{"url":"/sota/referring-expression-segmentation-on-j-hmdb","task":{"name":"Referring Expression Segmentation","url":"/task/referring-expression-segmentation","note":null},"dataset":{"name":"J-HMDB","url":"/dataset/jhmdb"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"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.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["AP","IoU overall","IoU mean","Precision@0.5","Precision@0.6","Precision@0.7","Precision@0.8","Precision@0.9"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AP":"higher","IoU overall":"higher","IoU mean":"higher","Precision@0.5":"higher","Precision@0.6":"higher","Precision@0.7":"higher","Precision@0.8":"higher","Precision@0.9":"higher"}},"counts":{"rows":21,"rows_with_code":10,"rows_with_paper_page":21,"rows_dated":21,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"SgMg (Video-Swin-B)","metrics":{"AP":"0.450","IoU mean":"0.725","IoU overall":"0.737","Precision@0.5":"0.972","Precision@0.6":"0.917","Precision@0.7":"0.714","Precision@0.8":"0.225","Precision@0.9":"0.003"},"uses_additional_data":true,"paper_date":"2023-07-25","paper":"/paper/spectrum-guided-multi-granularity-referring","paper_url":"https://arxiv.org/abs/2307.13537v1","paper_title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","code":"https://github.com/bo-miao/sgmg","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":2,"model":"SOC (Video-Swin-B)","metrics":{"AP":"0.446","IoU mean":"0.723","IoU overall":"0.736","Precision@0.5":"0.969","Precision@0.6":"0.914","Precision@0.7":"0.711","Precision@0.8":"0.213","Precision@0.9":"0.001"},"uses_additional_data":true,"paper_date":"2023-05-26","paper":"/paper/soc-semantic-assisted-object-cluster-for","paper_url":"https://arxiv.org/abs/2305.17011v1","paper_title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","code":"https://github.com/RobertLuo1/NeurIPS2023_SOC","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"VLIDE","metrics":{"AP":"0.441","IoU mean":"0.666","IoU overall":"0.68","Precision@0.5":"0.874","Precision@0.6":"0.791","Precision@0.7":"0.586","Precision@0.8":"0.182","Precision@0.9":"0.30"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/deeply-interleaved-two-stream-encoder-for","paper_url":"https://arxiv.org/abs/2203.15969v1","paper_title":"Deeply Interleaved Two-Stream Encoder for Referring Video Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"SOC (Video-Swin-T)","metrics":{"AP":"0.397","IoU mean":"0.701","IoU overall":"0.707","Precision@0.5":"0.947","Precision@0.6":"0.864","Precision@0.7":"0.627","Precision@0.8":"0.179","Precision@0.9":"0.001"},"uses_additional_data":false,"paper_date":"2023-05-26","paper":"/paper/soc-semantic-assisted-object-cluster-for","paper_url":"https://arxiv.org/abs/2305.17011v1","paper_title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","code":"https://github.com/RobertLuo1/NeurIPS2023_SOC","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"MTTR (w=10)","metrics":{"AP":"0.392","IoU mean":"0.698","IoU overall":"0.701","Precision@0.5":"0.939","Precision@0.6":"0.852","Precision@0.7":"0.616","Precision@0.8":"0.166","Precision@0.9":"0.001"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/end-to-end-referring-video-object","paper_url":"https://arxiv.org/abs/2111.14821v2","paper_title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","code":"https://github.com/mttr2021/MTTR","n_code_links":2,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"MTTR (w=8)","metrics":{"AP":"0.366","IoU mean":"0.679","IoU overall":"0.674","Precision@0.5":"0.91","Precision@0.6":"0.815","Precision@0.7":"0.57","Precision@0.8":"0.144","Precision@0.9":"0.001"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/end-to-end-referring-video-object","paper_url":"https://arxiv.org/abs/2111.14821v2","paper_title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","code":"https://github.com/mttr2021/MTTR","n_code_links":2,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"CMPC-V","metrics":{"AP":"0.342","IoU