{"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/referring-expression-segmentation","name":"Referring Expression Segmentation","slug":"referring-expression-segmentation","description_markdown":"The task aims at labeling the pixels of an image or video that represent an object instance referred by a linguistic expression. In particular, the referring expression (RE) must allow the identification of an individual object in a discourse or scene (the referent). REs unambiguously identify the target instance.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":145,"papers_with_code":97,"benchmarks":22,"benchmark_tables_in_archive":22,"benchmark_tables_shown":22,"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":11,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","slug":"referring-expression-segmentation-on-refcoco","dataset":"RefCoCo val","dataset_url":"/dataset/refcoco","rows_in_archive":37,"metrics":["Overall IoU","mIoU","Precision@0.5","Precision@0.6","Precision@0.7","Precision@0.8","Precision@0.9","Mean IoU"],"first_row_in_archive_order":{"model":"DeRIS-L","paper_title":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy","paper_url":"/paper/deris-decoupling-perception-and-cognition-for","paper_date":"2025-07-02","arxiv_id":"2507.01738","code_links":[{"title":"Dmmm1997/DeRIS","url":"https://github.com/Dmmm1997/DeRIS"}],"syntology":null}},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-3","slug":"referring-expression-segmentation-on-refcoco-3","dataset":"RefCOCO+ val","dataset_url":"/dataset/refcoco","rows_in_archive":33,"metrics":["Overall IoU","Mean IoU"],"first_row_in_archive_order":{"model":"MLCD-Seg-7B","paper_title":"Multi-label Cluster Discrimination for Visual Representation Learning","paper_url":"/paper/multi-label-cluster-discrimination-for-visual","paper_date":"2024-07-24","arxiv_id":"2407.17331","code_links":[{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"}],"syntology":{"n":11,"n_ran":7,"n_constructed":7,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 7 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) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multi-label-cluster-discrimination-for-visual#ran","syntology_url":"https://syntology.ai/paper/2407.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17331"}},"official":{"repos":["deepglint/unicom"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-refer-1","slug":"referring-expression-segmentation-on-refer-1","dataset":"Refer-YouTube-VOS (2021 public validation)","dataset_url":"/dataset/refer-youtube-vos","rows_in_archive":33,"metrics":["J&F","J","F"],"first_row_in_archive_order":{"model":"MPG-SAM 2","paper_title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","paper_url":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","paper_date":"2025-01-23","arxiv_id":"2501.13667","code_links":[{"title":"rongfu-dsb/MPG-SAM2","url":"https://github.com/rongfu-dsb/MPG-SAM2"}],"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and#ran","syntology_url":"https://syntology.ai/paper/2501.13667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13667"}},"official":{"repos":["rongfu-dsb/MPG-SAM2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-4","slug":"referring-expression-segmentation-on-refcoco-4","dataset":"RefCOCO+ testA","dataset_url":"/dataset/refcoco","rows_in_archive":30,"metrics":["Overall IoU","Mean IoU","mIoU"],"first_row_in_archive_order":{"model":"HyperSeg","paper_title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","paper_url":"/paper/hyperseg-towards-universal-visual","paper_date":"2024-11-26","arxiv_id":"2411.17606","code_links":[{"title":"congvvc/HyperSeg","url":"https://github.com/congvvc/HyperSeg"}],"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":4,"n_honours":4,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}},"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-5","slug":"referring-expression-segmentation-on-refcoco-5","dataset":"RefCOCO+ test B","dataset_url":"/dataset/refcoco","rows_in_archive":30,"metrics":["Overall IoU","Mean IoU","mIoU"],"first_row_in_archive_order":{"model":"MLCD-Seg-7B","paper_title":"Multi-label Cluster Discrimination for Visual Representation Learning","paper_url":"/paper/multi-label-cluster-discrimination-for-visual","paper_date":"2024-07-24","arxiv_id":"2407.17331","code_links":[{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"}],"syntology":{"n":11,"n_ran":7,"n_constructed":7,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 7 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) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multi-label-cluster-discrimination-for-visual#ran","syntology_url":"https://syntology.ai/paper/2407.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17331"}},"official":{"repos":["deepglint/unicom"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-a2d","slug":"referring-expression-segmentation-on-a2d","dataset":"A2D Sentences","dataset_url":"/dataset/a2d-sentences","rows_in_archive":27,"metrics":["AP","IoU overall","IoU mean","Precision@0.5","Precision@0.6","Precision@0.7","Precision@0.8","Precision@0.9"],"first_row_in_archive_order":{"model":"SgMg (Video-Swin-B)","paper_title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","paper_url":"/paper/spectrum-guided-multi-granularity-referring","paper_date":"2023-07-25","arxiv_id":"2307.13537","code_links":[{"title":"bo-miao/sgmg","url":"https://github.com/bo-miao/sgmg"}],"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/spectrum-guided-multi-granularity-referring#ran","syntology_url":"https://syntology.ai/paper/2307.13537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13537"}},"official":{"repos":["bo-miao/sgmg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog","slug":"referring-expression-segmentation-on-refcocog","dataset":"RefCOCOg-val","dataset_url":"/dataset/google-refexp","rows_in_archive":23,"metrics":["Overall IoU","Mean IoU","IoU","mIoU"],"first_row_in_archive_order":{"model":"MLCD-Seg-7B","paper_title":"Multi-label Cluster Discrimination for Visual Representation Learning","paper_url":"/paper/multi-label-cluster-discrimination-for-visual","paper_date":"2024-07-24","arxiv_id":"2407.17331","code_links":[{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"}],"syntology":{"n":11,"n_ran":7,"n_constructed":7,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 7 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) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multi-label-cluster-discrimination-for-visual#ran","syntology_url":"https://syntology.ai/paper/2407.