{"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":"/task/video-semantic-segmentation/papers/ran/1","list_of":"/task/video-semantic-segmentation","task":"Video Semantic Segmentation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_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'","n_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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":2,"rows_per_page":100,"rows":[1,100],"of":116,"counts":{"archive_papers_tagged":895,"with_a_code_link":418,"where_syntology_ran_a_sample":116,"not_listed_spam_title":0,"listed":895,"listed_where_code_ran":116,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":100,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":100,"listed_every_run_a_failure_of_syntologys_instrument":16,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/video-semantic-segmentation/papers/ran/1","prev":null,"next":"/task/video-semantic-segmentation/papers/ran/2","papers":[{"url":"/paper/unlocking-the-power-of-sam-2-for-few-shot","slug":"unlocking-the-power-of-sam-2-for-few-shot","title":"Unlocking the Power of SAM 2 for Few-Shot Segmentation","date":"2025-05-20","arxiv_id":"2505.14100","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unlocking-the-power-of-sam-2-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2505.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14100"}},"official":{"repos":["sam1224/fssam"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/glus-global-local-reasoning-unified-into-a","slug":"glus-global-local-reasoning-unified-into-a","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","date":"2025-04-10","arxiv_id":"2504.07962","repositories_listed":1,"syntology":{"n":12,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/glus-global-local-reasoning-unified-into-a#ran","syntology_url":"https://syntology.ai/paper/2504.07962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07962"}},"official":null}},{"url":"/paper/high-temporal-consistency-through-semantic","slug":"high-temporal-consistency-through-semantic","title":"High Temporal Consistency through Semantic Similarity Propagation in Semi-Supervised Video Semantic Segmentation for Autonomous Flight","date":"2025-03-19","arxiv_id":"2503.15676","repositories_listed":1,"syntology":{"n":39,"n_ran":25,"n_constructed":15,"n_ran_checked":20,"n_instrument":5,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":39,"phrase":"25 ran (of which 15 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/high-temporal-consistency-through-semantic#ran","syntology_url":"https://syntology.ai/paper/2503.15676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15676"}},"official":{"repos":["fraunhoferivi/ssp"],"state":"official (archive's flag): 25 ran","n_ran":25,"n_constructed":15,"n_ran_no_instrument_failure":20,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","slug":"mpg-sam-2-adapting-sam-2-with-mask-priors-and","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","date":"2025-01-23","arxiv_id":"2501.13667","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and#ran","syntology_url":"https://syntology.ai/paper/2501.13667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13667"}},"official":{"repos":["rongfu-dsb/MPG-SAM2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/edgetam-on-device-track-anything-model","slug":"edgetam-on-device-track-anything-model","title":"EdgeTAM: On-Device Track Anything Model","date":"2025-01-13","arxiv_id":"2501.07256","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":2,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/edgetam-on-device-track-anything-model#ran","syntology_url":"https://syntology.ai/paper/2501.07256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07256"}},"official":{"repos":["facebookresearch/edgetam"],"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":["found_in_text"]}}},{"url":"/paper/instructseg-unifying-instructed-visual","slug":"instructseg-unifying-instructed-visual","title":"InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models","date":"2024-12-18","arxiv_id":"2412.14006","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/instructseg-unifying-instructed-visual#ran","syntology_url":"https://syntology.ai/paper/2412.14006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14006"}},"official":{"repos":["congvvc/instructseg"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/stable-mean-teacher-for-semi-supervised-video","slug":"stable-mean-teacher-for-semi-supervised-video","title":"Stable Mean Teacher for Semi-supervised Video Action Detection","date":"2024-12-10","arxiv_id":"2412.07072","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/stable-mean-teacher-for-semi-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2412.07072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07072"}},"official":{"repos":["AKASH2907/stable-mean-teacher","akash2907/stable_mean_teacher"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/holmes-vau-towards-long-term-video-anomaly","slug":"holmes-vau-towards-long-term-video-anomaly","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","date":"2024-12-09","arxiv_id":"2412.06171","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/holmes-vau-towards-long-term-video-anomaly#ran","syntology_url":"https://syntology.ai/paper/2412.06171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06171"}},"official":{"repos":["pipixin321/holmesvau"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-track-anything","slug":"efficient-track-anything","title":"Efficient Track