https://github.com/aarbelle/GroundingBySeparation"}],"syntology":null}},{"leaderboard":"/sota/phrase-grounding-on-flickr30k-entities-dev","slug":"phrase-grounding-on-flickr30k-entities-dev","dataset":"Flickr30k Entities Dev","dataset_url":"/dataset/flickr30k-entities","rows_in_archive":3,"metrics":["R@1","R@10","R@5"],"first_row_in_archive_order":{"model":"Fiber-B","paper_title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","paper_url":"/paper/coarse-to-fine-vision-language-pre-training","paper_date":"2022-06-15","arxiv_id":"2206.07643","code_links":[{"title":"microsoft/fiber","url":"https://github.com/microsoft/fiber"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/coarse-to-fine-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2206.07643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07643"}},"official":{"repos":["microsoft/fiber"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}}},{"leaderboard":"/sota/phrase-grounding-on-referit","slug":"phrase-grounding-on-referit","dataset":"ReferIt","dataset_url":null,"rows_in_archive":3,"metrics":["Pointing Game Accuracy","Accuracy"],"first_row_in_archive_order":{"model":"VG_BiLSTM_VGG","paper_title":"Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding","paper_url":"/paper/multi-level-multimodal-common-semantic-space","paper_date":"2018-11-28","arxiv_id":"1811.11683","code_links":[{"title":"hassanhub/MultiGrounding","url":"https://github.com/hassanhub/MultiGrounding"}],"syntology":null}},{"leaderboard":"/sota/phrase-grounding-on-visual-genome","slug":"phrase-grounding-on-visual-genome","dataset":"Visual Genome","dataset_url":"/dataset/visual-genome","rows_in_archive":3,"metrics":["Pointing Game Accuracy"],"first_row_in_archive_order":{"model":"GbS VG","paper_title":"Detector-Free Weakly Supervised Grounding by Separation","paper_url":"/paper/detector-free-weakly-supervised-grounding-by","paper_date":"2021-04-20","arxiv_id":"2104.09829","code_links":[{"title":"aarbelle/GroundingBySeparation","url":"https://github.com/aarbelle/GroundingBySeparation"}],"syntology":null}}],"datasets":[{"url":"/dataset/visual-genome","name":"Visual Genome","full_name":"","num_papers_in_archive":1256},{"url":"/dataset/flickr30k","name":"Flickr30k","full_name":"Flickr30k","num_papers_in_archive":880},{"url":"/dataset/flickr30k-entities","name":"Flickr30K Entities","full_name":"","num_papers_in_archive":142},{"url":"/dataset/ms-cxr","name":"MS-CXR","full_name":"Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing","num_papers_in_archive":32},{"url":"/dataset/g-vue","name":"G-VUE","full_name":"General-purpose Visual Understanding Evaluation","num_papers_in_archive":2},{"url":"/dataset/vd-ref","name":"VD-Ref","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/grounded-open-vocabulary-acquisition","name":"Grounded Open Vocabulary Acquisition"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":88,"of":88,"of_with_code":51,"tagged_in_all":88,"counts":{"archive_papers_tagged":88,"with_a_code_link":51,"where_syntology_ran_a_sample":20,"not_listed_spam_title":0,"listed":88,"listed_where_code_ran":20,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":17,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/multimodal-compact-bilinear-pooling-for","slug":"multimodal-compact-bilinear-pooling-for","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","date":"2016-06-06","arxiv_id":"1606.01847","repositories_listed":10,"syntology":null},{"url":"/paper/mdetr-modulated-detection-for-end-to-end","slug":"mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","repositories_listed":5,"syntology":{"n":11,"n_ran":7,"n_constructed":4,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mdetr-modulated-detection-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2104.12763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12763"}},"official":{"repos":["ashkamath/mdetr"],"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/towards-visual-grounding-a-survey","slug":"towards-visual-grounding-a-survey","title":"Towards Visual Grounding: A Survey","date":"2024-12-28","arxiv_id":"2412.20206","repositories_listed":4,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"13 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; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-visual-grounding-a-survey#ran","syntology_url":"https://syntology.ai/paper/2412.20206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20206"}},"official":null}},{"url":"/paper/open-vocabulary-phrase-detection","slug":"open-vocabulary-phrase-detection","title":"Revisiting Image-Language Networks for Open-ended Phrase Detection","date":"2018-11-17","arxiv_id":"1811.07212","repositories_listed":3,"syntology":null},{"url":"/paper/grounding-of-textual-phrases-in-images-by","slug":"grounding-of-textual-phrases-in-images-by","title":"Grounding of Textual Phrases in Images by