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17331"}},"official":{"repos":["deepglint/unicom"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-j-hmdb","slug":"referring-expression-segmentation-on-j-hmdb","dataset":"J-HMDB","dataset_url":"/dataset/jhmdb","rows_in_archive":21,"metrics":["AP","IoU overall","IoU mean","Precision@0.5","Precision@0.6","Precision@0.7","Precision@0.8","Precision@0.9"],"first_row_in_archive_order":{"model":"SgMg (Video-Swin-B)","paper_title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","paper_url":"/paper/spectrum-guided-multi-granularity-referring","paper_date":"2023-07-25","arxiv_id":"2307.13537","code_links":[{"title":"bo-miao/sgmg","url":"https://github.com/bo-miao/sgmg"}],"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/spectrum-guided-multi-granularity-referring#ran","syntology_url":"https://syntology.ai/paper/2307.13537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13537"}},"official":{"repos":["bo-miao/sgmg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-davis","slug":"referring-expression-segmentation-on-davis","dataset":"DAVIS 2017 (val)","dataset_url":"/dataset/davis-2017","rows_in_archive":18,"metrics":["J&F 1st frame","J&F Full video","Zero-Shot Transfer","J&F score"],"first_row_in_archive_order":{"model":"UNINEXT-H","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","paper_url":"/paper/universal-instance-perception-as-object","paper_date":"2023-03-12","arxiv_id":"2303.06674","code_links":[{"title":"MasterBin-IIAU/UNINEXT","url":"https://github.com/MasterBin-IIAU/UNINEXT"}],"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/universal-instance-perception-as-object#ran","syntology_url":"https://syntology.ai/paper/2303.06674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06674"}},"official":{"repos":["MasterBin-IIAU/UNINEXT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog-1","slug":"referring-expression-segmentation-on-refcocog-1","dataset":"RefCOCOg-test","dataset_url":"/dataset/google-refexp","rows_in_archive":18,"metrics":["Overall IoU","Mean IoU","mIoU"],"first_row_in_archive_order":{"model":"UniLSeg-100","paper_title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","paper_url":"/paper/universal-segmentation-at-arbitrary","paper_date":"2023-12-04","arxiv_id":"2312.01623","code_links":[{"title":"yongliu20/UniLSeg","url":"https://github.com/yongliu20/UniLSeg"},{"title":"workforai/UniLSeg","url":"https://github.com/workforai/UniLSeg"}],"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":2,"n_instrument":12,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"14 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; 12 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/universal-segmentation-at-arbitrary#ran","syntology_url":"https://syntology.ai/paper/2312.01623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01623"}},"official":{"repos":["workforai/UniLSeg","yongliu20/UniLSeg"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-8","slug":"referring-expression-segmentation-on-refcoco-8","dataset":"RefCOCO testA","dataset_url":"/dataset/refcoco","rows_in_archive":13,"metrics":["Overall IoU","mIoU","Mean IoU"],"first_row_in_archive_order":{"model":"DeRIS-L","paper_title":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy","paper_url":"/paper/deris-decoupling-perception-and-cognition-for","paper_date":"2025-07-02","arxiv_id":"2507.01738","code_links":[{"title":"Dmmm1997/DeRIS","url":"https://github.com/Dmmm1997/DeRIS"}],"syntology":null}},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-9","slug":"referring-expression-segmentation-on-refcoco-9","dataset":"RefCOCO testB","dataset_url":"/dataset/refcoco","rows_in_archive":13,"metrics":["Overall IoU","mIoU","Mean IoU"],"first_row_in_archive_order":{"model":"HyperSeg","paper_title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","paper_url":"/paper/hyperseg-towards-universal-visual","paper_date":"2024-11-26","arxiv_id":"2411.17606","code_links":[{"title":"congvvc/HyperSeg","url":"https://github.com/congvvc/HyperSeg"}],"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":4,"n_honours":4,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}},"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on","slug":"referring-expression-segmentation-on","dataset":"PhraseCut","dataset_url":"/dataset/phrasecut","rows_in_archive":6,"metrics":["Mean IoU","Pr@0.5","Pr@0.7","Pr@0.9"],"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/referring-expression-segmentation-on-refcoco-6","slug":"referring-expression-segmentation-on-refcoco-6","dataset":"RefCOCO","dataset_url":"/dataset/refcoco","rows_in_archive":4,"metrics":["IoU","IoU (%)"],"first_row_in_archive_order":{"model":"DETRIS","paper_title":"Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation","paper_url":"/paper/densely-connected-parameter-efficient-tuning","paper_date":"2025-01-15","arxiv_id":"2501.08580","code_links":[{"title":"jiaqihuang01/detris","url":"https://github.com/jiaqihuang01/detris"}],"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"13 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; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/densely-connected-parameter-efficient-tuning#ran","syntology_url":"https://syntology.ai/paper/2501.08580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08580"}},"official":{"repos":["jiaqihuang01/detris"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-referit","slug":"referring-expression-segmentation-on-referit","dataset":"ReferIt","dataset_url":null,"rows_in_archive":3,"metrics":["Overall IoU","Mean IoU"],"first_row_in_archive_order":{"model":"PolyFormer-L","paper_title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","paper_url":"/paper/polyformer-referring-image-segmentation-as","paper_date":"2023-02-14","arxiv_id":"2302.07387","code_links":[{"title":"amazon-science/polygon-transformer","url":"https://github.com/amazon-science/polygon-transformer"}],"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/polyformer-referring-image-segmentation-as#ran","syntology_url":"https://syntology.ai/paper/2302.07387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07387"}},"official":{"repos":["amazon-science/polygon-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-expression-segmentation-on-refer","slug":"referring-expression-segmentation-on-refer","dataset":"Refer-YouTube-VOS","dataset_url":"/dataset/refer-youtube-vos","rows_in_archive":2,"metrics":["Mean IoU","Precision@0.5","Precision@0.9"],"first_row_in_archive_order":{"model":"RefVOS-Human REs","paper_title":"SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation","paper_url":"/paper/synthref-generation-of-synthetic-referring","paper_date":"2021-06-08","arxiv_id":"2106.04403","code_links":[{"title":"miriambellver/refvos","url":"https://github.com/miriambellver/refvos"},{"title":"imatge-upc/synthref","url":"https://github.com/imatge-upc/synthref"}],"syntology":null}},{"leaderboard":"/sota/referring-expression-segmentation-on-1","slug":"referring-expression-segmentation-on-1","dataset":"Referring Expressions for DAVIS 2016 & 2017","dataset_url":"/dataset/referring-expressions-for-davis-2016-2017","rows_in_archive":1,"metrics":["F","J","J&F 1st frame"],"first_row_in_archive_order":{"model":"MUTR","paper_title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","paper_url":"/paper/referred-by-multi-modality-a-unified-temporal","paper_date":"2023-05-25","arxiv_id":"2305.16318","code_links":[{"title":"opengvlab/mutr","url":"https://github.com/opengvlab/mutr"}],"syntology":null}},{"leaderboard":"/sota/referring-expression-segmentation-on-a2dre","slug":"referring-expression-segmentation-on-a2dre","dataset":"A2Dre test","dataset_url":"/dataset/a2d-referring-expressions","rows_in_archive":1,"metrics":["Overall IoU","Mean