mean":"0.617","IoU overall":"0.616","Precision@0.5":"0.813","Precision@0.6":"0.657","Precision@0.7":"0.371","Precision@0.8":"0.07","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2021-05-15","paper":"/paper/cross-modal-progressive-comprehension-for","paper_url":"https://arxiv.org/abs/2105.07175v1","paper_title":"Cross-Modal Progressive Comprehension for Referring Segmentation","code":"https://github.com/spyflying/CMPC-Refseg","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"Hui et al.","metrics":{"AP":"0.335","IoU mean":"0.604","IoU overall":"0.598","Precision@0.5":"0.783","Precision@0.6":"0.639","Precision@0.7":"0.378","Precision@0.8":"0.076","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2021-05-14","paper":"/paper/collaborative-spatial-temporal-modeling-for","paper_url":"https://arxiv.org/abs/2105.06818v1","paper_title":"Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"AAMN","metrics":{"AP":"0.321","IoU mean":"0.576","IoU overall":"0.583","Precision@0.5":"0.773","Precision@0.6":"0.627","Precision@0.7":"0.360","Precision@0.8":"0.044","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2020-11-02","paper":"/paper/actor-and-action-modular-network-for-text","paper_url":"https://arxiv.org/abs/2011.00786v2","paper_title":"Actor and Action Modular Network for Text-based Video Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"CMDy","metrics":{"AP":"0.301","IoU mean":"0.576","IoU overall":"0.554","Precision@0.5":"0.742","Precision@0.6":"0.587","Precision@0.7":"0.316","Precision@0.8":"0.047","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2020-04-03","paper":"/paper/context-modulated-dynamic-networks-for-actor","paper_url":"https://ojs.aaai.org//index.php/AAAI/article/view/6895","paper_title":"Context Modulated Dynamic Networks for Actor and Action Video Segmentation with Language Queries","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"PRPE","metrics":{"AP":"0.294","Precision@0.5":"0.572","Precision@0.6":"0.690","Precision@0.7":"0.319","Precision@0.8":"0.06","Precision@0.9":"0.001"},"uses_additional_data":false,"paper_date":"2020-07-20","paper":"/paper/polar-relative-positional-encoding-for-video","paper_url":"https://www.ijcai.org/proceedings/2020/132","paper_title":"Polar Relative Positional Encoding for Video-Language Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"ACGA","metrics":{"AP":"0.289","IoU mean":"0.584","IoU overall":"0.576","Precision@0.5":"0.756","Precision@0.6":"0.564","Precision@0.7":"0.287","Precision@0.8":"0.034","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/asymmetric-cross-guided-attention-network-for","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Asymmetric_Cross-Guided_Attention_Network_for_Actor_and_Action_Video_Segmentation_ICCV_2019_paper.html","paper_title":"Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query","code":"https://github.com/haowang1992/ACGA","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Gavrilyuk et al. (Optical flow)","metrics":{"AP":"0.267","IoU mean":"0.570","IoU overall":"0.555","Precision@0.5":"0.712","Precision@0.6":"0.518","Precision@0.7":"0.264","Precision@0.8":"0.030","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2018-03-20","paper":"/paper/actor-and-action-video-segmentation-from-a","paper_url":"http://arxiv.org/abs/1803.07485v1","paper_title":"Actor and Action Video Segmentation from a Sentence","code":"https://github.com/JerryX1110/awesome-rvos","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"VT-Capsule","metrics":{"AP":"0.261","IoU mean":"0.550","IoU overall":"0.535","Precision@0.5":"0.677","Precision@0.6":"0.513","Precision@0.7":"0.283","Precision@0.8":"0.051","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/visual-textual-capsule-routing-for-text-based","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/McIntosh_Visual-Textual_Capsule_Routing_for_Text-Based_Video_Segmentation_CVPR_2020_paper.html","paper_title":"Visual-Textual