{"url":"/dataset/davis-2017","name":"DAVIS 2017","full_name":"DAVIS 2017","description_markdown":"DAVIS17 is a dataset for video object segmentation.  It contains a total of 150 videos - 60 for training, 30 for validation, 60 for testing\r\n\r\nSource: [Siam R-CNN: Visual Tracking by Re-Detection](https://arxiv.org/abs/1911.12836)\r\nImage Source: [https://www.researchgate.net/figure/LucidTracker-qualitative-results-on-DAVIS-17-test-dev-set-Frames-sampled-along-the_fig5_331792902](https://www.researchgate.net/figure/LucidTracker-qualitative-results-on-DAVIS-17-test-dev-set-Frames-sampled-along-the_fig5_331792902)","description_withheld":null,"homepage":"https://davischallenge.org/challenge2017/index.html","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-2017-davis-challenge-on-video-object","title":"The 2017 DAVIS Challenge on Video Object Segmentation","first_author":"Jordi Pont-Tuset","url":null},"license":{"name":"Annotations under CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Video Object Segmentation","url":"/task/video-object-segmentation","datasets_with_task":"/datasets/task/video-object-segmentation"},{"name":"Video Prediction","url":"/task/video-prediction","datasets_with_task":"/datasets/task/video-prediction"},{"name":"Referring Expression Segmentation","url":"/task/referring-expression-segmentation","datasets_with_task":"/datasets/task/referring-expression-segmentation"},{"name":"Semi-Supervised Video Object Segmentation","url":"/task/semi-supervised-video-object-segmentation","datasets_with_task":"/datasets/task/semi-supervised-video-object-segmentation"},{"name":"Unsupervised Video Object Segmentation","url":"/task/unsupervised-video-object-segmentation","datasets_with_task":"/datasets/task/unsupervised-video-object-segmentation"},{"name":"Interactive Video Object Segmentation","url":"/task/interactive-video-object-segmentation","datasets_with_task":"/datasets/task/interactive-video-object-segmentation"}],"languages":[],"variants":["DAVIS 2017","DAVIS 2017 (test-dev)","DAVIS 2017 (val)","DAVIS-2017"],"data_loaders":[],"num_papers_in_archive":308,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset_variant":"DAVIS 2017 (val)","rows":81,"metrics":["J&F","Jaccard (Mean)","Jaccard (Recall)","Jaccard (Decay)","F-measure (Mean)","F-measure (Recall)","F-measure (Decay)","Speed (FPS)","Params(M)"],"first_row_in_archive_order":{"model":"SAM2","paper":"/paper/2408-00714","metrics":{"J&F":"90.7","Params(M)":"224.4"},"code_links":[{"title":"facebookresearch/segment-anything","url":"https://github.com/facebookresearch/segment-anything"},{"title":"facebookresearch/sam2","url":"https://github.com/facebookresearch/sam2"},{"title":"yangchris11/samurai","url":"https://github.com/yangchris11/samurai"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"ibaiGorordo/ONNX-SAM2-Segment-Anything","url":"https://github.com/ibaiGorordo/ONNX-SAM2-Segment-Anything"},{"title":"bowang-lab/medsam2","url":"https://github.com/bowang-lab/medsam2"},{"title":"TripleJoy/SAM2MOT","url":"https://github.com/TripleJoy/SAM2MOT"},{"title":"louisfinner/him2sam","url":"https://github.com/louisfinner/him2sam"},{"title":"MindCode-4/code-4","url":"https://github.com/MindCode-4/code-4/tree/main/sam"},{"title":"dcnieho/segment-anything-2","url":"https://github.com/dcnieho/segment-anything-2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/SAM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset_variant":"DAVIS 2017 (test-dev)","rows":59,"metrics":["J&F","Jaccard (Mean)","Jaccard (Recall)","Jaccard (Decay)","F-measure (Mean)","F-measure (Recall)","F-measure (Decay)","FPS"],"first_row_in_archive_order":{"model":"Cutie+ (base, MEGA)","paper":"/paper/putting-the-object-back-into-video-object","metrics":{"F-measure (Mean)":"91.4","FPS":"17.9","J&F":"88.1","Jaccard (Mean)":"84.7"},"code_links":[{"title":"hkchengrex/Cutie","url":"https://github.com/hkchengrex/Cutie"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/referring-expression-segmentation-on-davis","task":"Referring Expression Segmentation","dataset_variant":"DAVIS 2017 (val)","rows":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":"/paper/universal-instance-perception-as-object","metrics":{"J&F 1st frame":"72.5"},"code_links":[{"title":"MasterBin-IIAU/UNINEXT","url":"https://github.com/MasterBin-IIAU/UNINEXT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017-val","task":"Video Object Segmentation","dataset_variant":"DAVIS 2017 (val)","rows":17,"metrics":["Mean Jaccard & F-Measure","F-measure","Jaccard"],"first_row_in_archive_order":{"model":"XMem (BLK30K, MS)","paper":"/paper/xmem-long-term-video-object-segmentation-with","metrics":{"F-measure":"92.6","Jaccard":"86.3","Mean Jaccard & F-Measure":"89.5"},"code_links":[{"title":"hkchengrex/XMem","url":"https://github.com/hkchengrex/XMem"},{"title":"tianyuan168326/videosemanticcompression-pytorch","url":"https://github.com/tianyuan168326/videosemanticcompression-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-4","task":"Unsupervised Video Object Segmentation","dataset_variant":"DAVIS 2017 (val)","rows":10,"metrics":["J&F","Jaccard (Mean)","Jaccard (Recall)","F-measure (Mean)","F-measure (Recall)"],"first_row_in_archive_order":{"model":"DEVA (EntitySeg)","paper":"/paper/tracking-anything-with-decoupled-video","metrics":{"F-measure (Mean)":"76.4","J&F":"73.4","Jaccard (Mean)":"70.4"},"code_links":[{"title":"hkchengrex/Tracking-Anything-with-DEVA","url":"https://github.com/hkchengrex/Tracking-Anything-with-DEVA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017-test-1","task":"Video Object Segmentation","dataset_variant":"DAVIS 2017 (test-dev)","rows":10,"metrics":["Jaccard","F-measure","Mean Jaccard & F-Measure"],"first_row_in_archive_order":{"model":"BATMAN","paper":"/paper/batman-bilateral-attention-transformer-in","metrics":{"F-measure":"86.1","Jaccard":"78.4","Mean Jaccard & F-Measure":"82.