{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":91,"of":91,"counts":{"papers_with_a_benchmark_row":91,"with_a_code_link":76,"where_syntology_ran_a_sample":40,"not_listed_spam_title":0,"listed":91,"listed_where_code_ran":40,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":37,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":37,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}}}},{"paper":"/paper/memory-matching-is-not-enough-jointly","slug":"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","arxiv_id":"2409.14343","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/2408-00714","slug":"2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","arxiv_id":"2408.00714","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":49,"samples_ran":40,"samples_constructed":9,"samples_ran_checked":29,"samples_ran_instrument_failed":11,"samples_unverified":9,"pointer_only_for_licence":8,"official":{"repos":["facebookresearch/sam2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/2408-00714#ran","syntology_url":"https://syntology.ai/paper/2408.00714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00714"}}}},{"paper":"/paper/safari-adaptive-sequence-transformer-for","slug":"safari-adaptive-sequence-transformer-for","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","date":"2024-07-02","arxiv_id":"2407.02389","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-referring-image-segmentation-using","slug":"improving-referring-image-segmentation-using","title":"Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding","date":"2024-04-12","arxiv_id":"2404.08590","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-temporally-consistent-referring-video","slug":"towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","date":"2024-03-28","arxiv_id":"2403.19407","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":10,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["bo-miao/HTR"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-temporally-consistent-referring-video#ran","syntology_url":"https://syntology.ai/paper/2403.19407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19407"}}}},{"paper":"/paper/univs-unified-and-universal-video","slug":"univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","arxiv_id":"2402.18115","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":14,"official":{"repos":["minghanli/univs"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/univs-unified-and-universal-video#ran","syntology_url":"https://syntology.ai/paper/2402.18115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18115"}}}},{"paper":"/paper/putting-the-object-back-into-video-object","slug":"putting-the-object-back-into-video-object","title":"Putting the Object Back into Video Object Segmentation","date":"2023-10-19","arxiv_id":"2310.12982","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["hkchengrex/Cutie"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/putting-the-object-back-into-video-object#ran","syntology_url":"https://syntology.ai/paper/2310.12982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12982"}}}},{"paper":"/paper/tracking-anything-with-decoupled-video","slug":"tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","arxiv_id":"2309.03903","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":10,"official":{"repos":["hkchengrex/Tracking-Anything-with-DEVA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tracking-anything-with-decoupled-video#ran","syntology_url":"https://syntology.ai/paper/2309.03903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03903"}}}},{"paper":"/paper/spectrum-guided-multi-granularity-referring","slug":"spectrum-guided-multi-granularity-referring","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","date":"2023-07-25","arxiv_id":"2307.13537","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":9,"official":{"repos":["bo-miao/sgmg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spectrum-guided-multi-granularity-referring#ran","syntology_url":"https://syntology.ai/paper/2307.13537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13537"}}}},{"paper":"/paper/trickvos-a-bag-of-tricks-for-video-object","slug":"trickvos-a-bag-of-tricks-for-video-object","title":"TrickVOS: A Bag of Tricks for Video Object Segmentation","date":"2023-06-27","arxiv_id":"2306.15377","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","slug":"a-dynamic-multi-scale-voxel-flow-network-for","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","date":"2023-03-17","arxiv_id":"2303.09875","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["megvii-research/CVPR2023-DMVFN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-dynamic-multi-scale-voxel-flow-network-for#ran","syntology_url":"https://syntology.ai/paper/2303.09875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09875"}}}},{"paper":"/paper/mobilevos-real-time-video-object-segmentation","slug":"mobilevos-real-time-video-object-segmentation","title":"MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation","date":"2023-03-14","arxiv_id":"2303.07815","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/universal-instance-perception-as-object","slug":"universal-instance-perception-as-object","title":"Universal Instance Perception as Object Discovery and Retrieval","date":"2023-03-12","arxiv_id":"2303.06674","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["MasterBin-IIAU/UNINEXT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/universal-instance-perception-as-object#ran","syntology_url":"https://syntology.ai/paper/2303.06674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06674"}}}},{"paper":"/paper/polyformer-referring-image-segmentation-as","slug":"polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","arxiv_id":"2302.07387","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["amazon-science/polygon-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/polyformer-referring-image-segmentation-as#ran","syntology_url":"https://syntology.ai/paper/2302.07387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07387"}}}},{"paper":"/paper/tarvis-a-unified-approach-for-target-based","slug":"tarvis-a-unified-approach-for-target-based","title":"TarViS: A Unified Approach for Target-based Video Segmentation","date":"2023-01-06","arxiv_id":"2301.02657","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["Ali2500/TarViS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tarvis-a-unified-approach-for-target-based#ran","syntology_url":"https://syntology.ai/paper/2301.02657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02657"}}}},{"paper":"/paper/look-before-you-match-instance-understanding","slug":"look-before-you-match-instance-understanding","title":"Look Before You Match: Instance Understanding Matters in Video Object Segmentation","date":"2022-12-13","arxiv_id":"2212.06826","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/decoupling-features-in-hierarchical","slug":"decoupling-features-in-hierarchical","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","date":"2022-10-18","arxiv_id":"2210.09782","rows_on_this_dataset":12,"code_links":2,"syntology":null},{"paper":"/paper/swem-towards-real-time-video-object-1","slug":"swem-towards-real-time-video-object-1","title":"SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization","date":"2022-08-22","arxiv_id":"2208.10128","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/batman-bilateral-attention-transformer-in","slug":"batman-bilateral-attention-transformer-in","title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","date":"2022-08-01","arxiv_id":"2208.01159","rows_on_this_dataset":22,"code_links":0,"syntology":null},{"paper":"/paper/region-aware-video-object-segmentation-with","slug":"region-aware-video-object-segmentation-with","title":"Region Aware Video Object Segmentation with Deep Motion Modeling","date":"2022-07-21","arxiv_id":"2207.10258","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-quality-aware-dynamic-memory-for","slug":"learning-quality-aware-dynamic-memory-for","title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","date":"2022-07-16","arxiv_id":"2207.07922","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["workforai/qdmn"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-quality-aware-dynamic-memory-for#ran","syntology_url":"https://syntology.ai/paper/2207.