Reconstruction","date":"2015-11-12","arxiv_id":"1511.03745","repositories_listed":3,"syntology":null},{"url":"/paper/an-open-and-comprehensive-pipeline-for","slug":"an-open-and-comprehensive-pipeline-for","title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection","date":"2024-01-04","arxiv_id":"2401.02361","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-open-and-comprehensive-pipeline-for#ran","syntology_url":"https://syntology.ai/paper/2401.02361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02361"}},"official":{"repos":["open-mmlab/mmdetection"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/kosmos-2-grounding-multimodal-large-language","slug":"kosmos-2-grounding-multimodal-large-language","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","date":"2023-06-26","arxiv_id":"2306.14824","repositories_listed":2,"syntology":null},{"url":"/paper/making-the-most-of-text-semantics-to-improve","slug":"making-the-most-of-text-semantics-to-improve","title":"Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing","date":"2022-04-21","arxiv_id":"2204.09817","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/making-the-most-of-text-semantics-to-improve#ran","syntology_url":"https://syntology.ai/paper/2204.09817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.09817"}},"official":{"repos":["microsoft/hi-ml"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/flickr30k-entities-collecting-region-to","slug":"flickr30k-entities-collecting-region-to","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","date":"2015-05-19","arxiv_id":"1505.04870","repositories_listed":2,"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/flickr30k-entities-collecting-region-to#ran","syntology_url":"https://syntology.ai/paper/1505.04870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.04870"}},"official":null}},{"url":"/paper/disambiguating-reference-in-visually-grounded","slug":"disambiguating-reference-in-visually-grounded","title":"Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures","date":"2025-05-16","arxiv_id":"2505.11726","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":1,"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, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/disambiguating-reference-in-visually-grounded#ran","syntology_url":"https://syntology.ai/paper/2505.11726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11726"}},"official":{"repos":["sinadumi/mmrr"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/anatomical-grounding-pre-training-for-medical","slug":"anatomical-grounding-pre-training-for-medical","title":"Anatomical grounding pre-training for medical phrase grounding","date":"2025-02-23","arxiv_id":"2502.16585","repositories_listed":1,"syntology":null},{"url":"/paper/vicca-visual-interpretation-and-comprehension","slug":"vicca-visual-interpretation-and-comprehension","title":"VICCA: Visual Interpretation and Comprehension of Chest X-ray Anomalies in Generated Report Without Human Feedback","date":"2025-01-29","arxiv_id":"2501.17726","repositories_listed":1,"syntology":null},{"url":"/paper/context-infused-visual-grounding-for-art","slug":"context-infused-visual-grounding-for-art","title":"Context-Infused Visual Grounding for Art","date":"2024-10-16","arxiv_id":"2410.12369","repositories_listed":1,"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/context-infused-visual-grounding-for-art#ran","syntology_url":"https://syntology.ai/paper/2410.12369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12369"}},"official":{"repos":["selinakhan/CIGAr"],"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/transformer-with-controlled-attention-for","slug":"transformer-with-controlled-attention-for","title":"Transformer with Controlled Attention for Synchronous Motion Captioning","date":"2024-09-13","arxiv_id":"2409.09177","repositories_listed":1,"syntology":null},{"url":"/paper/lightmdetr-a-lightweight-approach-for-low","slug":"lightmdetr-a-lightweight-approach-for-low","title":"A Lightweight Modular Framework for Low-Cost Open-Vocabulary Object Detection Training","date":"2024-08-20","arxiv_id":"2408.10787","repositories_listed":1,"syntology":null},{"url":"/paper/empathic-grounding-explorations-using","slug":"empathic-grounding-explorations-using","title":"Empathic Grounding: Explorations using Multimodal Interaction and Large Language Models with Conversational Agents","date":"2024-07-01","arxiv_id":"2407.01824","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-medical-phrase-grounding-with-off","slug":"zero-shot-medical-phrase-grounding-with-off","title":"Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion Models","date":"2024-04-19","arxiv_id":"2404.12920","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/zero-shot-medical-phrase-grounding-with-off#ran","syntology_url":"https://syntology.ai/paper/2404.12920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12920"}},"official":{"repos":["vios-s/ldm-phrase-grounding"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/griffon-v2-advancing-multimodal-perception","slug":"griffon-v2-advancing-multimodal-perception","title":"Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring","date":"2024-03-14","arxiv_id":"2403.09333","repositories_listed":1,"syntology":null},{"url":"/paper/pg-video-llava-pixel-grounding-large-video","slug":"pg-video-llava-pixel-grounding-large-video","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","date":"2023-11-22","arxiv_id":"2311.13435","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pg-video-llava-pixel-grounding-large-video#ran","syntology_url":"https://syntology.ai/paper/2311.13435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13435"}},"official":{"repos":["mbzuai-oryx/video-llava"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/augment-the-pairs-semantics-preserving-image","slug":"augment-the-pairs-semantics-preserving-image","title":"Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models","date":"2023-11-05","arxiv_id":"2311.02536","repositories_listed":1,"syntology":null},{"url":"/paper/localizing-active-objects-from-egocentric","slug":"localizing-active-objects-from-egocentric","title":"Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge","date":"2023-10-23","arxiv_id":"2310.15066","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-representation-in-radiography","slug":"enhancing-representation-in-radiography","title":"Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive Learning","date":"2023-09-12","arxiv_id":"2309.05904","repositories_listed":1,"syntology":null},{"url":"/paper/box-based-refinement-for-weakly-supervised","slug":"box-based-refinement-for-weakly-supervised","title":"Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks","date":"2023-09-07","arxiv_id":"2309.03874","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":11,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/box-based-refinement-for-weakly-supervised#ran","syntology_url":"https://syntology.ai/paper/2309.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03874"}},"official":{"repos":["eyalgomel/box-based-refinement"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/a-joint-study-of-phrase-grounding-and-task","slug":"a-joint-study-of-phrase-grounding-and-task","title":"A Joint Study of Phrase Grounding and Task Performance in Vision and Language Models","date":"2023-09-06","arxiv_id":"2309.02691","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-joint-study-of-phrase-grounding-and-task#ran","syntology_url":"https://syntology.ai/paper/2309.02691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.02691"}},"official":{"repos":["lil-lab/phrase_grounding"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-on-interpretable-cross-modal","slug":"a-survey-on-interpretable-cross-modal","title":"A Survey on Interpretable Cross-modal Reasoning","date":"2023-09-05","arxiv_id":"2309.01955","repositories_listed":1,"syntology":null},{"url":"/paper/pay-attention-accuracy-versus","slug":"pay-attention-accuracy-versus","title":"Trade-offs in Fine-tuned Diffusion Models Between Accuracy and Interpretability","date":"2023-03-31","arxiv_id":"2303.17908","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-exploit-temporal-structure-for","slug":"learning-to-exploit-temporal-structure-for","title":"Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing","date":"2023-01-11","arxiv_id":"2301.04558","repositories_listed":1,"syntology":null},{"url":"/paper/similarity-maps-for-self-training-weakly","slug":"similarity-maps-for-self-training-weakly","title":"Similarity Maps for Self-Training Weakly-Supervised Phrase Grounding","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dq-detr-dual-query-detection-transformer-for","slug":"dq-detr-dual-query-detection-transformer-for","title":"DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding","date":"2022-11-28","arxiv_id":"2211.15516","repositories_listed":1,"syntology":null},{"url":"/paper/extending-phrase-grounding-with-pronouns-in","slug":"extending-phrase-grounding-with-pronouns-in","title":"Extending Phrase Grounding with Pronouns in Visual Dialogues","date":"2022-10-23","arxiv_id":"2210.12658","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/extending-phrase-grounding-with-pronouns-in#ran","syntology_url":"https://syntology.ai/paper/2210.12658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12658"}},"official":{"repos":["izhx/phrase-grounding-with-pronoun"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/omdet-language-aware-object-detection-with","slug":"omdet-language-aware-object-detection-with","title":"OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network","date":"2022-09-10","arxiv_id":"2209.05946","repositories_listed":1,"syntology":null},{"url":"/paper/what-is-where-by-looking-weakly-supervised","slug":"what-is-where-by-looking-weakly-supervised","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","date":"2022-06-19","arxiv_id":"2206.09358","repositories_listed":1,"syntology":null},{"url":"/paper/coarse-to-fine-vision-language-pre-training","slug":"coarse-to-fine-vision-language-pre-training","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","date":"2022-06-15","arxiv_id":"2206.07643","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/coarse-to-fine-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2206.07643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07643"}},"official":{"repos":["microsoft/fiber"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/glipv2-unifying-localization-and-vision","slug":"glipv2-unifying-localization-and-vision","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","date":"2022-06-12","arxiv_id":"2206.05836","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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glipv2-unifying-localization-and-vision#ran","syntology_url":"https://syntology.ai/paper/2206.05836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05836"}},"official":{"repos":["microsoft/GLIP"],"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/pevl-position-enhanced-pre-training-and","slug":"pevl-position-enhanced-pre-training-and","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","date":"2022-05-23","arxiv_id":"2205.11169","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":0,"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/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"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/unsupervised-vision-language-parsing","slug":"unsupervised-vision-language-parsing","title":"Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationships","date":"2022-03-27","arxiv_id":"2203.14260","repositories_listed":1,"syntology":null},{"url":"/paper/detector-free-weakly-supervised-grounding-by","slug":"detector-free-weakly-supervised-grounding-by","title":"Detector-Free Weakly Supervised Grounding by Separation","date":"2021-04-20","arxiv_id":"2104.09829","repositories_listed":1,"syntology":null},{"url":"/paper/mdetr-modulated-detection-for-end-to-end-1","slug":"mdetr-modulated-detection-for-end-to-end-1","title":"MDETR - Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-ground-medical-text-in-a-3d-human","slug":"learning-to-ground-medical-text-in-a-3d-human","title":"Learning to ground medical text in a 3D human atlas","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/maf-multimodal-alignment-framework-for-weakly","slug":"maf-multimodal-alignment-framework-for-weakly","title":"MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding","date":"2020-10-12","arxiv_id":"2010.05379","repositories_listed":1,"syntology":null},{"url":"/paper/improving-weakly-supervised-visual-grounding","slug":"improving-weakly-supervised-visual-grounding","title":"Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation","date":"2020-07-03","arxiv_id":"2007.01951","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-weakly-supervised-visual-grounding#ran","syntology_url":"https://syntology.ai/paper/2007.01951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.01951"}},"official":{"repos":["jhuang81/weak-sup-visual-grounding"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/shapeshifter-networks-cross-layer-parameter","slug":"shapeshifter-networks-cross-layer-parameter","title":"Neural Parameter Allocation Search","date":"2020-06-18","arxiv_id":"2006.10598","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/shapeshifter-networks-cross-layer-parameter#ran","syntology_url":"https://syntology.ai/paper/2006.10598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10598"}},"official":{"repos":["bryanplummer/ssn"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-learning-for-weakly-supervised","slug":"contrastive-learning-for-weakly-supervised","title":"Contrastive Learning for Weakly Supervised Phrase Grounding","date":"2020-06-17","arxiv_id":"2006.09920","repositories_listed":1,"syntology":null},{"url":"/paper/learning-cross-modal-context-graph-for-visual","slug":"learning-cross-modal-context-graph-for-visual","title":"Learning Cross-modal Context Graph for Visual Grounding","date":"2020-02-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/phrase-grounding-by-soft-label-chain","slug":"phrase-grounding-by-soft-label-chain","title":"Phrase Grounding by Soft-Label Chain Conditional Random Field","date":"2019-09-01","arxiv_id":"1909.00301","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-grounding-of-objects-from-natural","slug":"zero-shot-grounding-of-objects-from-natural","title":"Zero-Shot Grounding of Objects from Natural Language Queries","date":"2019-08-20","arxiv_id":"1908.07129","repositories_listed":1,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/zero-shot-grounding-of-objects-from-natural#ran","syntology_url":"https://syntology.ai/paper/1908.07129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07129"}},"official":{"repos":["TheShadow29/zsgnet-pytorch"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/modularized-textual-grounding-for","slug":"modularized-textual-grounding-for","title":"Modularized