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/interactive-video-object-segmentation-on","task":"Interactive Video Object Segmentation","dataset_variant":"DAVIS 2017","rows":7,"metrics":["AUC-J&F","J&F@60s","AUC-J","J@60s"],"first_row_in_archive_order":{"model":"MiVOS","paper":"/paper/modular-interactive-video-object-segmentation","metrics":{"AUC-J":"0.849","AUC-J&F":"0.879","J&F@60s":"0.885","J@60s":"0.854"},"code_links":[{"title":"hkchengrex/MiVOS","url":"https://github.com/hkchengrex/MiVOS"},{"title":"hkchengrex/Mask-Propagation","url":"https://github.com/hkchengrex/Mask-Propagation"},{"title":"hkchengrex/Scribble-to-Mask","url":"https://github.com/hkchengrex/Scribble-to-Mask"},{"title":"limingxing00/rde-vos-cvpr2022","url":"https://github.com/limingxing00/rde-vos-cvpr2022"},{"title":"Vujas-Eteph/CiVOS","url":"https://github.com/Vujas-Eteph/CiVOS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-5","task":"Unsupervised Video Object Segmentation","dataset_variant":"DAVIS 2017 (test-dev)","rows":6,"metrics":["J&F","Jaccard (Mean)","Jaccard (Recall)","Jaccard (Decay)","F-measure (Mean)","F-measure (Recall)","F-measure (Decay)"],"first_row_in_archive_order":{"model":"DEVA (EntitySeg)","paper":"/paper/tracking-anything-with-decoupled-video","metrics":{"J&F":"62.1"},"code_links":[{"title":"hkchengrex/Tracking-Anything-with-DEVA","url":"https://github.com/hkchengrex/Tracking-Anything-with-DEVA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017","task":"Video Object Segmentation","dataset_variant":"DAVIS 2017","rows":5,"metrics":["Jaccard (Mean)","mIoU","J&F","F-Score"],"first_row_in_archive_order":{"model":"AOC-MF (val)","paper":"/paper/towards-robust-video-object-segmentation-with","metrics":{"F-Score":"85.9","Jaccard (Mean)":"81.7"},"code_links":[{"title":"jerryx1110/robust-video-object-segmentation","url":"https://github.com/jerryx1110/robust-video-object-segmentation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-2","task":"Semi-Supervised Video Object Segmentation","dataset_variant":"DAVIS-2017","rows":2,"metrics":["F-measure (Mean)","J&F","Jaccard (Mean)","Speed (FPS)"],"first_row_in_archive_order":{"model":"STCN + TrickVOS (PT)","paper":"/paper/trickvos-a-bag-of-tricks-for-video-object","metrics":{"F-measure (Mean)":"89.6","J&F":"86.1","Jaccard (Mean)":"82.6","Speed (FPS)":"35.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-prediction-on-davis-2017","task":"Video Prediction","dataset_variant":"DAVIS 2017","rows":2,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"DMVFN","paper":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","metrics":{"LPIPS":"0.0996","MS-SSIM":"0.8397"},"code_links":[{"title":"megvii-research/CVPR2023-DMVFN","url":"https://github.com/megvii-research/CVPR2023-DMVFN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-17","task":"Semi-Supervised Video Object Segmentation","dataset_variant":"DAVIS 2017","rows":1,"metrics":["F-measure (Decay)","F-measure (Mean)","F-measure (Recall)","J&F","Jaccard (Decay)","Jaccard (Mean)","Jaccard (Recall)"],"first_row_in_archive_order":{"model":"FEELVOS","paper":"/paper/feelvos-fast-end-to-end-embedding-learning","metrics":{"F-measure (Decay)":"20.1","F-measure (Mean)":"74.0","F-measure (Recall)":"83.8","J&F":"71.55","Jaccard (Decay)":"17.5","Jaccard (Mean)":"69.1","Jaccard (Recall)":"79.1"},"code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/feelvos"},{"title":"kim-younghan/FEELVOS","url":"https://github.com/kim-younghan/FEELVOS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":7,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/memory-matching-is-not-enough-jointly","title":"Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation","date":"2024-09-22","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":49,"samples_ran":28,"samples_unverified":21,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/safari-adaptive-sequence-transformer-for","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","date":"2024-07-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-referring-image-segmentation-using","title":"Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding","date":"2024-04-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","date":"2024-03-28","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":14,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":12,"samples_unverified":2,"pointer_only_for_licence":14,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/putting-the-object-back-into-video-object","title":"Putting the Object Back into Video Object