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07922"}}}},{"paper":"/paper/xmem-long-term-video-object-segmentation-with","slug":"xmem-long-term-video-object-segmentation-with","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","date":"2022-07-14","arxiv_id":"2207.07115","rows_on_this_dataset":14,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["hkchengrex/XMem"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xmem-long-term-video-object-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2207.07115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07115"}}}},{"paper":"/paper/towards-robust-video-object-segmentation-with","slug":"towards-robust-video-object-segmentation-with","title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","date":"2022-07-02","arxiv_id":"2207.00887","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["jerryx1110/robust-video-object-segmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-robust-video-object-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2207.00887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.00887"}}}},{"paper":"/paper/associating-objects-with-scalable","slug":"associating-objects-with-scalable","title":"Scalable Video Object Segmentation with Identification Mechanism","date":"2022-03-22","arxiv_id":"2203.11442","rows_on_this_dataset":11,"code_links":2,"syntology":null},{"paper":"/paper/language-as-queries-for-referring-video","slug":"language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","arxiv_id":"2201.00487","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":8,"official":{"repos":["wjn922/referformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-as-queries-for-referring-video#ran","syntology_url":"https://syntology.ai/paper/2201.00487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00487"}}}},{"paper":"/paper/reliable-propagation-correction-modulation","slug":"reliable-propagation-correction-modulation","title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","date":"2021-12-06","arxiv_id":"2112.02853","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["jerryx1110/rpcmvos"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/reliable-propagation-correction-modulation#ran","syntology_url":"https://syntology.ai/paper/2112.02853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02853"}}}},{"paper":"/paper/hierarchical-interaction-network-for-video","slug":"hierarchical-interaction-network-for-video","title":"Hierarchical interaction network for video object segmentation from referring expressions","date":"2021-11-22","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dense-unsupervised-learning-for-video","slug":"dense-unsupervised-learning-for-video","title":"Dense Unsupervised Learning for Video Segmentation","date":"2021-11-11","arxiv_id":"2111.06265","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["visinf/dense-ulearn-vos"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dense-unsupervised-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2111.06265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06265"}}}},{"paper":"/paper/hierarchical-memory-matching-network-for","slug":"hierarchical-memory-matching-network-for","title":"Hierarchical Memory Matching Network for Video Object Segmentation","date":"2021-09-23","arxiv_id":"2109.11404","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":4,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["hongje/hmmn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hierarchical-memory-matching-network-for#ran","syntology_url":"https://syntology.ai/paper/2109.11404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11404"}}}},{"paper":"/paper/joint-inductive-and-transductive-learning-for","slug":"joint-inductive-and-transductive-learning-for","title":"Joint Inductive and Transductive Learning for Video Object Segmentation","date":"2021-08-08","arxiv_id":"2108.03679","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["maoyunyao/joint"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/joint-inductive-and-transductive-learning-for#ran","syntology_url":"https://syntology.ai/paper/2108.03679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03679"}}}},{"paper":"/paper/self-supervised-video-object-segmentation-by-1","slug":"self-supervised-video-object-segmentation-by-1","title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","date":"2021-07-27","arxiv_id":"2107.12569","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["bo-miao/MAMP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-supervised-video-object-segmentation-by-1#ran","syntology_url":"https://syntology.ai/paper/2107.12569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12569"}}}},{"paper":"/paper/do-different-tracking-tasks-require-different","slug":"do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","date":"2021-07-05","arxiv_id":"2107.02156","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":6,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["Zhongdao/UniTrack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":11,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/do-different-tracking-tasks-require-different#ran","syntology_url":"https://syntology.ai/paper/2107.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02156"}}}},{"paper":"/paper/rethinking-space-time-networks-with-improved","slug":"rethinking-space-time-networks-with-improved","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","date":"2021-06-09","arxiv_id":"2106.05210","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":6,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["hkchengrex/STCN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rethinking-space-time-networks-with-improved#ran","syntology_url":"https://syntology.ai/paper/2106.05210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05210"}}}},{"paper":"/paper/synthref-generation-of-synthetic-referring","slug":"synthref-generation-of-synthetic-referring","title":"SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation","date":"2021-06-08","arxiv_id":"2106.04403","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/vitae-vision-transformer-advanced-by","slug":"vitae-vision-transformer-advanced-by","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","date":"2021-06-07","arxiv_id":"2106.03348","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["Annbless/ViTAE"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vitae-vision-transformer-advanced-by#ran","syntology_url":"https://syntology.ai/paper/2106.03348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03348"}}}},{"paper":"/paper/associating-objects-with-transformers-for","slug":"associating-objects-with-transformers-for","title":"Associating Objects with Transformers for Video Object Segmentation","date":"2021-06-04","arxiv_id":"2106.02638","rows_on_this_dataset":13,"code_links":2,"syntology":null},{"paper":"/paper/emerging-properties-in-self-supervised-vision","slug":"emerging-properties-in-self-supervised-vision","title":"Emerging Properties in Self-Supervised Vision Transformers","date":"2021-04-29","arxiv_id":"2104.14294","rows_on_this_dataset":1,"code_links":32,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/dino"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/emerging-properties-in-self-supervised-vision#ran","syntology_url":"https://syntology.ai/paper/2104.14294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14294"}}}},{"paper":"/paper/guided-interactive-video-object-segmentation","slug":"guided-interactive-video-object-segmentation","title":"Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps","date":"2021-04-21","arxiv_id":"2104.10386","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":7,"samples_constructed":2,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["yuk6heo/GIS-RAmap"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/guided-interactive-video-object-segmentation#ran","syntology_url":"https://syntology.ai/paper/2104.10386","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10386"}}}},{"paper":"/paper/video-instance-segmentation-with-a-propose","slug":"video-instance-segmentation-with-a-propose","title":"Video Instance Segmentation with a Propose-Reduce Paradigm","date":"2021-03-25","arxiv_id":"2103.13746","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["dvlab-research/proposereduce"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-instance-segmentation-with-a-propose#ran","syntology_url":"https://syntology.ai/paper/2103.13746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13746"}}}},{"paper":"/paper/efficient-regional-memory-network-for-video","slug":"efficient-regional-memory-network-for-video","title":"Efficient