Textual Grounding for Counterfactual Resilience","date":"2019-04-07","arxiv_id":"1904.03589","repositories_listed":1,"syntology":null},{"url":"/paper/multi-level-multimodal-common-semantic-space","slug":"multi-level-multimodal-common-semantic-space","title":"Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding","date":"2018-11-28","arxiv_id":"1811.11683","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-diversified-and-discriminative","slug":"rethinking-diversified-and-discriminative","title":"Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding","date":"2018-05-09","arxiv_id":"1805.03508","repositories_listed":1,"syntology":null},{"url":"/paper/conditional-image-text-embedding-networks","slug":"conditional-image-text-embedding-networks","title":"Conditional Image-Text Embedding Networks","date":"2017-11-22","arxiv_id":"1711.08389","repositories_listed":1,"syntology":null},{"url":"/paper/natural-language-object-retrieval","slug":"natural-language-object-retrieval","title":"Natural Language Object Retrieval","date":"2015-11-13","arxiv_id":"1511.04164","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/natural-language-object-retrieval#ran","syntology_url":"https://syntology.ai/paper/1511.04164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.04164"}},"official":null}},{"url":null,"slug":"anatomy-grounded-weakly-supervised-prompt","title":"Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion Models","date":"2025-06-12","arxiv_id":"2506.10633","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-object-detection-and-phrase","title":"A Comparison of Object Detection and Phrase Grounding Models in Chest X-ray Abnormality Localization using Eye-tracking Data","date":"2025-03-02","arxiv_id":"2503.01037","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-local-alignment-for-medical","title":"Progressive Local Alignment for Medical Multimodal Pre-training","date":"2025-02-25","arxiv_id":"2502.18047","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-self-paced-learning-for-weakly","title":"Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding","date":"2025-01-28","arxiv_id":"2501.17053","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-alignment-enhanced-adaptive","title":"Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension","date":"2025-01-02","arxiv_id":"2501.01416","repositories_listed":0,"syntology":null},{"url":null,"slug":"vicas-a-dataset-for-combining-holistic-and","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","date":"2024-12-12","arxiv_id":"2412.09754","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-multimodal-hallucination","title":"Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data","date":"2024-08-30","arxiv_id":"2409.00238","repositories_listed":0,"syntology":null},{"url":null,"slug":"cxr-agent-vision-language-models-for-chest-x","title":"CXR-Agent: Vision-language models for chest X-ray interpretation with uncertainty aware radiology reporting","date":"2024-07-11","arxiv_id":"2407.08811","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-groundcam-quantifying-grounding-in-vision","title":"Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM","date":"2024-04-29","arxiv_id":"2404.19128","repositories_listed":0,"syntology":null},{"url":null,"slug":"medrg-medical-report-grounding-with-multi","title":"MedRG: Medical Report Grounding with Multi-modal Large Language Model","date":"2024-04-10","arxiv_id":"2404.06798","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-region-guidance-improving","title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training","date":"2024-03-04","arxiv_id":"2403.02325","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-understand-support-an-implicit","title":"How to Understand \"Support\"? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding","date":"2024-02-29","arxiv_id":"2402.19116","repositories_listed":0,"syntology":null},{"url":null,"slug":"phrase-grounding-based-style-transfer-for","title":"Phrase Grounding-based Style Transfer for Single-Domain Generalized Object Detection","date":"2024-02-02","arxiv_id":"2402.01304","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-vision-language-foundation","title":"Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinement","date":"2024-01-21","arxiv_id":"2401.11421","repositories_listed":0,"syntology":null},{"url":null,"slug":"catalog-phrase-grounding-cpg-grounding-of","title":"Catalog Phrase Grounding (CPG): Grounding of Product Textual Attributes in Product Images for e-commerce Vision-Language Applications","date":"2023-08-30","arxiv_id":"2308.16354","repositories_listed":0,"syntology":null},{"url":null,"slug":"read-look-and-detect-bounding-box-annotation","title":"Read, look and detect: Bounding box annotation from image-caption pairs","date":"2023-06-09","arxiv_id":"2306.06149","repositories_listed":0,"syntology":null},{"url":null,"slug":"elvis-empowering-locality-of-vision-language","title":"ELVIS: Empowering Locality of