Anything","date":"2024-11-28","arxiv_id":"2411.18933","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-track-anything#ran","syntology_url":"https://syntology.ai/paper/2411.18933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18933"}},"official":null}},{"url":"/paper/ikea-manuals-at-work-4d-grounding-of-assembly","slug":"ikea-manuals-at-work-4d-grounding-of-assembly","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","date":"2024-11-18","arxiv_id":"2411.11409","repositories_listed":1,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":18,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/ikea-manuals-at-work-4d-grounding-of-assembly#ran","syntology_url":"https://syntology.ai/paper/2411.11409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11409"}},"official":{"repos":["yunongLiu1/IKEA-Manuals-at-Work"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/smite-segment-me-in-time","slug":"smite-segment-me-in-time","title":"SMITE: Segment Me In TimE","date":"2024-10-24","arxiv_id":"2410.18538","repositories_listed":1,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/smite-segment-me-in-time#ran","syntology_url":"https://syntology.ai/paper/2410.18538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18538"}},"official":{"repos":["alimohammadiamirhossein/smite"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/sam2long-enhancing-sam-2-for-long-video","slug":"sam2long-enhancing-sam-2-for-long-video","title":"SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","date":"2024-10-21","arxiv_id":"2410.16268","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sam2long-enhancing-sam-2-for-long-video#ran","syntology_url":"https://syntology.ai/paper/2410.16268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16268"}},"official":{"repos":["mark12ding/sam2long"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/one-token-to-seg-them-all-language-instructed","slug":"one-token-to-seg-them-all-language-instructed","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","date":"2024-09-29","arxiv_id":"2409.19603","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/one-token-to-seg-them-all-language-instructed#ran","syntology_url":"https://syntology.ai/paper/2409.19603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19603"}},"official":{"repos":["showlab/videolisa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/x-prompt-multi-modal-visual-prompt-for-video","slug":"x-prompt-multi-modal-visual-prompt-for-video","title":"X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation","date":"2024-09-28","arxiv_id":"2409.19342","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/x-prompt-multi-modal-visual-prompt-for-video#ran","syntology_url":"https://syntology.ai/paper/2409.19342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19342"}},"official":{"repos":["pinxueguo/x-prompt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/surgical-sam-2-real-time-segment-anything-in","slug":"surgical-sam-2-real-time-segment-anything-in","title":"Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning","date":"2024-08-15","arxiv_id":"2408.07931","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":3,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/surgical-sam-2-real-time-segment-anything-in#ran","syntology_url":"https://syntology.ai/paper/2408.07931","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07931"}},"official":{"repos":["jinlab-imvr/surgical-sam-2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-03286","slug":"2408-03286","title":"Biomedical SAM 2: Segment Anything in Biomedical Images and Videos","date":"2024-08-06","arxiv_id":"2408.03286","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-03286#ran","syntology_url":"https://syntology.ai/paper/2408.03286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03286"}},"official":{"repos":["ZhilingYan/Biomedical-SAM-2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-00714","slug":"2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","arxiv_id":"2408.00714","repositories_listed":11,"syntology":{"n":49,"n_ran":40,"n_constructed":9,"n_ran_checked":34,"n_instrument":6,"n_unverified":9,"n_honours":2,"n_violates":0,"n_no_contract":32,"n_pointer_only":8,"phrase":"40 ran (of which 9 constructed an object rather than computing a result; 34 with no instrument failure: 2 honoured, 0 violated, 32 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/2408-00714#ran","syntology_url":"https://syntology.ai/paper/2408.00714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00714"}},"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"]}}},{"url":"/paper/2408-00169","slug":"2408-00169","title":"Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation","date":"2024-07-31","arxiv_id":"2408.00169","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-00169#ran","syntology_url":"https://syntology.ai/paper/2408.00169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00169"}},"official":{"repos":["vujas-eteph/lazyxmem"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/visa-reasoning-video-object-segmentation-via","slug":"visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","date":"2024-07-16","arxiv_id":"2407.11325","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visa-reasoning-video-object-segmentation-via#ran","syntology_url":"https://syntology.ai/paper/2407.11325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11325"}},"official":{"repos":["cilinyan/VISA","cilinyan/revos-api"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/actionvos-actions-as-prompts-for-video-object","slug":"actionvos-actions-as-prompts-for-video-object","title":"ActionVOS: Actions as Prompts for Video Object Segmentation","date":"2024-07-10","arxiv_id":"2407.07402","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":9,"n_pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/actionvos-actions-as-prompts-for-video-object#ran","syntology_url":"https://syntology.ai/paper/2407.07402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07402"}},"official":{"repos":["ut-vision/actionvos"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-spatial-semantic-features-for-robust","slug":"learning-spatial-semantic-features-for-robust","title":"Learning