Segmentation","date":"2023-10-19","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":7,"samples_unverified":3,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spectrum-guided-multi-granularity-referring","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","date":"2023-07-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/trickvos-a-bag-of-tricks-for-video-object","title":"TrickVOS: A Bag of Tricks for Video Object Segmentation","date":"2023-06-27","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","date":"2023-03-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mobilevos-real-time-video-object-segmentation","title":"MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation","date":"2023-03-14","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/universal-instance-perception-as-object","title":"Universal Instance Perception as Object Discovery and Retrieval","date":"2023-03-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tarvis-a-unified-approach-for-target-based","title":"TarViS: A Unified Approach for Target-based Video Segmentation","date":"2023-01-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/look-before-you-match-instance-understanding","title":"Look Before You Match: Instance Understanding Matters in Video Object Segmentation","date":"2022-12-13","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/decoupling-features-in-hierarchical","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","date":"2022-10-18","rows_on_this_dataset":12,"code_links":2,"syntology":null},{"paper":"/paper/swem-towards-real-time-video-object-1","title":"SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization","date":"2022-08-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/batman-bilateral-attention-transformer-in","title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","date":"2022-08-01","rows_on_this_dataset":22,"code_links":0,"syntology":null},{"paper":"/paper/region-aware-video-object-segmentation-with","title":"Region Aware Video Object Segmentation with Deep Motion Modeling","date":"2022-07-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-quality-aware-dynamic-memory-for","title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","date":"2022-07-16","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/xmem-long-term-video-object-segmentation-with","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","date":"2022-07-14","rows_on_this_dataset":14,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/towards-robust-video-object-segmentation-with","title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","date":"2022-07-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/associating-objects-with-scalable","title":"Scalable Video Object Segmentation with Identification Mechanism","date":"2022-03-22","rows_on_this_dataset":11,"code_links":2,"syntology":null},{"paper":"/paper/language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":7,"samples_unverified":1,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reliable-propagation-correction-modulation","title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","date":"2021-12-06","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":1,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hierarchical-interaction-network-for-video","title":"Hierarchical interaction network for video object segmentation from referring expressions","date":"2021-11-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dense-unsupervised-learning-for-video","title":"Dense Unsupervised Learning for Video Segmentation","date":"2021-11-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hierarchical-memory-matching-network-for","title":"Hierarchical Memory Matching Network for Video Object Segmentation","date":"2021-09-23","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/joint-inductive-and-transductive-learning-for","title":"Joint Inductive and Transductive Learning for Video Object Segmentation","date":"2021-08-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-supervised-video-object-segmentation-by-1","title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","date":"2021-07-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","date":"2021-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":6,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-space-time-networks-with-improved","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","date":"2021-06-09","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/synthref-generation-of-synthetic-referring","title":"SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation","date":"2021-06-08","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/vitae-vision-transformer-advanced-by","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","date":"2021-06-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/associating-objects-with-transformers-for","title":"Associating Objects with Transformers for Video Object Segmentation","date":"2021-06-04","rows_on_this_dataset":13,"code_links":2,"syntology":null},{"paper":"/paper/emerging-properties-in-self-supervised-vision","title":"Emerging Properties in Self-Supervised Vision