Regional Memory Network for Video Object Segmentation","date":"2021-03-24","arxiv_id":"2103.12934","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["hzxie/RMNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-regional-memory-network-for-video#ran","syntology_url":"https://syntology.ai/paper/2103.12934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12934"}}}},{"paper":"/paper/modular-interactive-video-object-segmentation","slug":"modular-interactive-video-object-segmentation","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","date":"2021-03-14","arxiv_id":"2103.07941","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":10,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["hkchengrex/MiVOS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/modular-interactive-video-object-segmentation#ran","syntology_url":"https://syntology.ai/paper/2103.07941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07941"}}}},{"paper":"/paper/fast-interactive-video-object-segmentation","slug":"fast-interactive-video-object-segmentation","title":"Fast Interactive Video Object Segmentation with Graph Neural Networks","date":"2021-03-05","arxiv_id":"2103.03821","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/separable-structure-modeling-for-semi","slug":"separable-structure-modeling-for-semi","title":"Separable Structure Modeling for Semi-supervised Video Object Segmentation","date":"2021-02-18","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/make-one-shot-video-object-segmentation-1","slug":"make-one-shot-video-object-segmentation-1","title":"Make One-Shot Video Object Segmentation Efficient Again","date":"2020-12-03","arxiv_id":"2012.01866","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/video-object-segmentation-with-adaptive","slug":"video-object-segmentation-with-adaptive","title":"Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement","date":"2020-10-15","arxiv_id":"2010.07958","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/collaborative-video-object-segmentation-by-1","slug":"collaborative-video-object-segmentation-by-1","title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","date":"2020-10-13","arxiv_id":"2010.06349","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["z-x-yang/CFBI"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/collaborative-video-object-segmentation-by-1#ran","syntology_url":"https://syntology.ai/paper/2010.06349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06349"}}}},{"paper":"/paper/refvos-a-closer-look-at-referring-expressions","slug":"refvos-a-closer-look-at-referring-expressions","title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","date":"2020-10-01","arxiv_id":"2010.00263","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/lsmvos-long-short-term-similarity-matching","slug":"lsmvos-long-short-term-similarity-matching","title":"LSMVOS: Long-Short-Term Similarity Matching for Video Object","date":"2020-09-02","arxiv_id":"2009.00771","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/matnet-motion-attentive-transition-network","slug":"matnet-motion-attentive-transition-network","title":"MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation","date":"2020-08-20","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/urvos-unified-referring-video-object","slug":"urvos-unified-referring-video-object","title":"URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark","date":"2020-08-01","arxiv_id":null,"rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/interactive-video-object-segmentation-using","slug":"interactive-video-object-segmentation-using","title":"Interactive Video Object Segmentation Using Global and Local Transfer Modules","date":"2020-07-16","arxiv_id":"2007.08139","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["yuk6heo/IVOS-ATNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/interactive-video-object-segmentation-using#ran","syntology_url":"https://syntology.ai/paper/2007.08139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08139"}}}},{"paper":"/paper/kernelized-memory-network-for-video-object","slug":"kernelized-memory-network-for-video-object","title":"Kernelized Memory Network for Video Object Segmentation","date":"2020-07-16","arxiv_id":"2007.08270","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/alba-reinforcement-learning-for-video-object","slug":"alba-reinforcement-learning-for-video-object","title":"ALBA : Reinforcement Learning for Video Object Segmentation","date":"2020-05-26","arxiv_id":"2005.13039","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-transductive-approach-for-video-object","slug":"a-transductive-approach-for-video-object","title":"A Transductive Approach for Video Object Segmentation","date":"2020-04-15","arxiv_id":"2004.07193","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/memory-aggregation-networks-for-efficient","slug":"memory-aggregation-networks-for-efficient","title":"Memory Aggregation Networks for Efficient Interactive Video Object Segmentation","date":"2020-03-30","arxiv_id":"2003.13246","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/collaborative-video-object-segmentation-by","slug":"collaborative-video-object-segmentation-by","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","date":"2020-03-18","arxiv_id":"2003.08333","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/stem-seg-spatio-temporal-embeddings-for","slug":"stem-seg-spatio-temporal-embeddings-for","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","date":"2020-03-18","arxiv_id":"2003.08429","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-video-object-segmentation-from-2","slug":"learning-video-object-segmentation-from-2","title":"Learning Video Object Segmentation from Unlabeled Videos","date":"2020-03-10","arxiv_id":"2003.05020","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["carrierlxk/MuG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-video-object-segmentation-from-2#ran","syntology_url":"https://syntology.ai/paper/2003.05020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05020"}}}},{"paper":"/paper/mast-a-memory-augmented-self-supervised","slug":"mast-a-memory-augmented-self-supervised","title":"MAST: A Memory-Augmented Self-supervised Tracker","date":"2020-02-18","arxiv_id":"2002.07793","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/unovost-unsupervised-offline-video-object","slug":"unovost-unsupervised-offline-video-object","title":"UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking","date":"2020-01-15","arxiv_id":"2001.05425","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unovost-unsupervised-offline-video-object#ran","syntology_url":"https://syntology.ai/paper/2001.05425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.05425"}}}},{"paper":"/paper/siam-r-cnn-visual-tracking-by-re-detection","slug":"siam-r-cnn-visual-tracking-by-re-detection","title":"Siam R-CNN: Visual Tracking by Re-Detection","date":"2019-11-28","arxiv_id":"1911.12836","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/siam-r-cnn-visual-tracking-by-re-detection#ran","syntology_url":"https://syntology.ai/paper/1911.12836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12836"}}}},{"paper":"/paper/agss-vos-attention-guided-single-shot-video","slug":"agss-vos-attention-guided-single-shot-video","title":"AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation","date":"2019-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/capsulevos-semi-supervised-video-object","slug":"capsulevos-semi-supervised-video-object","title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","date":"2019-09-30","arxiv_id":"1910.00132","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/joint-task-self-supervised-learning-for","slug":"joint-task-self-supervised-learning-for","title":"Joint-task Self-supervised Learning for Temporal