IoU"],"first_row_in_archive_order":{"model":"RefVos","paper_title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","paper_url":"/paper/refvos-a-closer-look-at-referring-expressions","paper_date":"2020-10-01","arxiv_id":"2010.00263","code_links":[{"title":"miriambellver/refvos","url":"https://github.com/miriambellver/refvos"},{"title":"imatge-upc/refvos","url":"https://github.com/imatge-upc/refvos"}],"syntology":null}},{"leaderboard":"/sota/referring-expression-segmentation-on-clevr","slug":"referring-expression-segmentation-on-clevr","dataset":"CLEVR-Ref+","dataset_url":"/dataset/clevr-ref","rows_in_archive":1,"metrics":["IoU"],"first_row_in_archive_order":{"model":"IEP-Ref (700K prog.)","paper_title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","paper_url":"/paper/clevr-ref-diagnosing-visual-reasoning-with","paper_date":"2019-01-03","arxiv_id":"1901.00850","code_links":[{"title":"ruotianluo/iep-ref","url":"https://github.com/ruotianluo/iep-ref"},{"title":"arjunakula/neurips2021","url":"https://github.com/arjunakula/neurips2021"},{"title":"byahn2/clevr_ref","url":"https://github.com/byahn2/clevr_ref"}],"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clevr-ref-diagnosing-visual-reasoning-with#ran","syntology_url":"https://syntology.ai/paper/1901.00850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.00850"}},"official":null}}},{"leaderboard":"/sota/referring-expression-segmentation-on-g-ref","slug":"referring-expression-segmentation-on-g-ref","dataset":"G-Ref val","dataset_url":null,"rows_in_archive":1,"metrics":["Overall IoU"],"first_row_in_archive_order":{"model":"MaIL","paper_title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","paper_url":"/paper/mail-a-unified-mask-image-language-trimodal","paper_date":"2021-11-21","arxiv_id":"2111.10747","code_links":[],"syntology":null}},{"leaderboard":"/sota/referring-expression-segmentation-on-g-ref-1","slug":"referring-expression-segmentation-on-g-ref-1","dataset":"G-Ref test A","dataset_url":null,"rows_in_archive":1,"metrics":["Overall IoU"],"first_row_in_archive_order":{"model":"MaIL","paper_title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","paper_url":"/paper/mail-a-unified-mask-image-language-trimodal","paper_date":"2021-11-21","arxiv_id":"2111.10747","code_links":[],"syntology":null}},{"leaderboard":"/sota/referring-expression-segmentation-on-g-ref-2","slug":"referring-expression-segmentation-on-g-ref-2","dataset":"G-Ref test B","dataset_url":null,"rows_in_archive":1,"metrics":["Overall IoU"],"first_row_in_archive_order":{"model":"MaIL","paper_title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","paper_url":"/paper/mail-a-unified-mask-image-language-trimodal","paper_date":"2021-11-21","arxiv_id":"2111.10747","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/refcoco","name":"RefCOCO","full_name":"","num_papers_in_archive":439},{"url":"/dataset/davis-2017","name":"DAVIS 2017","full_name":"DAVIS 2017","num_papers_in_archive":308},{"url":"/dataset/jhmdb","name":"JHMDB","full_name":"Joint-annotated Human Motion Data Base","num_papers_in_archive":249},{"url":"/dataset/referring-expressions-for-davis-2016-2017","name":"Referring Expressions for DAVIS 2016 & 2017","full_name":"","num_papers_in_archive":82},{"url":"/dataset/refer-youtube-vos","name":"Refer-YouTube-VOS","full_name":"","num_papers_in_archive":52},{"url":"/dataset/google-refexp","name":"Google Refexp","full_name":"","num_papers_in_archive":46},{"url":"/dataset/a2d-sentences","name":"A2D Sentences","full_name":"Sentences for the Actor-Action Dataset (A2D)","num_papers_in_archive":31},{"url":"/dataset/phrasecut","name":"PhraseCut","full_name":"","num_papers_in_archive":31},{"url":"/dataset/clevr-ref","name":"CLEVR-Ref+","full_name":"","num_papers_in_archive":17},{"url":"/dataset/a2d-referring-expressions","name":"A2Dre","full_name":"Subset of A2D Sentences which are not trivial","num_papers_in_archive":1},{"url":"/dataset/a2dre","name":"A2Dre+","full_name":"Extension of A2D sentences where trivial cases where filtered","num_papers_in_archive":1}],"subtasks":[{"url":"/task/generalized-referring-expression-segmentation","name":"Generalized Referring Expression Segmentation"},{"url":"/task/weakly-supervised-referring-expression","name":"Weakly Supervised Referring Expression Segmentation"}],"parent_tasks":[{"url":"/task/instance-segmentation","name":"Instance Segmentation"}],"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":145,"of_with_code":97,"tagged_in_all":145,"counts":{"archive_papers_tagged":145,"with_a_code_link":97,"where_syntology_ran_a_sample":48,"not_listed_spam_title":0,"listed":145,"listed_where_code_ran":48,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":42,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":42,"listed_every_run_a_failure_of_syntologys_instrument":6,"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/prompt-based-multi-modal-image-segmentation","slug":"prompt-based-multi-modal-image-segmentation","title":"Image Segmentation Using Text and Image Prompts","date":"2021-12-18","arxiv_id":"2112.10003","repositories_listed":6,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/prompt-based-multi-modal-image-segmentation#ran","syntology_url":"https://syntology.ai/paper/2112.10003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10003"}},"official":{"repos":["timojl/clipseg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/segmentation-from-natural-language","slug":"segmentation-from-natural-language","title":"Segmentation from Natural Language Expressions","date":"2016-03-20","arxiv_id":"1603.06180","repositories_listed":4,"syntology":null},{"url":"/paper/visionreasoner-unified-visual-perception-and","slug":"visionreasoner-unified-visual-perception-and","title":"VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning","date":"2025-05-17","arxiv_id":"2505.12081","repositories_listed":3,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/visionreasoner-unified-visual-perception-and#ran","syntology_url":"https://syntology.ai/paper/2505.12081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12081"}},"official":{"repos":["dvlab-research/VisionReasoner","hiyouga/easyr1","dvlab-research/Seg-Zero"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/seg-zero-reasoning-chain-guided-segmentation","slug":"seg-zero-reasoning-chain-guided-segmentation","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","date":"2025-03-09","arxiv_id":"2503.06520","repositories_listed":3,"syntology":null},{"url":"/paper/seqtr-a-simple-yet-universal-network-for","slug":"seqtr-a-simple-yet-universal-network-for","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","date":"2022-03-30","arxiv_id":"2203.16265","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seqtr-a-simple-yet-universal-network-for#ran","syntology_url":"https://syntology.ai/paper/2203.16265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16265"}},"official":{"repos":["sean-zhuh/seqtr"],"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/clevr-ref-diagnosing-visual-reasoning-with","slug":"clevr-ref-diagnosing-visual-reasoning-with","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","date":"2019-01-03","arxiv_id":"1901.00850","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clevr-ref-diagnosing-visual-reasoning-with#ran","syntology_url":"https://syntology.ai/paper/1901.00850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.00850"}},"official":null}},{"url":"/paper/3d-gres-generalized-3d-referring-expression","slug":"3d-gres-generalized-3d-referring-expression","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","date":"2024-07-30","arxiv_id":"2407.20664","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/3d-gres-generalized-3d-referring-expression#ran","syntology_url":"https://syntology.ai/paper/2407.20664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20664"}},"official":{"repos":["sosppxo/MDIN"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/f-lmm-grounding-frozen-large-multimodal","slug":"f-lmm-grounding-frozen-large-multimodal","title":"F-LMM: Grounding Frozen Large Multimodal Models","date":"2024-06-09","arxiv_id":"2406.05821","repositories_listed":2,"syntology":null},{"url":"/paper/hdc-hierarchical-semantic-decoding-with-1","slug":"hdc-hierarchical-semantic-decoding-with-1","title":"CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation","date":"2024-05-24","arxiv_id":"2405.15658","repositories_listed":2,"syntology":null},{"url":"/paper/uniref-segment-every-reference-object-in","slug":"uniref-segment-every-reference-object-in","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","date":"2023-12-25","arxiv_id":"2312.15715","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":2,"n_instrument":7,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniref-segment-every-reference-object-in#ran","syntology_url":"https://syntology.ai/paper/2312.15715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15715"}},"official":{"repos":["foundationvision/uniref"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/universal-segmentation-at-arbitrary","slug":"universal-segmentation-at-arbitrary","title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","date":"2023-12-04","arxiv_id":"2312.01623","repositories_listed":2,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":2,"n_instrument":12,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"14 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; 12 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/universal-segmentation-at-arbitrary#ran","syntology_url":"https://syntology.ai/paper/2312.01623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01623"}},"official":{"repos":["workforai/UniLSeg","yongliu20/UniLSeg"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/qwen-vl-a-frontier-large-vision-language","slug":"qwen-vl-a-frontier-large-vision-language","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","date":"2023-08-24","arxiv_id":"2308.12966","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/qwen-vl-a-frontier-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2308.12966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12966"}},"official":{"repos":["qwenlm/qwen-vl"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/gres-generalized-referring-expression-1","slug":"gres-generalized-referring-expression-1","title":"GRES: Generalized Referring Expression Segmentation","date":"2023-06-01","arxiv_id":"2306.00968","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/gres-generalized-referring-expression-1#ran","syntology_url":"https://syntology.ai/paper/2306.00968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00968"}},"official":{"repos":["henghuiding/ReLA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unleashing-text-to-image-diffusion-models-for-1","slug":"unleashing-text-to-image-diffusion-models-for-1","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","date":"2023-03-03","arxiv_id":"2303.02153","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unleashing-text-to-image-diffusion-models-for-1#ran","syntology_url":"https://syntology.ai/paper/2303.02153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02153"}},"official":{"repos":["wl-zhao/VPD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-referring-video-object","slug":"end-to-end-referring-video-object","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","date":"2021-11-29","arxiv_id":"2111.14821","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-referring-video-object#ran","syntology_url":"https://syntology.ai/paper/2111.14821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14821"}},"official":{"repos":["mttr2021/MTTR"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/synthref-generation-of-synthetic-referring","slug":"synthref-generation-of-synthetic-referring","title":"SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation","date":"2021-06-08","arxiv_id":"2106.04403","repositories_listed":2,"syntology":null},{"url":"/paper/refvos-a-closer-look-at-referring-expressions","slug":"refvos-a-closer-look-at-referring-expressions","title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","date":"2020-10-01","arxiv_id":"2010.00263","repositories_listed":2,"syntology":null},{"url":"/paper/multi-task-collaborative-network-for-joint","slug":"multi-task-collaborative-network-for-joint","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","date":"2020-03-19","arxiv_id":"2003.08813","repositories_listed":2,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/multi-task-collaborative-network-for-joint#ran","syntology_url":"https://syntology.ai/paper/2003.08813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.08813"}},"official":{"repos":["luogen1996/MCN"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/deris-decoupling-perception-and-cognition-for","slug":"deris-decoupling-perception-and-cognition-for","title":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy","date":"2025-07-02","arxiv_id":"2507.01738","repositories_listed":1,"syntology":null},{"url":"/paper/remotesam-towards-segment-anything-for-earth","slug":"remotesam-towards-segment-anything-for-earth","title":"RemoteSAM: Towards Segment Anything for Earth Observation","date":"2025-05-23","arxiv_id":"2505.18022","repositories_listed":1,"syntology":null},{"url":"/paper/groundingsuite-measuring-complex-multi","slug":"groundingsuite-measuring-complex-multi","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","date":"2025-03-13","arxiv_id":"2503.10596","repositories_listed":1,"syntology":null},{"url":"/paper/segagent-exploring-pixel-understanding","slug":"segagent-exploring-pixel-understanding","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","date":"2025-03-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pixfoundation-are-we-heading-in-the-right","slug":"pixfoundation-are-we-heading-in-the-right","title":"PixFoundation: Are We Heading in the Right Direction with Pixel-level Vision Foundation Models?","date":"2025-02-06","arxiv_id":"2502.04192","repositories_listed":1,"syntology":null},{"url":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","slug":"mpg-sam-2-adapting-sam-2-with-mask-priors-and","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","date":"2025-01-23","arxiv_id":"2501.13667","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and#ran","syntology_url":"https://syntology.ai/paper/2501.13667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13667"}},"official":{"repos":["rongfu-dsb/MPG-SAM2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/internvideo2-5-empowering-video-mllms-with","slug":"internvideo2-5-empowering-video-mllms-with","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","date":"2025-01-21","arxiv_id":"2501.12386","repositories_listed":1,"syntology":null},{"url":"/paper/densely-connected-parameter-efficient-tuning","slug":"densely-connected-parameter-efficient-tuning","title":"Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation","date":"2025-01-15","arxiv_id":"2501.08580","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"13 