Vision Language Pre-training with Intra-modal Similarity","date":"2023-04-11","arxiv_id":"2304.05303","repositories_listed":0,"syntology":null},{"url":null,"slug":"cavl-learning-contrastive-and-adaptive","title":"CAVL: Learning Contrastive and Adaptive Representations of Vision and Language","date":"2023-04-10","arxiv_id":"2304.04399","repositories_listed":0,"syntology":null},{"url":"/paper/limitr-leveraging-local-information-for","slug":"limitr-leveraging-local-information-for","title":"LIMITR: Leveraging Local Information for Medical Image-Text Representation","date":"2023-03-21","arxiv_id":"2303.11755","repositories_listed":0,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/limitr-leveraging-local-information-for#ran","syntology_url":"https://syntology.ai/paper/2303.11755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11755"}},"official":null}},{"url":null,"slug":"enhancing-the-role-of-context-in-region-word","title":"Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection","date":"2023-03-17","arxiv_id":"2303.10093","repositories_listed":0,"syntology":null},{"url":null,"slug":"medical-phrase-grounding-with-region-phrase","title":"Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment","date":"2023-03-14","arxiv_id":"2303.07618","repositories_listed":0,"syntology":null},{"url":null,"slug":"detailed-annotations-of-chest-x-rays-via-ct","title":"Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding","date":"2022-10-07","arxiv_id":"2210.03416","repositories_listed":0,"syntology":null},{"url":null,"slug":"lite-mdetr-a-lightweight-multi-modal-detector","title":"Lite-MDETR: A Lightweight Multi-Modal Detector","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-pre-trained-vision-and-language","title":"Improving Pre-trained Vision-and-Language Embeddings for Phrase Grounding","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-vision-language-grammar","title":"Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-plural-phrases-countering","title":"Grounding Plural Phrases: Countering Evaluation Biases by Individuation","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/disentangled-motif-aware-graph-learning-for","slug":"disentangled-motif-aware-graph-learning-for","title":"Disentangled Motif-aware Graph Learning for Phrase Grounding","date":"2021-04-13","arxiv_id":"2104.06008","repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-every-image-object-for-semi","title":"Utilizing Every Image Object for Semi-supervised Phrase Grounding","date":"2020-11-05","arxiv_id":"2011.02655","repositories_listed":0,"syntology":null},{"url":null,"slug":"propagating-over-phrase-relations-for-one","title":"Propagating Over Phrase Relations for One-Stage Visual Grounding","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-features-matter-effective-language","title":"Language Features Matter: Effective Language Representations for Vision-Language Tasks","date":"2019-08-17","arxiv_id":"1908.06327","repositories_listed":0,"syntology":null},{"url":null,"slug":"align2ground-weakly-supervised-phrase","title":"Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment","date":"2019-03-27","arxiv_id":"1903.11649","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-sequential-phrase-grounding-seqground","title":"Neural Sequential Phrase Grounding (SeqGROUND)","date":"2019-03-18","arxiv_id":"1903.07669","repositories_listed":0,"syntology":null},{"url":null,"slug":"pirc-net-using-proposal-indexing","title":"PIRC Net : Using Proposal Indexing, Relationships and Context for Phrase Grounding","date":"2018-12-07","arxiv_id":"1812.03213","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-conditional-networks-for-few-shot","title":"Dynamic Conditional Networks for Few-Shot Learning","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-aided-consistency-for-weakly","title":"Knowledge Aided Consistency for Weakly Supervised Phrase Grounding","date":"2018-03-11","arxiv_id":"1803.03879","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-guided-regression-network-with-context","title":"Query-guided Regression Network with Context Policy for Phrase Grounding","date":"2017-08-04","arxiv_id":"1708.01676","repositories_listed":0,"syntology":null},{"url":"/paper/learning-deep-structure-preserving-image-text","slug":"learning-deep-structure-preserving-image-text","title":"Learning Deep Structure-Preserving Image-Text Embeddings","date":"2015-11-19","arxiv_id":"1511.06078","repositories_listed":0,"syntology":null}],"syntology_records":20,"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":20,"papers_where_code_ran_first_page":"/task/phrase-grounding/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":"ran","page":1,"of":1,"url":"/task/phrase-grounding/papers/ran/1","json":"/task/phrase-grounding/papers/ran/1.json","rows":20}],"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":"9ba6bfbaabc4c163bc5ddd7a8498ddec41a6dcb5e9944309f01fbb74895a9065","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}