{"url":"/dataset/youtube-vos","name":"YouTube-VOS 2018","full_name":"Youtube Video Object Segmentation","description_markdown":"Youtube-VOS is a Video Object Segmentation dataset that contains 4,453 videos - 3,471 for training, 474 for validation, and 508 for testing. The training and validation videos have pixel-level ground truth annotations for every 5th frame (6 fps). It also contains Instance Segmentation annotations. It has more than 7,800 unique objects, 190k high-quality manual annotations and more than 340 minutes in duration.\r\n\r\nSource: [CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing](https://arxiv.org/abs/1910.00132)\r\nImage Source: [https://youtube-vos.org/](https://youtube-vos.org/)","description_withheld":null,"homepage":"https://youtube-vos.org/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","first_author":null,"url":"https://arxiv.org/pdf/1809.03327.pdf"},"license":{"name":"CC BY 4.0","url":"https://codalab.lisn.upsaclay.fr/competitions/6066#learn_the_details-terms_and_conditions"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video Object Segmentation","url":"/task/video-object-segmentation","datasets_with_task":"/datasets/task/video-object-segmentation"},{"name":"Visual Object Tracking","url":"/task/visual-object-tracking","datasets_with_task":"/datasets/task/visual-object-tracking"},{"name":"Semi-Supervised Video Object Segmentation","url":"/task/semi-supervised-video-object-segmentation","datasets_with_task":"/datasets/task/semi-supervised-video-object-segmentation"},{"name":"Video Inpainting","url":"/task/video-inpainting","datasets_with_task":"/datasets/task/video-inpainting"},{"name":"One-shot visual object segmentation","url":"/task/one-shot-visual-object-segmentation","datasets_with_task":"/datasets/task/one-shot-visual-object-segmentation"}],"languages":[],"variants":["YouTube-VOS 2018","YouTube-VOS","YouTube-VOS 2019"],"data_loaders":[],"num_papers_in_archive":203,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset_variant":"YouTube-VOS 2018","rows":53,"metrics":["Overall","Jaccard (Seen)","Jaccard (Unseen)","F-Measure (Seen)","F-Measure (Unseen)","Speed  (FPS)","Params(M)","Speed (FPS)"],"first_row_in_archive_order":{"model":"Cutie+ (base, MEGA)","paper":"/paper/putting-the-object-back-into-video-object","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"},"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/semi-supervised-video-object-segmentation-on-18","task":"Semi-Supervised Video Object Segmentation","dataset_variant":"YouTube-VOS 2019","rows":22,"metrics":["Overall","Jaccard (Seen)","F-Measure (Seen)","Jaccard (Unseen)","F-Measure (Unseen)","FPS","J&F","J score (unseen)"],"first_row_in_archive_order":{"model":"Cutie+ (base, MEGA)","paper":"/paper/putting-the-object-back-into-video-object","metrics":{"F-Measure (Seen)":"90.6","F-Measure (Unseen)":"90.5","J&F":"17.9","Jaccard (Seen)":"86.3","Jaccard (Unseen)":"82.7","Overall":"87.5"},"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/video-object-segmentation-on-youtube-vos-1","task":"Video Object Segmentation","dataset_variant":"YouTube-VOS 2018","rows":17,"metrics":["Mean Jaccard & F-Measure","Jaccard (Seen)","Jaccard (Unseen)","F-Measure (Seen)","F-Measure (Unseen)"],"first_row_in_archive_order":{"model":"XMem (BL30K, MS)","paper":"/paper/xmem-long-term-video-object-segmentation-with","metrics":{"F-Measure (Seen)":"90.3","F-Measure (Unseen)":"90.2","Jaccard (Seen)":"85.6","Jaccard (Unseen)":"81.7","Mean Jaccard & F-Measure":"86.9"},"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/video-inpainting-on-youtube-vos","task":"Video Inpainting","dataset_variant":"YouTube-VOS 2018","rows":10,"metrics":["PSNR","SSIM","VFID","Ewarp"],"first_row_in_archive_order":{"model":"ProPainter","paper":"/paper/propainter-improving-propagation-and","metrics":{"Ewarp":"-","PSNR":"34.43","SSIM":"0.9735","VFID":"0.042"},"code_links":[{"title":"sczhou/propainter","url":"https://github.com/sczhou/propainter"},{"title":"osmr/propainter","url":"https://github.com/osmr/propainter"},{"title":"osmr/pytorchcv","url":"https://github.com/osmr/pytorchcv"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos-2019-2","task":"Video Object Segmentation","dataset_variant":"YouTube-VOS 2019","rows":10,"metrics":["Mean Jaccard & F-Measure","Jaccard (Seen)","Jaccard (Unseen)","F-Measure (Seen)","F-Measure (Unseen)"],"first_row_in_archive_order":{"model":"XMem (BL30K,MS)","paper":"/paper/xmem-long-term-video-object-segmentation-with","metrics":{"F-Measure (Seen)":"89.8","F-Measure (Unseen)":"89.9","Jaccard (Seen)":"85.5","Jaccard (Unseen)":"81.8","Mean Jaccard & F-Measure":"86.8"},"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/visual-object-tracking-on-youtube-vos","task":"Visual Object Tracking","dataset_variant":"YouTube-VOS 2018","rows":9,"metrics":["O (Average of Measures)","Jaccard (Seen)","Jaccard (Unseen)","F-Measure (Seen)","F-Measure (Unseen)"],"first_row_in_archive_order":{"model":"OSVOS","paper":"/paper/one-shot-video-object-segmentation","metrics":{"F-Measure (Seen)":"60.5","F-Measure (Unseen)":"60.7","O (Average of Measures)":"58.8"},"code_links":[{"title":"kmaninis/OSVOS-PyTorch","url":"https://github.com/kmaninis/OSVOS-PyTorch"},{"title":"scaelles/OSVOS-TensorFlow","url":"https://github.com/scaelles/OSVOS-TensorFlow"},{"title":"kmaninis/OSVOS-caffe","url":"https://github.com/kmaninis/OSVOS-caffe"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/OSVOS"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/OSVOS"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/OSVOS"},{"title":"2023-MindSpore-1/ms-code-215","url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/OSVOS"},{"title":"Mind23-2/MindCode-5","url":"https://github.com/Mind23-2/MindCode-5/tree/main/OSVOS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/one-shot-visual-object-segmentation-on","task":"One-shot visual object segmentation","dataset_variant":"YouTube-VOS 2018","rows":2,"metrics":["F-Measure (Seen)","Jaccard (Seen)"],"first_row_in_archive_order":{"model":"OSVOS","paper":"/paper/one-shot-video-object-segmentation","metrics":{"F-Measure (Seen)":"60.5"},"code_links":[{"title":"kmaninis/OSVOS-PyTorch","url":"https://github.com/kmaninis/OSVOS-PyTorch"},{"title":"scaelles/OSVOS-TensorFlow","url":"https://github.com/scaelles/OSVOS-TensorFlow"},{"title":"kmaninis/OSVOS-caffe","url":"https://github.com/kmaninis/OSVOS-caffe"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/OSVOS"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/OSVOS"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/OSVOS"},{"title":"2023-MindSpore-1/ms-code-215","url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/OSVOS"},{"title":"Mind23-2/MindCode-5","url":"https://github.com/Mind23-2/MindCode-5/tree/main/OSVOS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-inpainting-on-youtube-vos-1","task":"Video Inpainting","dataset_variant":"YouTube-VOS","rows":2,"metrics":["LPIPS","PSNR","PSNR (square)","SSIM"],"first_row_in_archive_order":{"model":"FGT++","paper":"/paper/exploiting-optical-flow-guidance-for","metrics":{"LPIPS":"0.025","PSNR":"35.02","PSNR (square)":"33.18","SSIM":"97.6"},"code_links":[{"title":"hitachinsk/fgt","url":"https://github.com/hitachinsk/fgt"},{"title":"hitachinsk/isvi","url":"https://github.com/hitachinsk/isvi"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-object-tracking-on-youtube-vos-1","task":"Visual Object Tracking","dataset_variant":"YouTube-VOS","rows":2,"metrics":["F-Measure (Seen)","F-Measure (Unseen)","Jaccard (Seen)","Jaccard (Unseen)","O (Average of Measures)"],"first_row_in_archive_order":{"model":"AOC-MF","paper":"/paper/towards-robust-video-object-segmentation-with","metrics":{"F-Measure (Seen)":"87.4","F-Measure (Unseen)":"87.1","Jaccard (Seen)":"82.7","Jaccard (Unseen)":"78.8","O (Average of Measures)":"84"},"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/one-shot-visual-object-segmentation-on-1","task":"One-shot visual object segmentation","dataset_variant":"YouTube-VOS","rows":1,"metrics":["F-Measure (Seen)","F-Measure (Unseen)","Jaccard (Seen)","Jaccard (Unseen)"],"first_row_in_archive_order":{"model":"RVOS-Mask-ST+","paper":"/paper/rvos-end-to-end-recurrent-network-for-video","metrics":{"F-Measure (Seen)":"67.2","F-Measure (Unseen)":"51","Jaccard (Seen)":"63.6","Jaccard (Unseen)":"45.5"},"code_links":[{"title":"imatge-upc/rvos","url":"https://github.com/imatge-upc/rvos"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"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":1,"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":2,"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/propainter-improving-propagation-and","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","date":"2023-09-07","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":34,"samples_ran":20,"samples_unverified":14,"pointer_only_for_licence":16,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tracking-anything-in-high-quality","title":"Tracking Anything in High Quality","date":"2023-07-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deficiency-aware-masked-transformer-for-video","title":"Deficiency-Aware Masked Transformer for Video