Transformers","date":"2021-04-29","rows_on_this_dataset":1,"code_links":32,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":5,"samples_unverified":15,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/guided-interactive-video-object-segmentation","title":"Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps","date":"2021-04-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":6,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/video-instance-segmentation-with-a-propose","title":"Video Instance Segmentation with a Propose-Reduce Paradigm","date":"2021-03-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-regional-memory-network-for-video","title":"Efficient Regional Memory Network for Video Object Segmentation","date":"2021-03-24","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":5,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/modular-interactive-video-object-segmentation","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","date":"2021-03-14","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":9,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fast-interactive-video-object-segmentation","title":"Fast Interactive Video Object Segmentation with Graph Neural Networks","date":"2021-03-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/separable-structure-modeling-for-semi","title":"Separable Structure Modeling for Semi-supervised Video Object Segmentation","date":"2021-02-18","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/make-one-shot-video-object-segmentation-1","title":"Make One-Shot Video Object Segmentation Efficient Again","date":"2020-12-03","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/video-object-segmentation-with-adaptive","title":"Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement","date":"2020-10-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/collaborative-video-object-segmentation-by-1","title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","date":"2020-10-13","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/refvos-a-closer-look-at-referring-expressions","title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","date":"2020-10-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/lsmvos-long-short-term-similarity-matching","title":"LSMVOS: Long-Short-Term Similarity Matching for Video Object","date":"2020-09-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/matnet-motion-attentive-transition-network","title":"MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation","date":"2020-08-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/urvos-unified-referring-video-object","title":"URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark","date":"2020-08-01","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/kernelized-memory-network-for-video-object","title":"Kernelized Memory Network for Video Object Segmentation","date":"2020-07-16","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/interactive-video-object-segmentation-using","title":"Interactive Video Object Segmentation Using Global and Local Transfer Modules","date":"2020-07-16","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":0,"samples_unverified":15,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/alba-reinforcement-learning-for-video-object","title":"ALBA : Reinforcement Learning for Video Object Segmentation","date":"2020-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-transductive-approach-for-video-object","title":"A Transductive Approach for Video Object Segmentation","date":"2020-04-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/memory-aggregation-networks-for-efficient","title":"Memory Aggregation Networks for Efficient Interactive Video Object Segmentation","date":"2020-03-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/stem-seg-spatio-temporal-embeddings-for","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","date":"2020-03-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/collaborative-video-object-segmentation-by","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","date":"2020-03-18","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/learning-video-object-segmentation-from-2","title":"Learning Video Object Segmentation from Unlabeled Videos","date":"2020-03-10","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mast-a-memory-augmented-self-supervised","title":"MAST: A Memory-Augmented Self-supervised Tracker","date":"2020-02-18","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/unovost-unsupervised-offline-video-object","title":"UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking","date":"2020-01-15","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/siam-r-cnn-visual-tracking-by-re-detection","title":"Siam R-CNN: Visual Tracking by Re-Detection","date":"2019-11-28","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/agss-vos-attention-guided-single-shot-video","title":"AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation","date":"2019-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/capsulevos-semi-supervised-video-object","title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","date":"2019-09-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/joint-task-self-supervised-learning-for","title":"Joint-task Self-supervised Learning for Temporal