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; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/densely-connected-parameter-efficient-tuning#ran","syntology_url":"https://syntology.ai/paper/2501.08580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08580"}},"official":{"repos":["jiaqihuang01/detris"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/the-devil-is-in-temporal-token-high-quality","slug":"the-devil-is-in-temporal-token-high-quality","title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","date":"2025-01-15","arxiv_id":"2501.08549","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-visual-grounding-with-coarse-to","slug":"multi-task-visual-grounding-with-coarse-to","title":"Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints","date":"2025-01-12","arxiv_id":"2501.06710","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-task-visual-grounding-with-coarse-to#ran","syntology_url":"https://syntology.ai/paper/2501.06710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06710"}},"official":{"repos":["dmmm1997/c3vg"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ipdn-image-enhanced-prompt-decoding-network","slug":"ipdn-image-enhanced-prompt-decoding-network","title":"IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation","date":"2025-01-09","arxiv_id":"2501.04995","repositories_listed":1,"syntology":null},{"url":"/paper/rg-san-rule-guided-spatial-awareness-network","slug":"rg-san-rule-guided-spatial-awareness-network","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","date":"2024-12-03","arxiv_id":"2412.02402","repositories_listed":1,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":16,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/rg-san-rule-guided-spatial-awareness-network#ran","syntology_url":"https://syntology.ai/paper/2412.02402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02402"}},"official":{"repos":["sosppxo/rg-san"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/maskris-semantic-distortion-aware-data","slug":"maskris-semantic-distortion-aware-data","title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","date":"2024-11-28","arxiv_id":"2411.19067","repositories_listed":1,"syntology":null},{"url":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":4,"n_honours":4,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}},"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/text4seg-reimagining-image-segmentation-as","slug":"text4seg-reimagining-image-segmentation-as","title":"Text4Seg: Reimagining Image Segmentation as Text Generation","date":"2024-10-13","arxiv_id":"2410.09855","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/text4seg-reimagining-image-segmentation-as#ran","syntology_url":"https://syntology.ai/paper/2410.09855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09855"}},"official":{"repos":["mc-lan/text4seg"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/sam4mllm-enhance-multi-modal-large-language","slug":"sam4mllm-enhance-multi-modal-large-language","title":"SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation","date":"2024-09-01","arxiv_id":"2409.10542","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/sam4mllm-enhance-multi-modal-large-language#ran","syntology_url":"https://syntology.ai/paper/2409.10542","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.10542"}},"official":{"repos":["ai-application-and-integration-lab/sam4mllm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/multi-label-cluster-discrimination-for-visual","slug":"multi-label-cluster-discrimination-for-visual","title":"Multi-label Cluster Discrimination for Visual Representation Learning","date":"2024-07-24","arxiv_id":"2407.17331","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":7,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 7 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) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multi-label-cluster-discrimination-for-visual#ran","syntology_url":"https://syntology.ai/paper/2407.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17331"}},"official":{"repos":["deepglint/unicom"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/villa-video-reasoning-segmentation-with-large","slug":"villa-video-reasoning-segmentation-with-large","title":"ViLLa: Video Reasoning Segmentation with Large Language Model","date":"2024-07-18","arxiv_id":"2407.14500","repositories_listed":1,"syntology":null},{"url":"/paper/evf-sam-early-vision-language-fusion-for-text","slug":"evf-sam-early-vision-language-fusion-for-text","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","date":"2024-06-28","arxiv_id":"2406.20076","repositories_listed":1,"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/evf-sam-early-vision-language-fusion-for-text#ran","syntology_url":"https://syntology.ai/paper/2406.20076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20076"}},"official":{"repos":["hustvl/evf-sam"],"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","unlocated"]}}},{"url":"/paper/sam-as-the-guide-mastering-pseudo-label","slug":"sam-as-the-guide-mastering-pseudo-label","title":"SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation","date":"2024-06-03","arxiv_id":"2406.01451","repositories_listed":1,"syntology":null},{"url":"/paper/bring-adaptive-binding-prototypes-to","slug":"bring-adaptive-binding-prototypes-to","title":"Bring Adaptive Binding Prototypes to Generalized Referring Expression Segmentation","date":"2024-05-24","arxiv_id":"2405.15169","repositories_listed":1,"syntology":null},{"url":"/paper/improving-referring-image-segmentation-using","slug":"improving-referring-image-segmentation-using","title":"Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding","date":"2024-04-12","arxiv_id":"2404.08590","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-static-and-hierarchical-motion","slug":"decoupling-static-and-hierarchical-motion","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","date":"2024-04-04","arxiv_id":"2404.03645","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/decoupling-static-and-hierarchical-motion#ran","syntology_url":"https://syntology.ai/paper/2404.03645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03645"}},"official":{"repos":["heshuting555/dshmp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-temporally-consistent-referring-video","slug":"towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","date":"2024-03-28","arxiv_id":"2403.19407","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":1,"n_honours":1,"n_violates":3,"n_no_contract":0,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-temporally-consistent-referring-video#ran","syntology_url":"https://syntology.ai/paper/2403.19407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19407"}},"official":{"repos":["bo-miao/HTR"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/psalm-pixelwise-segmentation-with-large-multi","slug":"psalm-pixelwise-segmentation-with-large-multi","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","date":"2024-03-21","arxiv_id":"2403.14598","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"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) · 