Correspondence","date":"2019-09-26","arxiv_id":"1909.11895","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":23,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":2,"official":{"repos":["Liusifei/UVC"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/joint-task-self-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/1909.11895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11895"}}}},{"paper":"/paper/ranet-ranking-attention-network-for-fast","slug":"ranet-ranking-attention-network-for-fast","title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","date":"2019-08-19","arxiv_id":"1908.06647","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Storife/RANet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ranet-ranking-attention-network-for-fast#ran","syntology_url":"https://syntology.ai/paper/1908.06647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.06647"}}}},{"paper":"/paper/proposal-tracking-and-segmentation-pts-a","slug":"proposal-tracking-and-segmentation-pts-a","title":"Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation","date":"2019-07-02","arxiv_id":"1907.01203","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-unsupervised-video-object","slug":"learning-unsupervised-video-object","title":"Learning Unsupervised Video Object Segmentation Through Visual Attention","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-learning-for-video","slug":"self-supervised-learning-for-video","title":"Self-supervised Learning for Video Correspondence Flow","date":"2019-05-02","arxiv_id":"1905.00875","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fast-user-guided-video-object-segmentation-by","slug":"fast-user-guided-video-object-segmentation-by","title":"Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks","date":"2019-04-22","arxiv_id":"1904.09791","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/190408141","slug":"190408141","title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","date":"2019-04-17","arxiv_id":"1904.08141","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/spatiotemporal-cnn-for-video-object","slug":"spatiotemporal-cnn-for-video-object","title":"Spatiotemporal CNN for Video Object Segmentation","date":"2019-04-04","arxiv_id":"1904.02363","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["longyin880815/STCNN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spatiotemporal-cnn-for-video-object#ran","syntology_url":"https://syntology.ai/paper/1904.02363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02363"}}}},{"paper":"/paper/video-object-segmentation-using-space-time","slug":"video-object-segmentation-using-space-time","title":"Video Object Segmentation using Space-Time Memory Networks","date":"2019-04-01","arxiv_id":"1904.00607","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-object-segmentation-using-space-time#ran","syntology_url":"https://syntology.ai/paper/1904.00607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00607"}}}},{"paper":"/paper/learning-correspondence-from-the-cycle","slug":"learning-correspondence-from-the-cycle","title":"Learning Correspondence from the Cycle-Consistency of Time","date":"2019-03-18","arxiv_id":"1903.07593","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rvos-end-to-end-recurrent-network-for-video","slug":"rvos-end-to-end-recurrent-network-for-video","title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","date":"2019-03-13","arxiv_id":"1903.05612","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/feelvos-fast-end-to-end-embedding-learning","slug":"feelvos-fast-end-to-end-embedding-learning","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","date":"2019-02-25","arxiv_id":"1902.09513","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/feelvos-fast-end-to-end-embedding-learning#ran","syntology_url":"https://syntology.ai/paper/1902.09513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09513"}}}},{"paper":"/paper/fast-online-object-tracking-and-segmentation","slug":"fast-online-object-tracking-and-segmentation","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","date":"2018-12-12","arxiv_id":"1812.05050","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fast-online-object-tracking-and-segmentation#ran","syntology_url":"https://syntology.ai/paper/1812.05050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05050"}}}},{"paper":"/paper/a-generative-appearance-model-for-end-to-end","slug":"a-generative-appearance-model-for-end-to-end","title":"A Generative Appearance Model for End-to-end Video Object Segmentation","date":"2018-11-28","arxiv_id":"1811.11611","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-generative-appearance-model-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/1811.11611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11611"}}}},{"paper":"/paper/videomatch-matching-based-video-object","slug":"videomatch-matching-based-video-object","title":"VideoMatch: Matching based Video Object Segmentation","date":"2018-09-04","arxiv_id":"1809.01123","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/pyramid-dilated-deeper-convlstm-for-video","slug":"pyramid-dilated-deeper-convlstm-for-video","title":"Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection","date":"2018-09-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/premvos-proposal-generation-refinement-and","slug":"premvos-proposal-generation-refinement-and","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","date":"2018-07-24","arxiv_id":"1807.09190","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/premvos-proposal-generation-refinement-and#ran","syntology_url":"https://syntology.ai/paper/1807.09190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09190"}}}},{"paper":"/paper/fast-and-accurate-online-video-object","slug":"fast-and-accurate-online-video-object","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","date":"2018-06-06","arxiv_id":"1806.02323","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":3,"official":{"repos":["JingchunCheng/FAVOS"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fast-and-accurate-online-video-object#ran","syntology_url":"https://syntology.ai/paper/1806.02323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02323"}}}},{"paper":"/paper/fast-video-object-segmentation-by-reference","slug":"fast-video-object-segmentation-by-reference","title":"Fast Video Object Segmentation by Reference-Guided Mask Propagation","date":"2018-06-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/cnn-in-mrf-video-object-segmentation-via","slug":"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","arxiv_id":"1803.09453","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/video-object-segmentation-with-language","slug":"video-object-segmentation-with-language","title":"Video Object Segmentation with Language Referring Expressions","date":"2018-03-21","arxiv_id":"1803.08006","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/efficient-video-object-segmentation-via","slug":"efficient-video-object-segmentation-via","title":"Efficient Video Object Segmentation via Network Modulation","date":"2018-02-04","arxiv_id":"1802.01218","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/video-object-segmentation-without-temporal","slug":"video-object-segmentation-without-temporal","title":"Video Object Segmentation Without Temporal Information","date":"2017-09-18","arxiv_id":"1709.06031","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/online-adaptation-of-convolutional-neural","slug":"online-adaptation-of-convolutional-neural","title":"Online Adaptation of Convolutional Neural Networks for Video Object Segmentation","date":"2017-06-28","arxiv_id":"1706.09364","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/lucid-data-dreaming-for-video-object","slug":"lucid-data-dreaming-for-video-object","title":"Lucid Data Dreaming for Video Object Segmentation","date":"2017-03-28","arxiv_id":"1703.09554","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/video-frame-synthesis-using-deep-voxel-flow","slug":"video-frame-synthesis-using-deep-voxel-flow","title":"Video Frame Synthesis using Deep Voxel Flow","date":"2017-02-08","arxiv_id":"1702.02463","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-frame-synthesis-using-deep-voxel-flow#ran","syntology_url":"https://syntology.ai/paper/1702.02463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02463"}}}},{"paper":"/paper/one-shot-video-object-segmentation","slug":"one-shot-video-object-segmentation","title":"One-Shot Video Object