Capsule Routing for Text-Based Video Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"Gavrilyuk et al.","metrics":{"AP":"0.233","IoU mean":"0.542","IoU overall":"0.541","Precision@0.5":"0.699","Precision@0.6":"0.460","Precision@0.7":"0.173","Precision@0.8":"0.014","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2018-03-20","paper":"/paper/actor-and-action-video-segmentation-from-a","paper_url":"http://arxiv.org/abs/1803.07485v1","paper_title":"Actor and Action Video Segmentation from a Sentence","code":"https://github.com/JerryX1110/awesome-rvos","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Hu et al.","metrics":{"AP":"0.178","IoU mean":"0.528","IoU overall":"0.546","Precision@0.5":"0.633","Precision@0.6":"0.350","Precision@0.7":"0.085","Precision@0.8":"0.002","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2016-03-20","paper":"/paper/segmentation-from-natural-language","paper_url":"http://arxiv.org/abs/1603.06180v1","paper_title":"Segmentation from Natural Language Expressions","code":"https://github.com/ronghanghu/text_objseg","n_code_links":4,"syntology":null},{"rank_in_archive_order":17,"model":"Li et al.","metrics":{"AP":"0.173","IoU mean":"0.491","IoU overall":"0.529","Precision@0.5":"0.578","Precision@0.6":"0.335","Precision@0.7":"0.103","Precision@0.8":"0.060","Precision@0.9":"0.000"},"uses_additional_data":false,"paper_date":"2017-07-01","paper":"/paper/tracking-by-natural-language-specification","paper_url":"http://openaccess.thecvf.com/content_cvpr_2017/html/Li_Tracking_by_Natural_CVPR_2017_paper.html","paper_title":"Tracking by Natural Language Specification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"HINet","metrics":{"IoU mean":"0.627","IoU overall":"0.652","Precision@0.5":"0.819","Precision@0.6":"0.736","Precision@0.7":"0.542","Precision@0.8":"0.168","Precision@0.9":"0.4"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/hierarchical-interaction-network-for-video","paper_url":"https://www.bmvc2021-virtualconference.com/conference/papers/paper_0386.html","paper_title":"Hierarchical interaction network for video object segmentation from referring expressions","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"ClawCraneNet","metrics":{"IoU mean":"0.655","IoU overall":"0.644","Precision@0.5":"0.880","Precision@0.6":"0.796","Precision@0.7":"0.566","Precision@0.8":"0.147","Precision@0.9":"0.002"},"uses_additional_data":false,"paper_date":"2021-03-19","paper":"/paper/clawcranenet-leveraging-object-level-relation","paper_url":"https://arxiv.org/abs/2103.10702v4","paper_title":"ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"CMSA+CFSA","metrics":{"IoU mean":"0.581","IoU overall":"0.628","Precision@0.5":"0.764","Precision@0.6":"0.625","Precision@0.7":"0.389","Precision@0.8":"0.09","Precision@0.9":"0.001"},"uses_additional_data":false,"paper_date":"2021-02-09","paper":"/paper/referring-segmentation-in-images-and-videos","paper_url":"https://arxiv.org/abs/2102.04762v1","paper_title":"Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"RefVOS","metrics":{"IoU mean":"0.568","IoU overall":"0.606","Precision@0.5":"0.731","Precision@0.6":"0.62","Precision@0.7":"0.392","Precision@0.8":"0.088","Precision@0.9":"0.0"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/hierarchical-interaction-network-for-video","paper_url":"https://www.bmvc2021-virtualconference.com/conference/papers/paper_0386.html","paper_title":"Hierarchical interaction network for video object segmentation from referring expressions","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":14,"n_unverified":6,"n_samples":20,"n_pointer_only_licence":9,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":22,"n_unverified":9,"n_samples":31,"n_pointer_only_licence":9,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}