4 unverified","sample_list":"/paper/psalm-pixelwise-segmentation-with-large-multi#ran","syntology_url":"https://syntology.ai/paper/2403.14598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14598"}},"official":{"repos":["zamling/psalm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/univs-unified-and-universal-video","slug":"univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","arxiv_id":"2402.18115","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/univs-unified-and-universal-video#ran","syntology_url":"https://syntology.ai/paper/2402.18115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18115"}},"official":{"repos":["minghanli/univs"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unveiling-parts-beyond-objects-towards-finer-1","slug":"unveiling-parts-beyond-objects-towards-finer-1","title":"Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mask-grounding-for-referring-image","slug":"mask-grounding-for-referring-image","title":"Mask Grounding for Referring Image Segmentation","date":"2023-12-19","arxiv_id":"2312.12198","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":13,"phrase":"10 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; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mask-grounding-for-referring-image#ran","syntology_url":"https://syntology.ai/paper/2312.12198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12198"}},"official":{"repos":["yxchng/mask-grounding"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/gsva-generalized-segmentation-via-multimodal","slug":"gsva-generalized-segmentation-via-multimodal","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","date":"2023-12-15","arxiv_id":"2312.10103","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/gsva-generalized-segmentation-via-multimodal#ran","syntology_url":"https://syntology.ai/paper/2312.10103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10103"}},"official":{"repos":["leaplabthu/gsva"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/general-object-foundation-model-for-images","slug":"general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","arxiv_id":"2312.09158","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":3,"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/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}},"official":{"repos":["FoundationVision/GLEE"],"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/evp-enhanced-visual-perception-using-inverse","slug":"evp-enhanced-visual-perception-using-inverse","title":"EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment","date":"2023-12-13","arxiv_id":"2312.08548","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-parts-beyond-objects-towards-finer","slug":"unveiling-parts-beyond-objects-towards-finer","title":"Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression Segmentation","date":"2023-12-13","arxiv_id":"2312.08007","repositories_listed":1,"syntology":null},{"url":"/paper/next-chat-an-lmm-for-chat-detection-and","slug":"next-chat-an-lmm-for-chat-detection-and","title":"NExT-Chat: An LMM for Chat, Detection and Segmentation","date":"2023-11-08","arxiv_id":"2311.04498","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":0,"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/next-chat-an-lmm-for-chat-detection-and#ran","syntology_url":"https://syntology.ai/paper/2311.04498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04498"}},"official":{"repos":["next-chatv/next-chat"],"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/glamm-pixel-grounding-large-multimodal-model","slug":"glamm-pixel-grounding-large-multimodal-model","title":"GLaMM: Pixel Grounding Large Multimodal Model","date":"2023-11-06","arxiv_id":"2311.03356","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glamm-pixel-grounding-large-multimodal-model#ran","syntology_url":"https://syntology.ai/paper/2311.03356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03356"}},"official":{"repos":["mbzuai-oryx/groundingLMM"],"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/towards-omni-supervised-referring-expression","slug":"towards-omni-supervised-referring-expression","title":"Towards Omni-supervised Referring Expression Segmentation","date":"2023-11-01","arxiv_id":"2311.00397","repositories_listed":1,"syntology":null},{"url":"/paper/tracking-anything-with-decoupled-video","slug":"tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","arxiv_id":"2309.03903","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"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) · 3 unverified","sample_list":"/paper/tracking-anything-with-decoupled-video#ran","syntology_url":"https://syntology.ai/paper/2309.03903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03903"}},"official":{"repos":["hkchengrex/Tracking-Anything-with-DEVA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/3d-stmn-dependency-driven-superpoint-text","slug":"3d-stmn-dependency-driven-superpoint-text","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","date":"2023-08-31","arxiv_id":"2308.16632","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/3d-stmn-dependency-driven-superpoint-text#ran","syntology_url":"https://syntology.ai/paper/2308.16632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16632"}},"official":{"repos":["sosppxo/3d-stmn"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/referring-image-segmentation-using-text","slug":"referring-image-segmentation-using-text","title":"Referring Image Segmentation Using Text Supervision","date":"2023-08-28","arxiv_id":"2308.14575","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/referring-image-segmentation-using-text#ran","syntology_url":"https://syntology.ai/paper/2308.14575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14575"}},"official":{"repos":["fawnliu/tris"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/spectrum-guided-multi-granularity-referring","slug":"spectrum-guided-multi-granularity-referring","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","date":"2023-07-25","arxiv_id":"2307.13537","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/spectrum-guided-multi-granularity-referring#ran","syntology_url":"https://syntology.ai/paper/2307.13537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13537"}},"official":{"repos":["bo-miao/sgmg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-vision-and-language-encoders","slug":"bridging-vision-and-language-encoders","title":"Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation","date":"2023-07-21","arxiv_id":"2307.11545","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/bridging-vision-and-language-encoders#ran","syntology_url":"https://syntology.ai/paper/2307.11545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11545"}},"official":{"repos":["kkakkkka/etris"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/onlinerefer-a-simple-online-baseline-for","slug":"onlinerefer-a-simple-online-baseline-for","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","date":"2023-07-18","arxiv_id":"2307.09356","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/onlinerefer-a-simple-online-baseline-for#ran","syntology_url":"https://syntology.ai/paper/2307.09356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09356"}},"official":{"repos":["wudongming97/onlinerefer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-open-vocabulary-universal-image-1","slug":"hierarchical-open-vocabulary-universal-image-1","title":"Hierarchical