Segmentation","date":"2016-11-16","arxiv_id":"1611.05198","rows_on_this_dataset":2,"code_links":8,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}}}},{"paper":"/paper/memory-matching-is-not-enough-jointly","slug":"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","arxiv_id":"2409.14343","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/2408-00714","slug":"2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","arxiv_id":"2408.00714","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":49,"samples_ran":40,"samples_constructed":9,"samples_ran_checked":29,"samples_ran_instrument_failed":11,"samples_unverified":9,"pointer_only_for_licence":8,"official":{"repos":["facebookresearch/sam2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/2408-00714#ran","syntology_url":"https://syntology.ai/paper/2408.00714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00714"}}}},{"paper":"/paper/safari-adaptive-sequence-transformer-for","slug":"safari-adaptive-sequence-transformer-for","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","date":"2024-07-02","arxiv_id":"2407.02389","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-referring-image-segmentation-using","slug":"improving-referring-image-segmentation-using","title":"Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding","date":"2024-04-12","arxiv_id":"2404.08590","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-temporally-consistent-referring-video","slug":"towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","date":"2024-03-28","arxiv_id":"2403.19407","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":10,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["bo-miao/HTR"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-temporally-consistent-referring-video#ran","syntology_url":"https://syntology.ai/paper/2403.19407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19407"}}}},{"paper":"/paper/univs-unified-and-universal-video","slug":"univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","arxiv_id":"2402.18115","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":14,"official":{"repos":["minghanli/univs"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/univs-unified-and-universal-video#ran","syntology_url":"https://syntology.ai/paper/2402.18115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18115"}}}},{"paper":"/paper/putting-the-object-back-into-video-object","slug":"putting-the-object-back-into-video-object","title":"Putting the Object Back into Video Object Segmentation","date":"2023-10-19","arxiv_id":"2310.12982","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["hkchengrex/Cutie"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/putting-the-object-back-into-video-object#ran","syntology_url":"https://syntology.ai/paper/2310.12982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12982"}}}},{"paper":"/paper/tracking-anything-with-decoupled-video","slug":"tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","arxiv_id":"2309.03903","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":10,"official":{"repos":["hkchengrex/Tracking-Anything-with-DEVA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tracking-anything-with-decoupled-video#ran","syntology_url":"https://syntology.ai/paper/2309.03903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03903"}}}},{"paper":"/paper/spectrum-guided-multi-granularity-referring","slug":"spectrum-guided-multi-granularity-referring","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","date":"2023-07-25","arxiv_id":"2307.13537","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":9,"official":{"repos":["bo-miao/sgmg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spectrum-guided-multi-granularity-referring#ran","syntology_url":"https://syntology.ai/paper/2307.13537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13537"}}}},{"paper":"/paper/trickvos-a-bag-of-tricks-for-video-object","slug":"trickvos-a-bag-of-tricks-for-video-object","title":"TrickVOS: A Bag of Tricks for Video Object Segmentation","date":"2023-06-27","arxiv_id":"2306.15377","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","slug":"a-dynamic-multi-scale-voxel-flow-network-for","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","date":"2023-03-17","arxiv_id":"2303.09875","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["megvii-research/CVPR2023-DMVFN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-dynamic-multi-scale-voxel-flow-network-for#ran","syntology_url":"https://syntology.ai/paper/2303.09875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09875"}}}},{"paper":"/paper/mobilevos-real-time-video-object-segmentation","slug":"mobilevos-real-time-video-object-segmentation","title":"MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation","date":"2023-03-14","arxiv_id":"2303.07815","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/universal-instance-perception-as-object","slug":"universal-instance-perception-as-object","title":"Universal Instance Perception as Object Discovery and Retrieval","date":"2023-03-12","arxiv_id":"2303.06674","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["MasterBin-IIAU/UNINEXT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/universal-instance-perception-as-object#ran","syntology_url":"https://syntology.ai/paper/2303.06674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06674"}}}},{"paper":"/paper/polyformer-referring-image-segmentation-as","slug":"polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","arxiv_id":"2302.07387","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["amazon-science/polygon-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/polyformer-referring-image-segmentation-as#ran","syntology_url":"https://syntology.ai/paper/2302.07387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07387"}}}},{"paper":"/paper/tarvis-a-unified-approach-for-target-based","slug":"tarvis-a-unified-approach-for-target-based","title":"TarViS: A Unified Approach for Target-based Video Segmentation","date":"2023-01-06","arxiv_id":"2301.02657","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["Ali2500/TarViS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tarvis-a-unified-approach-for-target-based#ran","syntology_url":"https://syntology.ai/paper/2301.02657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02657"}}}},{"paper":"/paper/look-before-you-match-instance-understanding","slug":"look-before-you-match-instance-understanding","title":"Look Before You Match: Instance Understanding Matters in Video Object Segmentation","date":"2022-12-13","arxiv_id":"2212.06826","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/decoupling-features-in-hierarchical","slug":"decoupling-features-in-hierarchical","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","date":"2022-10-18","arxiv_id":"2210.09782","rows_on_this_dataset":12,"code_links":2,"syntology":null},{"paper":"/paper/swem-towards-real-time-video-object-1","slug":"swem-towards-real-time-video-object-1","title":"SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization","date":"2022-08-22","arxiv_id":"2208.10128","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/batman-bilateral-attention-transformer-in","slug":"batman-bilateral-attention-transformer-in","title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","date":"2022-08-01","arxiv_id":"2208.01159","rows_on_this_dataset":22,"code_links":0,"syntology":null},{"paper":"/paper/region-aware-video-object-segmentation-with","slug":"region-aware-video-object-segmentation-with","title":"Region Aware Video Object Segmentation with Deep Motion Modeling","date":"2022-07-21","arxiv_id":"2207.10258","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-quality-aware-dynamic-memory-for","slug":"learning-quality-aware-dynamic-memory-for","title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","date":"2022-07-16","arxiv_id":"2207.07922","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["workforai/qdmn"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-quality-aware-dynamic-memory-for#ran","syntology_url":"https://syntology.ai/paper/2207.