Inpainting","date":"2023-07-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/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":1,"code_links":0,"syntology":null},{"paper":"/paper/exploiting-optical-flow-guidance-for","title":"Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting","date":"2023-01-24","rows_on_this_dataset":2,"code_links":2,"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/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":19,"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":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/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":12,"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":2,"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/towards-an-end-to-end-framework-for-flow","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","date":"2022-04-06","rows_on_this_dataset":1,"code_links":2,"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/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/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-memory-matching-network-for","title":"Hierarchical Memory Matching Network for Video Object Segmentation","date":"2021-09-23","rows_on_this_dataset":1,"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/fuseformer-fusing-fine-grained-information-in","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","date":"2021-09-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":10,"samples_unverified":1,"pointer_only_for_licence":11,"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/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":4,"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/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/efficient-regional-memory-network-for-video","title":"Efficient Regional Memory Network for Video Object Segmentation","date":"2021-03-24","rows_on_this_dataset":1,"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":1,"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/separable-structure-modeling-for-semi","title":"Separable Structure Modeling for Semi-supervised Video Object Segmentation","date":"2021-02-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sstvos-sparse-spatiotemporal-transformers-for","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","date":"2021-01-21","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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":1,"code_links":4,"syntology":null},{"paper":"/paper/delving-into-the-cyclic-mechanism-in-semi","title":"Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation","date":"2020-10-23","rows_on_this_dataset":1,"code_links":1,"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":1,"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/flow-edge-guided-video-completion","title":"Flow-edge Guided Video Completion","date":"2020-09-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-joint-spatial-temporal","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","date":"2020-07-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/kernelized-memory-network-for-video-object","title":"Kernelized Memory Network for Video Object Segmentation","date":"2020-07-16","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-fast-and-robust-target-models-for","title":"Learning Fast and Robust Target Models for Video Object Segmentation","date":"2020-02-27","rows_on_this_dataset":1,"code_links":2,"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/copy-and-paste-networks-for-deep-video","title":"Copy-and-Paste Networks for Deep Video Inpainting","date":"2019-08-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/learnable-gated-temporal-shift-module-for","title":"Learnable Gated Temporal Shift Module for Deep Video Inpainting","date":"2019-07-02","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deep-flow-guided-video-inpainting","title":"Deep Flow-Guided Video Inpainting","date":"2019-05-08","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-video-inpainting","title":"Deep Video Inpainting","date":"2019-05-05","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/video-object-segmentation-using-space-time","title":"Video Object Segmentation using Space-Time Memory Networks","date":"2019-04-01","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":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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":2,"code_links":1,"syntology":null},{"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":1,"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/youtube-vos-sequence-to-sequence-video-object","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","date":"2018-09-03","rows_on_this_dataset":2,"code_links":4,"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":3,"code_links":1,"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":1,"code_links":0,"syntology":null},{"paper":"/paper/one-shot-video-object-segmentation","title":"One-Shot Video Object Segmentation","date":"2016-11-16","rows_on_this_dataset":3,"code_links":8,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":21,"samples_harvested":168,"samples_ran":90,"samples_unverified":78,"pointer_only_for_licence":73,"papers_with_no_sample_that_ran":3,"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."}