Open-vocabulary Universal Image Segmentation","date":"2023-07-03","arxiv_id":"2307.00764","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/hierarchical-open-vocabulary-universal-image-1#ran","syntology_url":"https://syntology.ai/paper/2307.00764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.00764"}},"official":{"repos":["berkeley-hipie/hipie"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/shikra-unleashing-multimodal-llm-s","slug":"shikra-unleashing-multimodal-llm-s","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","date":"2023-06-27","arxiv_id":"2306.15195","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/shikra-unleashing-multimodal-llm-s#ran","syntology_url":"https://syntology.ai/paper/2306.15195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15195"}},"official":{"repos":["shikras/shikra"],"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/losh-long-short-text-joint-prediction-network","slug":"losh-long-short-text-joint-prediction-network","title":"LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation","date":"2023-06-14","arxiv_id":"2306.08736","repositories_listed":1,"syntology":null},{"url":"/paper/soc-semantic-assisted-object-cluster-for","slug":"soc-semantic-assisted-object-cluster-for","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","date":"2023-05-26","arxiv_id":"2305.17011","repositories_listed":1,"syntology":null},{"url":"/paper/referred-by-multi-modality-a-unified-temporal","slug":"referred-by-multi-modality-a-unified-temporal","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","date":"2023-05-25","arxiv_id":"2305.16318","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-referring-expression-segmentation","slug":"advancing-referring-expression-segmentation","title":"Advancing Referring Expression Segmentation Beyond Single Image","date":"2023-05-21","arxiv_id":"2305.12452","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-referring-image-segmentation-with","slug":"zero-shot-referring-image-segmentation-with","title":"Zero-shot Referring Image Segmentation with Global-Local Context Features","date":"2023-03-31","arxiv_id":"2303.17811","repositories_listed":1,"syntology":null},{"url":"/paper/universal-instance-perception-as-object","slug":"universal-instance-perception-as-object","title":"Universal Instance Perception as Object Discovery and Retrieval","date":"2023-03-12","arxiv_id":"2303.06674","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/universal-instance-perception-as-object#ran","syntology_url":"https://syntology.ai/paper/2303.06674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06674"}},"official":{"repos":["MasterBin-IIAU/UNINEXT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/polyformer-referring-image-segmentation-as","slug":"polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","arxiv_id":"2302.07387","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/polyformer-referring-image-segmentation-as#ran","syntology_url":"https://syntology.ai/paper/2302.07387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07387"}},"official":{"repos":["amazon-science/polygon-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-segment-every-referring-object","slug":"learning-to-segment-every-referring-object","title":"Learning To Segment Every Referring Object Point by Point","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generalized-decoding-for-pixel-image-and","slug":"generalized-decoding-for-pixel-image-and","title":"Generalized Decoding for Pixel, Image, and Language","date":"2022-12-21","arxiv_id":"2212.11270","repositories_listed":1,"syntology":null},{"url":"/paper/vlt-vision-language-transformer-and-query","slug":"vlt-vision-language-transformer-and-query","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2022-10-28","arxiv_id":"2210.15871","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vlt-vision-language-transformer-and-query#ran","syntology_url":"https://syntology.ai/paper/2210.15871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15871"}},"official":{"repos":["henghuiding/Vision-Language-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-modulated-detection-transformer-as","slug":"exploring-modulated-detection-transformer-as","title":"Exploring Modulated Detection Transformer as a Tool for Action Recognition in Videos","date":"2022-09-21","arxiv_id":"2209.10126","repositories_listed":1,"syntology":null},{"url":"/paper/multi-attention-network-for-compressed-video","slug":"multi-attention-network-for-compressed-video","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","date":"2022-07-26","arxiv_id":"2207.12622","repositories_listed":1,"syntology":null},{"url":"/paper/r-2vos-robust-referring-video-object","slug":"r-2vos-robust-referring-video-object","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","date":"2022-07-04","arxiv_id":"2207.01203","repositories_listed":1,"syntology":null},{"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/modeling-motion-with-multi-modal-features-for","slug":"modeling-motion-with-multi-modal-features-for","title":"Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation","date":"2022-04-06","arxiv_id":"2204.02547","repositories_listed":1,"syntology":null},{"url":"/paper/local-global-context-aware-transformer-for","slug":"local-global-context-aware-transformer-for","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","date":"2022-03-18","arxiv_id":"2203.09773","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/local-global-context-aware-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2203.09773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09773"}},"official":{"repos":["leonnnop/locater"],"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/language-as-queries-for-referring-video","slug":"language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","arxiv_id":"2201.00487","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-as-queries-for-referring-video#ran","syntology_url":"https://syntology.ai/paper/2201.00487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00487"}},"official":{"repos":["wjn922/referformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lavt-language-aware-vision-transformer-for","slug":"lavt-language-aware-vision-transformer-for","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","date":"2021-12-04","arxiv_id":"2112.02244","repositories_listed":1,"syntology":null},{"url":"/paper/cris-clip-driven-referring-image-segmentation","slug":"cris-clip-driven-referring-image-segmentation","title":"CRIS: CLIP-Driven Referring Image Segmentation","date":"2021-11-30","arxiv_id":"2111.15174","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"8 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; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cris-clip-driven-referring-image-segmentation#ran","syntology_url":"https://syntology.ai/paper/2111.15174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15174"}},"official":{"repos":["DerrickWang005/CRIS.pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-grained-vision-language-pre-training","slug":"multi-grained-vision-language-pre-training","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","date":"2021-11-16","arxiv_id":"2111.08276","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-grained-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2111.