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07922"}}}},{"paper":"/paper/xmem-long-term-video-object-segmentation-with","slug":"xmem-long-term-video-object-segmentation-with","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","date":"2022-07-14","arxiv_id":"2207.07115","rows_on_this_dataset":14,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["hkchengrex/XMem"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xmem-long-term-video-object-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2207.07115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07115"}}}},{"paper":"/paper/towards-robust-video-object-segmentation-with","slug":"towards-robust-video-object-segmentation-with","title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","date":"2022-07-02","arxiv_id":"2207.00887","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["jerryx1110/robust-video-object-segmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-robust-video-object-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2207.00887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.00887"}}}},{"paper":"/paper/associating-objects-with-scalable","slug":"associating-objects-with-scalable","title":"Scalable Video Object Segmentation with Identification Mechanism","date":"2022-03-22","arxiv_id":"2203.11442","rows_on_this_dataset":11,"code_links":2,"syntology":null},{"paper":"/paper/language-as-queries-for-referring-video","slug":"language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","arxiv_id":"2201.00487","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":8,"official":{"repos":["wjn922/referformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-as-queries-for-referring-video#ran","syntology_url":"https://syntology.ai/paper/2201.00487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00487"}}}},{"paper":"/paper/reliable-propagation-correction-modulation","slug":"reliable-propagation-correction-modulation","title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","date":"2021-12-06","arxiv_id":"2112.02853","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["jerryx1110/rpcmvos"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/reliable-propagation-correction-modulation#ran","syntology_url":"https://syntology.ai/paper/2112.02853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02853"}}}},{"paper":"/paper/hierarchical-interaction-network-for-video","slug":"hierarchical-interaction-network-for-video","title":"Hierarchical interaction network for video object segmentation from referring expressions","date":"2021-11-22","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dense-unsupervised-learning-for-video","slug":"dense-unsupervised-learning-for-video","title":"Dense Unsupervised Learning for Video Segmentation","date":"2021-11-11","arxiv_id":"2111.06265","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["visinf/dense-ulearn-vos"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dense-unsupervised-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2111.06265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06265"}}}},{"paper":"/paper/hierarchical-memory-matching-network-for","slug":"hierarchical-memory-matching-network-for","title":"Hierarchical Memory Matching Network for Video Object Segmentation","date":"2021-09-23","arxiv_id":"2109.11404","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":4,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["hongje/hmmn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hierarchical-memory-matching-network-for#ran","syntology_url":"https://syntology.ai/paper/2109.11404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11404"}}}},{"paper":"/paper/joint-inductive-and-transductive-learning-for","slug":"joint-inductive-and-transductive-learning-for","title":"Joint Inductive and Transductive Learning for Video Object Segmentation","date":"2021-08-08","arxiv_id":"2108.03679","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["maoyunyao/joint"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/joint-inductive-and-transductive-learning-for#ran","syntology_url":"https://syntology.ai/paper/2108.03679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03679"}}}},{"paper":"/paper/self-supervised-video-object-segmentation-by-1","slug":"self-supervised-video-object-segmentation-by-1","title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","date":"2021-07-27","arxiv_id":"2107.12569","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["bo-miao/MAMP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-supervised-video-object-segmentation-by-1#ran","syntology_url":"https://syntology.ai/paper/2107.12569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12569"}}}},{"paper":"/paper/do-different-tracking-tasks-require-different","slug":"do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","date":"2021-07-05","arxiv_id":"2107.02156","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":6,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["Zhongdao/UniTrack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":11,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/do-different-tracking-tasks-require-different#ran","syntology_url":"https://syntology.ai/paper/2107.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02156"}}}},{"paper":"/paper/rethinking-space-time-networks-with-improved","slug":"rethinking-space-time-networks-with-improved","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","date":"2021-06-09","arxiv_id":"2106.05210","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":6,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["hkchengrex/STCN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rethinking-space-time-networks-with-improved#ran","syntology_url":"https://syntology.ai/paper/2106.05210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05210"}}}},{"paper":"/paper/synthref-generation-of-synthetic-referring","slug":"synthref-generation-of-synthetic-referring","title":"SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation","date":"2021-06-08","arxiv_id":"2106.04403","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/vitae-vision-transformer-advanced-by","slug":"vitae-vision-transformer-advanced-by","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","date":"2021-06-07","arxiv_id":"2106.03348","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["Annbless/ViTAE"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vitae-vision-transformer-advanced-by#ran","syntology_url":"https://syntology.ai/paper/2106.03348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03348"}}}},{"paper":"/paper/associating-objects-with-transformers-for","slug":"associating-objects-with-transformers-for","title":"Associating Objects with Transformers for Video Object Segmentation","date":"2021-06-04","arxiv_id":"2106.02638","rows_on_this_dataset":13,"code_links":2,"syntology":null},{"paper":"/paper/emerging-properties-in-self-supervised-vision","slug":"emerging-properties-in-self-supervised-vision","title":"Emerging Properties in Self-Supervised Vision Transformers","date":"2021-04-29","arxiv_id":"2104.14294","rows_on_this_dataset":1,"code_links":32,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/dino"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/emerging-properties-in-self-supervised-vision#ran","syntology_url":"https://syntology.ai/paper/2104.14294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14294"}}}},{"paper":"/paper/guided-interactive-video-object-segmentation","slug":"guided-interactive-video-object-segmentation","title":"Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps","date":"2021-04-21","arxiv_id":"2104.10386","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":7,"samples_constructed":2,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["yuk6heo/GIS-RAmap"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/guided-interactive-video-object-segmentation#ran","syntology_url":"https://syntology.ai/paper/2104.10386","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10386"}}}},{"paper":"/paper/video-instance-segmentation-with-a-propose","slug":"video-instance-segmentation-with-a-propose","title":"Video Instance Segmentation with a Propose-Reduce Paradigm","date":"2021-03-25","arxiv_id":"2103.13746","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["dvlab-research/proposereduce"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-instance-segmentation-with-a-propose#ran","syntology_url":"https://syntology.ai/paper/2103.13746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13746"}}}},{"paper":"/paper/efficient-regional-memory-network-for-video","slug":"efficient-regional-memory-network-for-video","title":"Efficient Regional Memory Network for Video Object