Spatial-Semantic Features for Robust Video Object Segmentation","date":"2024-07-10","arxiv_id":"2407.07760","repositories_listed":0,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-spatial-semantic-features-for-robust#ran","syntology_url":"https://syntology.ai/paper/2407.07760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07760"}},"official":null}},{"url":"/paper/zero-shot-video-semantic-segmentation-based","slug":"zero-shot-video-semantic-segmentation-based","title":"Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models","date":"2024-05-27","arxiv_id":"2405.16947","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-video-semantic-segmentation-based#ran","syntology_url":"https://syntology.ai/paper/2405.16947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16947"}},"official":{"repos":["QianWangX/VidSeg_diffusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/decoupling-static-and-hierarchical-motion","slug":"decoupling-static-and-hierarchical-motion","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","date":"2024-04-04","arxiv_id":"2404.03645","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/decoupling-static-and-hierarchical-motion#ran","syntology_url":"https://syntology.ai/paper/2404.03645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03645"}},"official":{"repos":["heshuting555/dshmp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dvis-daq-improving-video-segmentation-via","slug":"dvis-daq-improving-video-segmentation-via","title":"DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries","date":"2024-03-29","arxiv_id":"2404.00086","repositories_listed":3,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dvis-daq-improving-video-segmentation-via#ran","syntology_url":"https://syntology.ai/paper/2404.00086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00086"}},"official":{"repos":["skyworkai/daq-vs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","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"}},"official":{"repos":["bo-miao/HTR"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/psalm-pixelwise-segmentation-with-large-multi","slug":"psalm-pixelwise-segmentation-with-large-multi","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","date":"2024-03-21","arxiv_id":"2403.14598","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/psalm-pixelwise-segmentation-with-large-multi#ran","syntology_url":"https://syntology.ai/paper/2403.14598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14598"}},"official":{"repos":["zamling/psalm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-pre-trained-text-to-video-diffusion","slug":"exploring-pre-trained-text-to-video-diffusion","title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation","date":"2024-03-18","arxiv_id":"2403.12042","repositories_listed":1,"syntology":{"n":20,"n_ran":16,"n_constructed":5,"n_ran_checked":10,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":20,"phrase":"16 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/exploring-pre-trained-text-to-video-diffusion#ran","syntology_url":"https://syntology.ai/paper/2403.12042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12042"}},"official":{"repos":["buxiangzhiren/vd-it"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":5,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/depth-aware-test-time-training-for-zero-shot","slug":"depth-aware-test-time-training-for-zero-shot","title":"Depth-aware Test-Time Training for Zero-shot Video Object Segmentation","date":"2024-03-07","arxiv_id":"2403.04258","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/depth-aware-test-time-training-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2403.04258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04258"}},"official":{"repos":["NiFangBaAGe/DATTT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-common-feature-mining-for-efficient","slug":"deep-common-feature-mining-for-efficient","title":"Deep Common Feature Mining for Efficient Video Semantic Segmentation","date":"2024-03-05","arxiv_id":"2403.02689","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/deep-common-feature-mining-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2403.02689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02689"}},"official":{"repos":["buaahugegun/dcfm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","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"}},"official":{"repos":["minghanli/univs"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/we-re-not-using-videos-effectively-an-updated","slug":"we-re-not-using-videos-effectively-an-updated","title":"We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline","date":"2024-02-01","arxiv_id":"2402.00868","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/we-re-not-using-videos-effectively-an-updated#ran","syntology_url":"https://syntology.ai/paper/2402.00868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00868"}},"official":{"repos":["simarkareer/unifiedvideoda"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vivim-a-video-vision-mamba-for-medical-video","slug":"vivim-a-video-vision-mamba-for-medical-video","title":"Vivim: a Video Vision Mamba for Medical Video Segmentation","date":"2024-01-25","arxiv_id":"2401.14168","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vivim-a-video-vision-mamba-for-medical-video#ran","syntology_url":"https://syntology.ai/paper/2401.14168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14168"}},"official":{"repos":["scott-yjyang/vivim"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rap-sam-towards-real-time-all-purpose-segment","slug":"rap-sam-towards-real-time-all-purpose-segment","title":"RAP-SAM: Towards Real-Time All-Purpose Segment