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08276"}},"official":{"repos":["zengyan-97/x-vlm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-transformer-and-query","slug":"vision-language-transformer-and-query","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2021-08-12","arxiv_id":"2108.05565","repositories_listed":1,"syntology":null},{"url":"/paper/referring-transformer-a-one-step-approach-to","slug":"referring-transformer-a-one-step-approach-to","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","date":"2021-06-06","arxiv_id":"2106.03089","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/referring-transformer-a-one-step-approach-to#ran","syntology_url":"https://syntology.ai/paper/2106.03089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03089"}},"official":{"repos":["ubc-vision/RefTR"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-progressive-comprehension-for","slug":"cross-modal-progressive-comprehension-for","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","date":"2021-05-15","arxiv_id":"2105.07175","repositories_listed":1,"syntology":null},{"url":"/paper/comprehensive-multi-modal-interactions-for","slug":"comprehensive-multi-modal-interactions-for","title":"Comprehensive Multi-Modal Interactions for Referring Image Segmentation","date":"2021-04-21","arxiv_id":"2104.10412","repositories_listed":1,"syntology":null},{"url":"/paper/ocid-ref-a-3d-robotic-dataset-with-embodied","slug":"ocid-ref-a-3d-robotic-dataset-with-embodied","title":"OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding","date":"2021-03-13","arxiv_id":"2103.07679","repositories_listed":1,"syntology":null},{"url":"/paper/referring-image-segmentation-via-cross-modal-1","slug":"referring-image-segmentation-via-cross-modal-1","title":"Referring Image Segmentation via Cross-Modal Progressive Comprehension","date":"2020-10-01","arxiv_id":"2010.00514","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/referring-image-segmentation-via-cross-modal-1#ran","syntology_url":"https://syntology.ai/paper/2010.00514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.00514"}},"official":{"repos":["spyflying/CMPC-Refseg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/phrasecut-language-based-image-segmentation-1","slug":"phrasecut-language-based-image-segmentation-1","title":"PhraseCut: Language-based Image Segmentation in the Wild","date":"2020-08-03","arxiv_id":"2008.01187","repositories_listed":1,"syntology":null},{"url":"/paper/urvos-unified-referring-video-object","slug":"urvos-unified-referring-video-object","title":"URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bilingunet-image-segmentation-by-modulating","slug":"bilingunet-image-segmentation-by-modulating","title":"Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters","date":"2020-03-28","arxiv_id":"2003.12739","repositories_listed":1,"syntology":null},{"url":"/paper/referring-expression-object-segmentation-with","slug":"referring-expression-object-segmentation-with","title":"Referring Expression Object Segmentation with Caption-Aware Consistency","date":"2019-10-10","arxiv_id":"1910.04748","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/referring-expression-object-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/1910.04748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04748"}},"official":{"repos":["wenz116/lang2seg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/asymmetric-cross-guided-attention-network-for","slug":"asymmetric-cross-guided-attention-network-for","title":"Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query","date":"2019-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-self-attention-network-for","slug":"cross-modal-self-attention-network-for","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","date":"2019-04-09","arxiv_id":"1904.04745","repositories_listed":1,"syntology":null},{"url":"/paper/referring-image-segmentation-via-recurrent","slug":"referring-image-segmentation-via-recurrent","title":"Referring Image Segmentation via Recurrent Refinement Networks","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/actor-and-action-video-segmentation-from-a","slug":"actor-and-action-video-segmentation-from-a","title":"Actor and Action Video Segmentation from a Sentence","date":"2018-03-20","arxiv_id":"1803.07485","repositories_listed":1,"syntology":null},{"url":"/paper/mattnet-modular-attention-network-for","slug":"mattnet-modular-attention-network-for","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","date":"2018-01-24","arxiv_id":"1801.08186","repositories_listed":1,"syntology":null},{"url":null,"slug":"mask-aware-text-to-image-retrieval-referring","title":"Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval","date":"2025-06-28","arxiv_id":"2506.22864","repositories_listed":0,"syntology":null},{"url":null,"slug":"refer-to-anything-with-vision-language","title":"Refer to Anything with Vision-Language Prompts","date":"2025-06-05","arxiv_id":"2506.05342","repositories_listed":0,"syntology":null},{"url":null,"slug":"resanything-attribute-prompting-for-arbitrary","title":"RESAnything: Attribute Prompting for Arbitrary Referring Segmentation","date":"2025-05-03","arxiv_id":"2505.02867","repositories_listed":0,"syntology":null}],"syntology_records":50,"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":7,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","since_archive":"/sota/referring-expression-segmentation-on-refcoco#since-judged","papers_judged":7,"placed":0},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-4","since_archive":"/sota/referring-expression-segmentation-on-refcoco-4#since-judged","papers_judged":5,"placed":0},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-5","since_archive":"/sota/referring-expression-segmentation-on-refcoco-5#since-judged","papers_judged":5,"placed":0},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog","since_archive":"/sota/referring-expression-segmentation-on-refcocog#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-8","since_archive":"/sota/referring-expression-segmentation-on-refcoco-8#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-9","since_archive":"/sota/referring-expression-segmentation-on-refcoco-9#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-6","since_archive":"/sota/referring-expression-segmentation-on-refcoco-6#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":48,"papers_where_code_ran_first_page":"/task/referring-expression-segmentation/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/referring-expression-segmentation/papers/2","json":"/task/referring-expression-segmentation/papers/2.json","rows":45},{"order":"ran","page":1,"of":1,"url":"/task/referring-expression-segmentation/papers/ran/1","json":"/task/referring-expression-segmentation/papers/ran/1.json","rows":48}],"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":"e958bf9bb6df88591da7bb97b599ae7b54f5c23d4a5b8b851f56cccdb95102a4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}