{"url":"/sota/video-object-segmentation-on-youtube-vos","task":{"name":"Semi-Supervised Video Object Segmentation","url":"/task/semi-supervised-video-object-segmentation","note":null},"dataset":{"name":"YouTube-VOS 2018","url":"/dataset/youtube-vos"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The semi-supervised scenario assumes the user inputs a full mask of the object(s) of interest in the first frame of a video sequence. Methods have to produce the segmentation mask for that object(s) in the subsequent frames.","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":["Overall","Jaccard (Seen)","Jaccard (Unseen)","F-Measure (Seen)","F-Measure (Unseen)","Speed  (FPS)","Params(M)","Speed (FPS)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Overall":null,"Jaccard (Seen)":null,"Jaccard (Unseen)":null,"F-Measure (Seen)":null,"F-Measure (Unseen)":null,"Speed  (FPS)":null,"Params(M)":"lower","Speed (FPS)":null}},"counts":{"rows":53,"rows_with_code":52,"rows_with_paper_page":53,"rows_dated":53,"rows_using_additional_data":14},"rows":[{"rank_in_archive_order":1,"model":"Cutie+ (base, MEGA)","metrics":{"F-Measure (Seen)":"91.0","F-Measure (Unseen)":"90.1","Jaccard (Seen)":"86.6","Jaccard (Unseen)":"82.2","Overall":"87.5","Speed (FPS)":"17.9"},"uses_additional_data":true,"paper_date":"2023-10-19","paper":"/paper/putting-the-object-back-into-video-object","paper_url":"https://arxiv.org/abs/2310.12982v2","paper_title":"Putting the Object Back into Video Object Segmentation","code":"https://github.com/hkchengrex/Cutie","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"XMem (BL30K, MS)","metrics":{"F-Measure (Seen)":"90.3","F-Measure (Unseen)":"90.2","Jaccard (Seen)":"85.6","Jaccard (Unseen)":"81.7","Overall":"86.9"},"uses_additional_data":true,"paper_date":"2022-07-14","paper":"/paper/xmem-long-term-video-object-segmentation-with","paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","code":"https://github.com/hkchengrex/XMem","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"XMem (MS)","metrics":{"F-Measure (Seen)":"89.9","F-Measure (Unseen)":"89.9","Jaccard (Seen)":"85.3","Jaccard (Unseen)":"81.7","Overall":"86.7"},"uses_additional_data":true,"paper_date":"2022-07-14","paper":"/paper/xmem-long-term-video-object-segmentation-with","paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","code":"https://github.com/hkchengrex/XMem","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":4,"model":"SwinB-AOTv2-L (all frames, MS)","metrics":{"F-Measure (Seen)":"90.7","F-Measure (Unseen)":"88.9","Jaccard (Seen)":"85.6","Jaccard (Unseen)":"80.7","Overall":"86.5","Params(M)":"65.6","Speed (FPS)":"0.7"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/associating-objects-with-scalable","paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"SwinB-DeAOT-L","metrics":{"F-Measure (Seen)":"90.6","F-Measure (Unseen)":"88.4","Jaccard (Seen)":"85.6","Jaccard (Unseen)":"80.0","Overall":"86.2","Params(M)":"70.3","Speed (FPS)":"11.9"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"XMem (BL30K)","metrics":{"F-Measure (Seen)":"89.8","F-Measure (Unseen)":"89.2","Jaccard (Seen)":"85.1","Jaccard (Unseen)":"80.3","Overall":"86.1","Speed  (FPS)":"22.6"},"uses_additional_data":true,"paper_date":"2022-07-14","paper":"/paper/xmem-long-term-video-object-segmentation-with","paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","code":"https://github.com/hkchengrex/XMem","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":7,"model":"R50-DeAOT-L","metrics":{"F-Measure (Seen)":"89.9","F-Measure (Unseen)":"88.7","Jaccard (Seen)":"84.9","Jaccard (Unseen)":"80.4","Overall":"86.0","Params(M)":"19.8","Speed (FPS)":"22.4"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"SwinB-AOTv2-L (all frames)","metrics":{"F-Measure (Seen)":"90.1","F-Measure (Unseen)":"88.2","Jaccard (Unseen)":"79.6","Overall":"85.8","Speed (FPS)":"5.1"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/associating-objects-with-scalable","paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"XMem","metrics":{"F-Measure (Seen)":"89.3","F-Measure (Unseen)":"88.7","Jaccard (Seen)":"84.6","Jaccard (Unseen)":"80.2","Overall":"85.7","Speed  (FPS)":"22.6"},"uses_additional_data":true,"paper_date":"2022-07-14","paper":"/paper/xmem-long-term-video-object-segmentation-with","paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","code":"https://github.com/hkchengrex/XMem","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":10,"model":"R50-AOT-L (all frames)","metrics":{"F-Measure (Seen)":"89.5","F-Measure (Unseen)":"88.2","Jaccard (Seen)":"84.5","Jaccard (Unseen)":"79.6","Overall":"85.5","Params(M)":"14.9","Speed  (FPS)":"6.4"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"R50-AOTv2-L (all frames)","metrics":{"F-Measure (Seen)":"90.2","F-Measure (Unseen)":"87.3","Jaccard (Seen)":"85.1","Jaccard (Unseen)":"78.9","Overall":"85.4","Params(M)":"15.1","Speed (FPS)":"6.3"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/associating-objects-with-scalable","paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"SwinB-AOT-L (all frames)","metrics":{"F-Measure (Seen)":"90.1","F-Measure (Unseen)":"86.9","Jaccard (Seen)":"85.1","Jaccard (Unseen)":"78.4","Overall":"85.1","Params(M)":"65.4","Speed  (FPS)":"5.2"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"R50-AOST (L'=3)","metrics":{"F-Measure (Seen)":"88.8","F-Measure (Unseen)":"87.9","Jaccard (Seen)":"83.8","Jaccard (Unseen)":"79.3","Overall":"85.0","Params(M)":"15.4","Speed (FPS)":"14.9"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/associating-objects-with-scalable","paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"DeAOT-L","metrics":{"F-Measure (Seen)":"89.4","Jaccard (Seen)":"84.2","Jaccard (Unseen)":"78.6","Overall":"84.8","Speed (FPS)":"24.7"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"DeAOT-B","metrics":{"F-Measure (Seen)":"88.9","F-Measure (Unseen)":"87.0","Jaccard (Seen)":"83.9","Jaccard (Unseen)":"78.5","Overall":"84.6","Params(M)":"13.2","Speed (FPS)":"30.4"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"SwinB-AOT-L","metrics":{"F-Measure (Seen)":"89.3","F-Measure (Unseen)":"86.4","Jaccard (Seen)":"84.3","Jaccard (Unseen)":"77.9","Overall":"84.5","Params(M)":"65.4","Speed  (FPS)":"9.3"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"AOT-L (all frames)","metrics":{"F-Measure (Seen)":"88.8","F-Measure (Unseen)":"87.1","Jaccard (Seen)":"83.7","Jaccard (Unseen)":"78.4","Overall":"84.5","Params(M)":"8.3","Speed  (FPS)":"6.5"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":18,"model":"R50-AOST (L'=2)","metrics":{"F-Measure (Seen)":"88.5","F-Measure (Unseen)":"87.2","Jaccard (Seen)":"83.5","Jaccard (Unseen)":"78.8","Overall":"84.5","Params(M)":"13.9","Speed (FPS)":"20.2"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/associating-objects-with-scalable","paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"XMem (YouTubeVOS only)","metrics":{"F-Measure (Seen)":"88.5","F-Measure (Unseen)":"87.2","Jaccard (Seen)":"83.7","Jaccard (Unseen)":"78.2","Overall":"84.4","Speed  (FPS)":"22.6"},"uses_additional_data":false,"paper_date":"2022-07-14","paper":"/paper/xmem-long-term-video-object-segmentation-with","paper_url":"https://arxiv.org/abs/2207.07115v2","paper_title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","code":"https://github.com/hkchengrex/XMem","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":20,"model":"RAVOS","metrics":{"F-Measure (Seen)":"87.8","F-Measure (Unseen)":"87.4","Jaccard (Seen)":"83.1","Jaccard (Unseen)":"79.1","Overall":"84.4","Speed  (FPS)":"23"},"uses_additional_data":true,"paper_date":"2022-07-21","paper":"/paper/region-aware-video-object-segmentation-with","paper_url":"https://arxiv.org/abs/2207.10258v1","paper_title":"Region Aware Video Object Segmentation with Deep Motion Modeling","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"RPCMVOS-MS","metrics":{"F-Measure (Seen)":"87.9","F-Measure (Unseen)":"86.9","Jaccard (Seen)":"83.3","Jaccard (Unseen)":"78.9","Overall":"84.3"},"uses_additional_data":false,"paper_date":"2021-12-06","paper":"/paper/reliable-propagation-correction-modulation","paper_url":"https://arxiv.org/abs/2112.02853v1","paper_title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","code":"https://github.com/jerryx1110/rpcmvos","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"R50-AOT-L","metrics":{"F-Measure (Seen)":"88.5","F-Measure (Unseen)":"86.1","Jaccard (Seen)":"83.7","Jaccard (Unseen)":"78.1","Overall":"84.1","Params(M)":"14.9","Speed  (FPS)":"14.9"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":23,"model":"AOT-B (all frames)","metrics":{"F-Measure (Seen)":"88.5","F-Measure (Unseen)":"86.5","Jaccard (Seen)":"83.6","Jaccard (Unseen)":"78.0","Overall":"84.1","Params(M)":"8.3","Speed  (FPS)":"20.5"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"DeAOT-S","metrics":{"F-Measure (Seen)":"88.3","F-Measure (Unseen)":"86.6","Jaccard (Seen)":"83.3","Jaccard (Unseen)":"77.9","Overall":"84.0","Params(M)":"10.2","Speed (FPS)":"38.7"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":25,"model":"RPCMVOS","metrics":{"F-Measure (Seen)":"87.7","F-Measure (Unseen)":"86.7","Jaccard (Seen)":"83.1","Overall":"84","Speed (FPS)":"78.5"},"uses_additional_data":false,"paper_date":"2021-12-06","paper":"/paper/reliable-propagation-correction-modulation","paper_url":"https://arxiv.org/abs/2112.02853v1","paper_title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","code":"https://github.com/jerryx1110/rpcmvos","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"AOT-L","metrics":{"F-Measure (Seen)":"87.9","F-Measure (Unseen)":"86.5","Jaccard (Seen)":"82.9","Jaccard (Unseen)":"77.7","Overall":"83.8","Params(M)":"8.3","Speed  (FPS)":"16.0"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":27,"model":"QDMN","metrics":{"F-Measure (Seen)":"87.5","F-Measure (Unseen)":"86.4","Jaccard (Seen)":"82.7","Jaccard (Unseen)":"78.4","Overall":"83.8"},"uses_additional_data":true,"paper_date":"2022-07-16","paper":"/paper/learning-quality-aware-dynamic-memory-for","paper_url":"https://arxiv.org/abs/2207.07922v1","paper_title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","code":"https://github.com/workforai/qdmn","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":28,"model":"AOT-B","metrics":{"F-Measure (Seen)":"87.5","F-Measure (Unseen)":"86.0","Jaccard (Seen)":"82.6","Jaccard (Unseen)":"77.7","Overall":"83.5","Params(M)":"8.3","Speed  (FPS)":"20.5"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":29,"model":"AOT-S (all frames)","metrics":{"F-Measure (Seen)":"87.0","F-Measure (Unseen)":"85.7","Jaccard (Seen)":"82.2","Jaccard (Unseen)":"77.3","Overall":"83.0","Params(M)":"7.9","Speed  (FPS)":"27.1"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":30,"model":"CFBI+","metrics":{"F-Measure (Seen)":"86.6","F-Measure (Unseen)":"85.6","Jaccard (Seen)":"81.8","Jaccard (Unseen)":"77.1","Overall":"82.8","Speed  (FPS)":"4.0"},"uses_additional_data":false,"paper_date":"2020-10-13","paper":"/paper/collaborative-video-object-segmentation-by-1","paper_url":"https://arxiv.org/abs/2010.06349v2","paper_title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","code":"https://github.com/z-x-yang/CFBI","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"HMMN","metrics":{"F-Measure (Seen)":"87.0","F-Measure (Unseen)":"84.6","Jaccard (Seen)":"82.1","Jaccard (Unseen)":"76.8","Overall":"82.6"},"uses_additional_data":true,"paper_date":"2021-09-23","paper":"/paper/hierarchical-memory-matching-network-for","paper_url":"https://arxiv.org/abs/2109.11404v1","paper_title":"Hierarchical Memory Matching Network for Video Object Segmentation","code":"https://github.com/hongje/hmmn","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":32,"model":"AOT-S","metrics":{"F-Measure (Seen)":"86.7","F-Measure (Unseen)":"85.0","Jaccard (Seen)":"82.0","Jaccard (Unseen)":"76.6","Overall":"82.6","Params(M)":"7.9","Speed  (FPS)":"27.1"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":33,"model":"DeAOT-T","metrics":{"F-Measure (Seen)":"86.3","F-Measure (Unseen)":"84.2","Jaccard (Seen)":"81.6","Jaccard (Unseen)":"75.8","Overall":"82.0","Params(M)":"7.2","Speed (FPS)":"53.4"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/decoupling-features-in-hierarchical","paper_url":"https://arxiv.org/abs/2210.09782v3","paper_title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":34,"model":"MiVOS","metrics":{"F-Measure (Seen)":"84.7","F-Measure (Unseen)":"85.5","Jaccard (Seen)":"80.6","Jaccard (Unseen)":"77.3","Overall":"82.0"},"uses_additional_data":true,"paper_date":"2021-03-14","paper":"/paper/modular-interactive-video-object-segmentation","paper_url":"https://arxiv.org/abs/2103.07941v3","paper_title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","code":"https://github.com/hkchengrex/MiVOS","n_code_links":5,"syntology":{"n_ran":9,"n_unverified":9,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"R50-AOST (L'=1)","metrics":{"F-Measure (Seen)":"86.1","F-Measure (Unseen)":"83.5","Jaccard (Seen)":"81.4","Jaccard (Unseen)":"75.5","Overall":"81.6","Params(M)":"12.5","Speed (FPS)":"30.9"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/associating-objects-with-scalable","paper_url":"https://arxiv.org/abs/2203.11442v8","paper_title":"Scalable Video Object Segmentation with Identification Mechanism","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":36,"model":"RMNet","metrics":{"F-Measure (Seen)":"85.7","F-Measure (Unseen)":"82.4","Jaccard (Seen)":"82.1","Jaccard (Unseen)":"75.7","Overall":"81.5"},"uses_additional_data":true,"paper_date":"2021-03-24","paper":"/paper/efficient-regional-memory-network-for-video","paper_url":"https://arxiv.org/abs/2103.12934v2","paper_title":"Efficient Regional Memory Network for Video Object Segmentation","code":"https://github.com/hzxie/RMNet","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"KMN","metrics":{"F-Measure (Seen)":"85.6","F-Measure (Unseen)":"83.3","Jaccard (Seen)":"81.4","Jaccard (Unseen)":"75.3","Overall":"81.4"},"uses_additional_data":true,"paper_date":"2020-07-16","paper":"/paper/kernelized-memory-network-for-video-object","paper_url":"https://arxiv.org/abs/2007.08270v1","paper_title":"Kernelized Memory Network for Video Object Segmentation","code":"https://github.com/hkchengrex/Mask-Propagation","n_code_links":1,"syntology":null},{"rank_in_archive_order":38,"model":"CFBI","metrics":{"F-Measure (Seen)":"85.8","F-Measure (Unseen)":"83.4","Jaccard (Seen)":"81.1","Jaccard (Unseen)":"75.3","Overall":"81.4","Params(M)":"66.3","Speed  (FPS)":"3.4"},"uses_additional_data":false,"paper_date":"2020-03-18","paper":"/paper/collaborative-video-object-segmentation-by","paper_url":"https://arxiv.org/abs/2003.08333v2","paper_title":"Collaborative Video Object Segmentation by Foreground-Background Integration","code":"https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/en/model_zoo/segmentation/cfbi.md","n_code_links":2,"syntology":null},{"rank_in_archive_order":39,"model":"AOT-T (all frames)","metrics":{"F-Measure (Seen)":"84.7","F-Measure (Unseen)":"83.5","Jaccard (Seen)":"80.0","Jaccard (Unseen)":"75.2","Overall":"80.9","Params(M)":"5.3","Speed  (FPS)":"41.0"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":40,"model":"AOT-T","metrics":{"F-Measure (Seen)":"84.5","F-Measure (Unseen)":"82.2","Jaccard (Seen)":"80.1","Jaccard (Unseen)":"74.0","Overall":"80.2","Params(M)":"5.3","Speed  (FPS)":"41.0"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/associating-objects-with-transformers-for","paper_url":"https://arxiv.org/abs/2106.02638v3","paper_title":"Associating Objects with Transformers for Video Object Segmentation","code":"https://github.com/yoxu515/aot-benchmark","n_code_links":2,"syntology":null},{"rank_in_archive_order":41,"model":"AFB-URR","metrics":{"F-Measure (Seen)":"83.1","F-Measure (Unseen)":"82.6","Jaccard (Seen)":"78.8","Jaccard (Unseen)":"74.1","Overall":"79.6"},"uses_additional_data":true,"paper_date":"2020-10-15","paper":"/paper/video-object-segmentation-with-adaptive","paper_url":"https://arxiv.org/abs/2010.07958v1","paper_title":"Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement","code":"https://github.com/xmlyqing00/AFB-URR","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"FRTM","metrics":{"F-Measure (Seen)":"76.2","F-Measure (Unseen)":"74.1","Jaccard (Seen)":"72.3","Overall":"72.1","Speed  (FPS)":"65.9"},"uses_additional_data":false,"paper_date":"2020-02-27","paper":"/paper/learning-fast-and-robust-target-models-for","paper_url":"https://arxiv.org/abs/2003.00908v2","paper_title":"Learning Fast and Robust Target Models for Video Object Segmentation","code":"https://github.com/andr345/frtm-vos","n_code_links":2,"syntology":null},{"rank_in_archive_order":43,"model":"e-OSVOS","metrics":{"F-Measure (Seen)":"66.0","F-Measure (Unseen)":"73.8","Jaccard (Seen)":"71.7","Jaccard (Unseen)":"74.3","Overall":"71.4"},"uses_additional_data":true,"paper_date":"2020-12-03","paper":"/paper/make-one-shot-video-object-segmentation-1","paper_url":"https://arxiv.org/abs/2012.01866v1","paper_title":"Make One-Shot Video Object Segmentation Efficient Again","code":"https://github.com/timmeinhardt/trackformer","n_code_links":4,"syntology":null},{"rank_in_archive_order":44,"model":"STM-cycle","metrics":{"F-Measure (Seen)":"75.8","F-Measure (Unseen)":"70.4","Jaccard (Seen)":"71.7","Overall":"69.9","Speed  (FPS)":"61.4"},"uses_additional_data":false,"paper_date":"2020-10-23","paper":"/paper/delving-into-the-cyclic-mechanism-in-semi","paper_url":"https://arxiv.org/abs/2010.12176v1","paper_title":"Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation","code":"https://github.com/lyxok1/STM-Training","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"MAMP","metrics":{"F-Measure (Seen)":"68.4","F-Measure (Unseen)":"73.2","Jaccard (Seen)":"67.0","Jaccard (Unseen)":"64.5","Overall":"68.2"},"uses_additional_data":false,"paper_date":"2021-07-27","paper":"/paper/self-supervised-video-object-segmentation-by-1","paper_url":"https://arxiv.org/abs/2107.12569v2","paper_title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","code":"https://github.com/bo-miao/MAMP","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"STM","metrics":{"Overall":"68.2"},"uses_additional_data":false,"paper_date":"2019-04-01","paper":"/paper/video-object-segmentation-using-space-time","paper_url":"https://arxiv.org/abs/1904.00607v2","paper_title":"Video Object Segmentation using Space-Time Memory Networks","code":"https://github.com/seoungwugoh/STM","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":47,"model":"SSM-VOS","metrics":{"F-Measure (Seen)":"73.3","F-Measure (Unseen)":"62.6","Jaccard (Seen)":"72.3","Jaccard (Unseen)":"57.8","Overall":"66.5","Speed  (FPS)":"24.1"},"uses_additional_data":false,"paper_date":"2021-02-18","paper":"/paper/separable-structure-modeling-for-semi","paper_url":"https://ieeexplore.ieee.org/document/9356697","paper_title":"Separable Structure Modeling for Semi-supervised Video Object Segmentation","code":"https://github.com/li-plus/SSM-VOS","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"S2S","metrics":{"F-Measure (Seen)":"70.0","F-Measure (Unseen)":"61.2","Jaccard (Seen)":"71.0","Overall":"64.4","Speed  (FPS)":"55.5"},"uses_additional_data":false,"paper_date":"2018-09-03","paper":"/paper/youtube-vos-sequence-to-sequence-video-object","paper_url":"http://arxiv.org/abs/1809.00461v1","paper_title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","code":"https://github.com/BehradToghi/ECCV_Youtube_VOS","n_code_links":4,"syntology":null},{"rank_in_archive_order":49,"model":"CapsuleVOS","metrics":{"F-Measure (Seen)":"68.1","F-Measure (Unseen)":"59.9","Jaccard (Seen)":"67.3","Jaccard (Unseen)":"53.7","Overall":"62.3","Speed  (FPS)":"13.5"},"uses_additional_data":false,"paper_date":"2019-09-30","paper":"/paper/capsulevos-semi-supervised-video-object","paper_url":"https://arxiv.org/abs/1910.00132v1","paper_title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","code":"https://github.com/KevinDuarte/CapsuleVOS","n_code_links":1,"syntology":null},{"rank_in_archive_order":50,"model":"OSVOS","metrics":{"F-Measure (Seen)":"60.5","F-Measure (Unseen)":"60.7","Jaccard (Seen)":"59.8","Jaccard (Unseen)":"54.2","Overall":"58.8","Speed  (FPS)":"0.10"},"uses_additional_data":false,"paper_date":"2016-11-16","paper":"/paper/one-shot-video-object-segmentation","paper_url":"http://arxiv.org/abs/1611.05198v4","paper_title":"One-Shot Video Object Segmentation","code":"https://github.com/kmaninis/OSVOS-PyTorch","n_code_links":8,"syntology":null},{"rank_in_archive_order":51,"model":"RVOS","metrics":{"F-Measure (Seen)":"67.2","F-Measure (Unseen)":"51.0","Jaccard (Seen)":"63.6","Overall":"56.8","Speed  (FPS)":"45.5"},"uses_additional_data":false,"paper_date":"2019-03-13","paper":"/paper/rvos-end-to-end-recurrent-network-for-video","paper_url":"https://arxiv.org/abs/1903.05612v2","paper_title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","code":"https://github.com/imatge-upc/rvos","n_code_links":1,"syntology":null},{"rank_in_archive_order":52,"model":"OSMN","metrics":{"F-Measure (Seen)":"60.1","F-Measure (Unseen)":"44.0","Jaccard (Seen)":"60.0","Jaccard (Unseen)":"40.6","Overall":"51.2","Speed  (FPS)":"7.14"},"uses_additional_data":false,"paper_date":"2018-02-04","paper":"/paper/efficient-video-object-segmentation-via","paper_url":"http://arxiv.org/abs/1802.01218v1","paper_title":"Efficient Video Object Segmentation via Network Modulation","code":"https://github.com/linjieyangsc/video_seg","n_code_links":1,"syntology":null},{"rank_in_archive_order":53,"model":"STCN","metrics":{"F-Measure (Seen)":"87.9","F-Measure (Unseen)":"87.3","Jaccard (Seen)":"83.2","Jaccard (Unseen)":"79.0"},"uses_additional_data":true,"paper_date":"2021-06-09","paper":"/paper/rethinking-space-time-networks-with-improved","paper_url":"https://arxiv.org/abs/2106.05210v2","paper_title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","code":"https://github.com/hkchengrex/STCN","n_code_links":3,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":2}}],"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 6,264 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":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"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":13,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":31,"n_unverified":38,"n_samples":69,"n_pointer_only_licence":13,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":36,"n_unverified":50,"n_samples":86,"n_pointer_only_licence":21,"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"}}}