{"url":"/sota/referring-expression-segmentation-on-refer-1","task":{"name":"Referring Expression Segmentation","url":"/task/referring-expression-segmentation","note":null},"dataset":{"name":"Refer-YouTube-VOS (2021 public validation)","url":"/dataset/refer-youtube-vos"},"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":["J&F","J","F"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"J&F":null,"J":null,"F":null}},"counts":{"rows":33,"rows_with_code":26,"rows_with_paper_page":33,"rows_dated":32,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"MPG-SAM 2","metrics":{"F":"76.1","J":"71.7","J&F":"73.9"},"uses_additional_data":false,"paper_date":"2025-01-23","paper":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","paper_url":"https://arxiv.org/abs/2501.13667v1","paper_title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","code":"https://github.com/rongfu-dsb/MPG-SAM2","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":11,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"VRS-HQ (Chat-UniVi-13B)","metrics":{"F":"73.1","J":"69","J&F":"71"},"uses_additional_data":false,"paper_date":"2025-01-15","paper":"/paper/the-devil-is-in-temporal-token-high-quality","paper_url":"https://arxiv.org/abs/2501.08549v1","paper_title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","code":"https://github.com/sitonggong/vrs-hq","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"GLEE-Pro","metrics":{"F":"72.9","J":"68.2","J&F":"70.6"},"uses_additional_data":true,"paper_date":"2023-12-14","paper":"/paper/general-object-foundation-model-for-images","paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","code":"https://github.com/FoundationVision/GLEE","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"UNINEXT-H","metrics":{"F":"72.7","J":"67.6","J&F":"70.1"},"uses_additional_data":false,"paper_date":"2023-03-12","paper":"/paper/universal-instance-perception-as-object","paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","code":"https://github.com/MasterBin-IIAU/UNINEXT","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"ReferDINO (Swin-B)","metrics":{"F":"71.5 ","J":"67.0","J&F":"69.3"},"uses_additional_data":false,"paper_date":"2025-01-24","paper":"/paper/referdino-referring-video-object-segmentation","paper_url":"https://arxiv.org/abs/2501.14607v1","paper_title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"MUTR","metrics":{"F":"70.4","J":"66.4","J&F":"68.4"},"uses_additional_data":false,"paper_date":"2023-05-25","paper":"/paper/referred-by-multi-modality-a-unified-temporal","paper_url":"https://arxiv.org/abs/2305.16318v2","paper_title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","code":"https://github.com/opengvlab/mutr","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"VLP (VLMo-L)","metrics":{"F":"69.8 ","J":"65.3 ","J&F":"67.6 "},"uses_additional_data":false,"paper_date":"2024-05-17","paper":"/paper/driving-referring-video-object-segmentation","paper_url":"https://arxiv.org/abs/2405.10610v2","paper_title":"Harnessing Vision-Language Pretrained Models with Temporal-Aware Adaptation for Referring Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"UniRef-L (Swin-L)","metrics":{"F":"69.2","J":"65.5","J&F":"67.4"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/segment-every-reference-object-in-spatial-and","paper_url":"http://openaccess.thecvf.com//content/ICCV2023/html/Wu_Segment_Every_Reference_Object_in_Spatial_and_Temporal_Spaces_ICCV_2023_paper.html","paper_title":"Segment Every Reference Object in Spatial and Temporal Spaces","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"SOC (Joint training, Video-Swin-B)","metrics":{"F":"69.3","J":"65.3","J&F":"67.3±0.5"},"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":10,"model":"HTR (Pre-training)","metrics":{"F":"68.9","J":"65.3","J&F":"67.1"},"uses_additional_data":false,"paper_date":"2024-03-28","paper":"/paper/towards-temporally-consistent-referring-video","paper_url":"https://arxiv.org/abs/2403.19407v2","paper_title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","code":"https://github.com/bo-miao/HTR","n_code_links":1,"syntology":{"n_ran":14,"n_unverified":1,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"DsHmp (Video-Swin-Base)","metrics":{"F":"69.1","J":"65","J&F":"67.1"},"uses_additional_data":false,"paper_date":"2024-04-04","paper":"/paper/decoupling-static-and-hierarchical-motion","paper_url":"https://arxiv.org/abs/2404.03645v1","paper_title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","code":"https://github.com/heshuting555/dshmp","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":12,"model":"UniRef++-L","metrics":{"F":"69.0","J":"64.8","J&F":"66.9"},"uses_additional_data":false,"paper_date":"2023-12-25","paper":"/paper/uniref-segment-every-reference-object-in","paper_url":"https://arxiv.org/abs/2312.15715v1","paper_title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","code":"https://github.com/foundationvision/uniref","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"ViLLa","metrics":{"F":"68.6","J":"64.6","J&F":"66.5"},"uses_additional_data":false,"paper_date":"2024-07-18","paper":"/paper/villa-video-reasoning-segmentation-with-large","paper_url":"https://arxiv.org/abs/2407.14500v2","paper_title":"ViLLa: Video Reasoning Segmentation with Large Language Model","code":"https://github.com/rkzheng99/villa","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"DEVA (ReferFormer)","metrics":{"J&F":"66.0"},"uses_additional_data":true,"paper_date":"2023-09-07","paper":"/paper/tracking-anything-with-decoupled-video","paper_url":"https://arxiv.org/abs/2309.03903v1","paper_title":"Tracking Anything with Decoupled Video Segmentation","code":"https://github.com/hkchengrex/Tracking-Anything-with-DEVA","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":15,"model":"SgMg (Pre-training)","metrics":{"F":"67.4","J":"63.9","J&F":"65.7"},"uses_additional_data":false,"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":16,"model":"GroPrompt","metrics":{"F":"66.9","J":"64.1","J&F":"65.5"},"uses_additional_data":false,"paper_date":"2024-06-18","paper":"/paper/groprompt-efficient-grounded-prompting-and","paper_url":"https://arxiv.org/abs/2406.12834v2","paper_title":"GroPrompt: Efficient Grounded Prompting and Adaptation for Referring Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"EPCFormer (ViT-H)","metrics":{"F":"67.2","J":"62.9","J&F":"65"},"uses_additional_data":false,"paper_date":"2023-08-08","paper":"/paper/epcformer-expression-prompt-collaboration","paper_url":"https://arxiv.org/abs/2308.04162v2","paper_title":"Expression Prompt Collaboration Transformer for Universal Referring Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"UniLSeg-100","metrics":{"F":"67.0","J":"62.8","J&F":"64.9"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/universal-segmentation-at-arbitrary","paper_url":"https://arxiv.org/abs/2312.01623v4","paper_title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","code":"https://github.com/yongliu20/UniLSeg","n_code_links":2,"syntology":{"n_ran":13,"n_unverified":3,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"LoSh-R","metrics":{"F":"66.0","J":"62.5","J&F":"64.2"},"uses_additional_data":true,"paper_date":"2023-06-14","paper":"/paper/losh-long-short-text-joint-prediction-network","paper_url":"https://arxiv.org/abs/2306.08736v3","paper_title":"LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation","code":"https://github.com/linfengyuan1997/losh","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"VLT","metrics":{"F":"65.6","J":"61.9","J&F":"63.8"},"uses_additional_data":false,"paper_date":"2022-10-28","paper":"/paper/vlt-vision-language-transformer-and-query","paper_url":"https://arxiv.org/abs/2210.15871v1","paper_title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","code":"https://github.com/henghuiding/Vision-Language-Transformer","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"OnlineRefer (Swin-L, online)","metrics":{"F":"65.5","J":"61.6","J&F":"63.5"},"uses_additional_data":false,"paper_date":"2023-07-18","paper":"/paper/onlinerefer-a-simple-online-baseline-for","paper_url":"https://arxiv.org/abs/2307.09356v1","paper_title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","code":"https://github.com/wudongming97/onlinerefer","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"R2VOS (Video-Swin-T)","metrics":{"F":"63.1","J":"59.6","J&F":"61.3"},"uses_additional_data":true,"paper_date":"2022-07-04","paper":"/paper/r-2vos-robust-referring-video-object","paper_url":"https://arxiv.org/abs/2207.01203v3","paper_title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","code":"https://github.com/lxa9867/R2VOS","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"SOC (Video-Swin-T)","metrics":{"F":"60.5","J":"57.8","J&F":"59.2"},"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":24,"model":"UniVS(Swin-L)","metrics":{"F":"59.5","J":"56.8","J&F":"58.0"},"uses_additional_data":true,"paper_date":"2024-02-28","paper":"/paper/univs-unified-and-universal-video","paper_url":"https://arxiv.org/abs/2402.18115v2","paper_title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","code":"https://github.com/minghanli/univs","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":2,"n_samples":14,"n_pointer_only_licence":14}},{"rank_in_archive_order":25,"model":"ReferFormer (ResNet-101)","metrics":{"F":"58.4","J":"56.1","J&F":"57.3"},"uses_additional_data":true,"paper_date":"2022-01-03","paper":"/paper/language-as-queries-for-referring-video","paper_url":"https://arxiv.org/abs/2201.00487v2","paper_title":"Language as Queries for Referring Video Object Segmentation","code":"https://github.com/wjn922/referformer","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":26,"model":"MANET","metrics":{"F":"56.51","J":"54.75","J&F":"55.63"},"uses_additional_data":false,"paper_date":"2022-07-26","paper":"/paper/multi-attention-network-for-compressed-video","paper_url":"https://arxiv.org/abs/2207.12622v1","paper_title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","code":"https://github.com/dexianghong/manet","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"ReferFormer (ResNet-50)","metrics":{"F":"56.6","J":"54.8","J&F":"55.6"},"uses_additional_data":true,"paper_date":"2022-01-03","paper":"/paper/language-as-queries-for-referring-video","paper_url":"https://arxiv.org/abs/2201.00487v2","paper_title":"Language as Queries for Referring Video Object Segmentation","code":"https://github.com/wjn922/referformer","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":28,"model":"MTTR (w=12)","metrics":{"F":"56.64","J":"54.00","J&F":"55.32"},"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":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"Locater","metrics":{"F":"51.1","J":"48.8","J&F":"50"},"uses_additional_data":false,"paper_date":"2022-03-18","paper":"/paper/local-global-context-aware-transformer-for","paper_url":"https://arxiv.org/abs/2203.09773v2","paper_title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","code":"https://github.com/leonnnop/locater","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"MLRLSA","metrics":{"F":"48.43","J":"50.96","J&F":"49.70"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/multi-level-representation-learning-with","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Wu_Multi-Level_Representation_Learning_With_Semantic_Alignment_for_Referring_Video_Object_CVPR_2022_paper.html","paper_title":"Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"VLIDE","metrics":{"F":"50.67","J":"48.44","J&F":"49.56"},"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":32,"model":"URVOS","metrics":{"F":"50.8","J":"47.0","J&F":"48.9"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/urvos-unified-referring-video-object","paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2327_ECCV_2020_paper.php","paper_title":"URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark","code":"https://github.com/skynbe/Refer-Youtube-VOS","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"InternVideo2.5","metrics":{"J&F":"34.2"},"uses_additional_data":false,"paper_date":"2025-01-21","paper":"/paper/internvideo2-5-empowering-video-mllms-with","paper_url":"https://arxiv.org/abs/2501.12386v2","paper_title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","code":"https://github.com/opengvlab/internvideo","n_code_links":1,"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 6,795 of the 9,581 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":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+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":16,"rows_with_any_sample_ran":15,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":14,"samples_over_distinct_papers":{"n_ran":99,"n_unverified":47,"n_samples":146,"n_pointer_only_licence":48,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":106,"n_unverified":48,"n_samples":154,"n_pointer_only_licence":56,"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"}}}