Correspondence","date":"2019-09-26","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":23,"samples_ran":4,"samples_unverified":19,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ranet-ranking-attention-network-for-fast","title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","date":"2019-08-19","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":1,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/proposal-tracking-and-segmentation-pts-a","title":"Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation","date":"2019-07-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-unsupervised-video-object","title":"Learning Unsupervised Video Object Segmentation Through Visual Attention","date":"2019-06-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-learning-for-video","title":"Self-supervised Learning for Video Correspondence Flow","date":"2019-05-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fast-user-guided-video-object-segmentation-by","title":"Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks","date":"2019-04-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/190408141","title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","date":"2019-04-17","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/spatiotemporal-cnn-for-video-object","title":"Spatiotemporal CNN for Video Object Segmentation","date":"2019-04-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/video-object-segmentation-using-space-time","title":"Video Object Segmentation using Space-Time Memory Networks","date":"2019-04-01","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-correspondence-from-the-cycle","title":"Learning Correspondence from the Cycle-Consistency of Time","date":"2019-03-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rvos-end-to-end-recurrent-network-for-video","title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","date":"2019-03-13","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/feelvos-fast-end-to-end-embedding-learning","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","date":"2019-02-25","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":1,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fast-online-object-tracking-and-segmentation","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","date":"2018-12-12","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":1,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-generative-appearance-model-for-end-to-end","title":"A Generative Appearance Model for End-to-end Video Object Segmentation","date":"2018-11-28","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/videomatch-matching-based-video-object","title":"VideoMatch: Matching based Video Object Segmentation","date":"2018-09-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/pyramid-dilated-deeper-convlstm-for-video","title":"Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection","date":"2018-09-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/premvos-proposal-generation-refinement-and","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","date":"2018-07-24","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":3,"samples_unverified":12,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fast-and-accurate-online-video-object","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","date":"2018-06-06","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fast-video-object-segmentation-by-reference","title":"Fast Video Object Segmentation by Reference-Guided Mask Propagation","date":"2018-06-01","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/cnn-in-mrf-video-object-segmentation-via","title":"CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF","date":"2018-03-26","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/video-object-segmentation-with-language","title":"Video Object Segmentation with Language Referring Expressions","date":"2018-03-21","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/efficient-video-object-segmentation-via","title":"Efficient Video Object Segmentation via Network Modulation","date":"2018-02-04","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/video-object-segmentation-without-temporal","title":"Video Object Segmentation Without Temporal Information","date":"2017-09-18","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/online-adaptation-of-convolutional-neural","title":"Online Adaptation of Convolutional Neural Networks for Video Object Segmentation","date":"2017-06-28","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/lucid-data-dreaming-for-video-object","title":"Lucid Data Dreaming for Video Object Segmentation","date":"2017-03-28","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/video-frame-synthesis-using-deep-voxel-flow","title":"Video Frame Synthesis using Deep Voxel Flow","date":"2017-02-08","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/one-shot-video-object-segmentation","title":"One-Shot Video Object Segmentation","date":"2016-11-16","rows_on_this_dataset":2,"code_links":8,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":43,"samples_harvested":387,"samples_ran":167,"samples_unverified":220,"pointer_only_for_licence":86,"papers_with_no_sample_that_ran":9,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}