Segmentation","date":"2021-03-24","arxiv_id":"2103.12934","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["hzxie/RMNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-regional-memory-network-for-video#ran","syntology_url":"https://syntology.ai/paper/2103.12934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12934"}}}},{"paper":"/paper/modular-interactive-video-object-segmentation","slug":"modular-interactive-video-object-segmentation","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","date":"2021-03-14","arxiv_id":"2103.07941","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":10,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["hkchengrex/MiVOS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/modular-interactive-video-object-segmentation#ran","syntology_url":"https://syntology.ai/paper/2103.07941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07941"}}}},{"paper":"/paper/fast-interactive-video-object-segmentation","slug":"fast-interactive-video-object-segmentation","title":"Fast Interactive Video Object Segmentation with Graph Neural Networks","date":"2021-03-05","arxiv_id":"2103.03821","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/separable-structure-modeling-for-semi","slug":"separable-structure-modeling-for-semi","title":"Separable Structure Modeling for Semi-supervised Video Object Segmentation","date":"2021-02-18","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/make-one-shot-video-object-segmentation-1","slug":"make-one-shot-video-object-segmentation-1","title":"Make One-Shot Video Object Segmentation Efficient Again","date":"2020-12-03","arxiv_id":"2012.01866","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/video-object-segmentation-with-adaptive","slug":"video-object-segmentation-with-adaptive","title":"Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement","date":"2020-10-15","arxiv_id":"2010.07958","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/collaborative-video-object-segmentation-by-1","slug":"collaborative-video-object-segmentation-by-1","title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","date":"2020-10-13","arxiv_id":"2010.06349","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["z-x-yang/CFBI"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/collaborative-video-object-segmentation-by-1#ran","syntology_url":"https://syntology.ai/paper/2010.06349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06349"}}}},{"paper":"/paper/refvos-a-closer-look-at-referring-expressions","slug":"refvos-a-closer-look-at-referring-expressions","title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","date":"2020-10-01","arxiv_id":"2010.00263","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/lsmvos-long-short-term-similarity-matching","slug":"lsmvos-long-short-term-similarity-matching","title":"LSMVOS: Long-Short-Term Similarity Matching for Video Object","date":"2020-09-02","arxiv_id":"2009.00771","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/matnet-motion-attentive-transition-network","slug":"matnet-motion-attentive-transition-network","title":"MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation","date":"2020-08-20","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/urvos-unified-referring-video-object","slug":"urvos-unified-referring-video-object","title":"URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark","date":"2020-08-01","arxiv_id":null,"rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/interactive-video-object-segmentation-using","slug":"interactive-video-object-segmentation-using","title":"Interactive Video Object Segmentation Using Global and Local Transfer Modules","date":"2020-07-16","arxiv_id":"2007.08139","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["yuk6heo/IVOS-ATNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/interactive-video-object-segmentation-using#ran","syntology_url":"https://syntology.ai/paper/2007.08139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08139"}}}},{"paper":"/paper/kernelized-memory-network-for-video-object","slug":"kernelized-memory-network-for-video-object","title":"Kernelized Memory Network for Video Object Segmentation","date":"2020-07-16","arxiv_id":"2007.08270","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/alba-reinforcement-learning-for-video-object","slug":"alba-reinforcement-learning-for-video-object","title":"ALBA : Reinforcement Learning for Video Object Segmentation","date":"2020-05-26","arxiv_id":"2005.13039","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-transductive-approach-for-video-object","slug":"a-transductive-approach-for-video-object","title":"A Transductive Approach for Video Object Segmentation","date":"2020-04-15","arxiv_id":"2004.07193","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/memory-aggregation-networks-for-efficient","slug":"memory-aggregation-networks-for-efficient","title":"Memory Aggregation Networks for Efficient Interactive Video Object Segmentation","date":"2020-03-30","arxiv_id":"2003.13246","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/collaborative-video-object-segmentation-by","slug":"collaborative-video-object-segmentation-by","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","date":"2020-03-18","arxiv_id":"2003.08333","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/stem-seg-spatio-temporal-embeddings-for","slug":"stem-seg-spatio-temporal-embeddings-for","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","date":"2020-03-18","arxiv_id":"2003.08429","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-video-object-segmentation-from-2","slug":"learning-video-object-segmentation-from-2","title":"Learning Video Object Segmentation from Unlabeled Videos","date":"2020-03-10","arxiv_id":"2003.05020","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["carrierlxk/MuG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-video-object-segmentation-from-2#ran","syntology_url":"https://syntology.ai/paper/2003.05020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05020"}}}},{"paper":"/paper/mast-a-memory-augmented-self-supervised","slug":"mast-a-memory-augmented-self-supervised","title":"MAST: A Memory-Augmented Self-supervised Tracker","date":"2020-02-18","arxiv_id":"2002.07793","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/unovost-unsupervised-offline-video-object","slug":"unovost-unsupervised-offline-video-object","title":"UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking","date":"2020-01-15","arxiv_id":"2001.05425","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unovost-unsupervised-offline-video-object#ran","syntology_url":"https://syntology.ai/paper/2001.05425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.05425"}}}},{"paper":"/paper/siam-r-cnn-visual-tracking-by-re-detection","slug":"siam-r-cnn-visual-tracking-by-re-detection","title":"Siam R-CNN: Visual Tracking by Re-Detection","date":"2019-11-28","arxiv_id":"1911.12836","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/siam-r-cnn-visual-tracking-by-re-detection#ran","syntology_url":"https://syntology.ai/paper/1911.12836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12836"}}}},{"paper":"/paper/agss-vos-attention-guided-single-shot-video","slug":"agss-vos-attention-guided-single-shot-video","title":"AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation","date":"2019-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/capsulevos-semi-supervised-video-object","slug":"capsulevos-semi-supervised-video-object","title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","date":"2019-09-30","arxiv_id":"1910.00132","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/joint-task-self-supervised-learning-for","slug":"joint-task-self-supervised-learning-for","title":"Joint-task Self-supervised Learning for Temporal Correspondence","date":"2019-09-26","arxiv_id":"1909.11895","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":23,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":2,"official":{"repos":["Liusifei/UVC"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/joint-task-self-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/1909.11895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11895"}}}},{"paper":"/paper/ranet-ranking-attention-network-for-fast","slug":"ranet-ranking-attention-network-for-fast","title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","date":"2019-08-19","arxiv_id":"1908.06647","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Storife/RANet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ranet-ranking-attention-network-for-fast#ran","syntology_url":"https://syntology.ai/paper/1908.06647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.06647"}}}},{"paper":"/paper/proposal-tracking-and-segmentation-pts-a","slug":"proposal-tracking-and-segmentation-pts-a","title":"Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation","date":"2019-07-02","arxiv_id":"1907.01203","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-unsupervised-video-object","slug":"learning-unsupervised-video-object","title":"Learning Unsupervised Video Object Segmentation Through Visual Attention","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-learning-for-video","slug":"self-supervised-learning-for-video","title":"Self-supervised Learning for Video Correspondence Flow","date":"2019-05-02","arxiv_id":"1905.00875","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fast-user-guided-video-object-segmentation-by","slug":"fast-user-guided-video-object-segmentation-by","title":"Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks","date":"2019-04-22","arxiv_id":"1904.09791","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/190408141","slug":"190408141","title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","date":"2019-04-17","arxiv_id":"1904.08141","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/spatiotemporal-cnn-for-video-object","slug":"spatiotemporal-cnn-for-video-object","title":"Spatiotemporal CNN for Video Object Segmentation","date":"2019-04-04","arxiv_id":"1904.02363","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["longyin880815/STCNN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spatiotemporal-cnn-for-video-object#ran","syntology_url":"https://syntology.ai/paper/1904.02363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02363"}}}},{"paper":"/paper/video-object-segmentation-using-space-time","slug":"video-object-segmentation-using-space-time","title":"Video Object Segmentation using Space-Time Memory Networks","date":"2019-04-01","arxiv_id":"1904.00607","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-object-segmentation-using-space-time#ran","syntology_url":"https://syntology.ai/paper/1904.00607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00607"}}}},{"paper":"/paper/learning-correspondence-from-the-cycle","slug":"learning-correspondence-from-the-cycle","title":"Learning Correspondence from the Cycle-Consistency of Time","date":"2019-03-18","arxiv_id":"1903.07593","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rvos-end-to-end-recurrent-network-for-video","slug":"rvos-end-to-end-recurrent-network-for-video","title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","date":"2019-03-13","arxiv_id":"1903.05612","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/feelvos-fast-end-to-end-embedding-learning","slug":"feelvos-fast-end-to-end-embedding-learning","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","date":"2019-02-25","arxiv_id":"1902.09513","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/feelvos-fast-end-to-end-embedding-learning#ran","syntology_url":"https://syntology.ai/paper/1902.09513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09513"}}}},{"paper":"/paper/fast-online-object-tracking-and-segmentation","slug":"fast-online-object-tracking-and-segmentation","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","date":"2018-12-12","arxiv_id":"1812.05050","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fast-online-object-tracking-and-segmentation#ran","syntology_url":"https://syntology.ai/paper/1812.05050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05050"}}}},{"paper":"/paper/a-generative-appearance-model-for-end-to-end","slug":"a-generative-appearance-model-for-end-to-end","title":"A Generative Appearance Model for End-to-end Video Object Segmentation","date":"2018-11-28","arxiv_id":"1811.11611","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-generative-appearance-model-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/1811.11611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11611"}}}},{"paper":"/paper/videomatch-matching-based-video-object","slug":"videomatch-matching-based-video-object","title":"VideoMatch: Matching based Video Object Segmentation","date":"2018-09-04","arxiv_id":"1809.01123","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/pyramid-dilated-deeper-convlstm-for-video","slug":"pyramid-dilated-deeper-convlstm-for-video","title":"Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection","date":"2018-09-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/premvos-proposal-generation-refinement-and","slug":"premvos-proposal-generation-refinement-and","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","date":"2018-07-24","arxiv_id":"1807.09190","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/premvos-proposal-generation-refinement-and#ran","syntology_url":"https://syntology.ai/paper/1807.09190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09190"}}}},{"paper":"/paper/fast-and-accurate-online-video-object","slug":"fast-and-accurate-online-video-object","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","date":"2018-06-06","arxiv_id":"1806.02323","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":3,"official":{"repos":["JingchunCheng/FAVOS"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fast-and-accurate-online-video-object#ran","syntology_url":"https://syntology.ai/paper/1806.02323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02323"}}}},{"paper":"/paper/fast-video-object-segmentation-by-reference","slug":"fast-video-object-segmentation-by-reference","title":"Fast Video Object Segmentation by Reference-Guided Mask Propagation","date":"2018-06-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/cnn-in-mrf-video-object-segmentation-via","slug":"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","arxiv_id":"1803.09453","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/video-object-segmentation-with-language","slug":"video-object-segmentation-with-language","title":"Video Object Segmentation with Language Referring Expressions","date":"2018-03-21","arxiv_id":"1803.08006","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/efficient-video-object-segmentation-via","slug":"efficient-video-object-segmentation-via","title":"Efficient Video Object Segmentation via Network Modulation","date":"2018-02-04","arxiv_id":"1802.01218","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/video-object-segmentation-without-temporal","slug":"video-object-segmentation-without-temporal","title":"Video Object Segmentation Without Temporal Information","date":"2017-09-18","arxiv_id":"1709.06031","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/online-adaptation-of-convolutional-neural","slug":"online-adaptation-of-convolutional-neural","title":"Online Adaptation of Convolutional Neural Networks for Video Object Segmentation","date":"2017-06-28","arxiv_id":"1706.09364","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/lucid-data-dreaming-for-video-object","slug":"lucid-data-dreaming-for-video-object","title":"Lucid Data Dreaming for Video Object Segmentation","date":"2017-03-28","arxiv_id":"1703.09554","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/video-frame-synthesis-using-deep-voxel-flow","slug":"video-frame-synthesis-using-deep-voxel-flow","title":"Video Frame Synthesis using Deep Voxel Flow","date":"2017-02-08","arxiv_id":"1702.02463","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-frame-synthesis-using-deep-voxel-flow#ran","syntology_url":"https://syntology.ai/paper/1702.02463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02463"}}}},{"paper":"/paper/one-shot-video-object-segmentation","slug":"one-shot-video-object-segmentation","title":"One-Shot Video Object Segmentation","date":"2016-11-16","arxiv_id":"1611.05198","rows_on_this_dataset":2,"code_links":8,"syntology":null}],"papers_where_code_ran":40,"papers_where_code_ran_first_page":"/dataset/davis-2017/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/davis-2017/papers/ran/1","json":"/dataset/davis-2017/papers/ran/1.json","rows":40}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":43,"samples_harvested":387,"samples_ran":277,"samples_constructed":33,"samples_ran_checked":207,"samples_ran_instrument_failed":70,"samples_unverified":110,"pointer_only_for_licence":110,"papers_with_no_sample_that_ran":3,"papers_with_a_sample_that_ran":40,"papers_with_a_run_with_no_instrument_failure":37,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"a44d5a7c15962d274630b79224663c9b651a7d6e5982735c3a2514cbcf0c828f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}