Anything","date":"2024-01-18","arxiv_id":"2401.10228","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rap-sam-towards-real-time-all-purpose-segment#ran","syntology_url":"https://syntology.ai/paper/2401.10228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10228"}},"official":{"repos":["xushilin1/rap-sam"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/omg-seg-is-one-model-good-enough-for-all","slug":"omg-seg-is-one-model-good-enough-for-all","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","date":"2024-01-18","arxiv_id":"2401.10229","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/omg-seg-is-one-model-good-enough-for-all#ran","syntology_url":"https://syntology.ai/paper/2401.10229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10229"}},"official":{"repos":["lxtgh/omg-seg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/uniref-segment-every-reference-object-in","slug":"uniref-segment-every-reference-object-in","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","date":"2023-12-25","arxiv_id":"2312.15715","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniref-segment-every-reference-object-in#ran","syntology_url":"https://syntology.ai/paper/2312.15715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15715"}},"official":{"repos":["foundationvision/uniref"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/semi-supervised-active-learning-for-video","slug":"semi-supervised-active-learning-for-video","title":"Semi-supervised Active Learning for Video Action Detection","date":"2023-12-12","arxiv_id":"2312.07169","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/semi-supervised-active-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2312.07169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07169"}},"official":{"repos":["akash2907/semi-sup-active-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/betrayed-by-attention-a-simple-yet-effective","slug":"betrayed-by-attention-a-simple-yet-effective","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","date":"2023-11-29","arxiv_id":"2311.17893","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/betrayed-by-attention-a-simple-yet-effective#ran","syntology_url":"https://syntology.ai/paper/2311.17893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17893"}},"official":{"repos":["shvdiwnkozbw/ssl-uvos"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/segic-unleashing-the-emergent-correspondence","slug":"segic-unleashing-the-emergent-correspondence","title":"SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation","date":"2023-11-24","arxiv_id":"2311.14671","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/segic-unleashing-the-emergent-correspondence#ran","syntology_url":"https://syntology.ai/paper/2311.14671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14671"}},"official":{"repos":["menglcool/segic"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/da-stc-domain-adaptive-video-semantic","slug":"da-stc-domain-adaptive-video-semantic","title":"Unified Domain Adaptive Semantic Segmentation","date":"2023-11-22","arxiv_id":"2311.13254","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/da-stc-domain-adaptive-video-semantic#ran","syntology_url":"https://syntology.ai/paper/2311.13254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13254"}},"official":{"repos":["zhe-sapi/udass"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mask-propagation-for-efficient-video-semantic-1","slug":"mask-propagation-for-efficient-video-semantic-1","title":"Mask Propagation for Efficient Video Semantic Segmentation","date":"2023-10-29","arxiv_id":"2310.18954","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mask-propagation-for-efficient-video-semantic-1#ran","syntology_url":"https://syntology.ai/paper/2310.18954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18954"}},"official":{"repos":["ziplab/mpvss"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/multi-grained-temporal-prototype-learning-for","slug":"multi-grained-temporal-prototype-learning-for","title":"Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation","date":"2023-09-20","arxiv_id":"2309.11160","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-grained-temporal-prototype-learning-for#ran","syntology_url":"https://syntology.ai/paper/2309.11160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.11160"}},"official":{"repos":["nankepan/VIPMT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/catr-combinatorial-dependence-audio-queried","slug":"catr-combinatorial-dependence-audio-queried","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","date":"2023-09-18","arxiv_id":"2309.09709","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/catr-combinatorial-dependence-audio-queried#ran","syntology_url":"https://syntology.ai/paper/2309.09709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09709"}},"official":{"repos":["aspirinone/catr.github.io"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/paper/videocutler-surprisingly-simple-unsupervised","slug":"videocutler-surprisingly-simple-unsupervised","title":"VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation","date":"2023-08-28","arxiv_id":"2308.14710","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videocutler-surprisingly-simple-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2308.14710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14710"}},"official":{"repos":["facebookresearch/cutler"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/locate-self-supervised-object-discovery-via","slug":"locate-self-supervised-object-discovery-via","title":"LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training","date":"2023-08-22","arxiv_id":"2308.11239","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/locate-self-supervised-object-discovery-via#ran","syntology_url":"https://syntology.ai/paper/2308.11239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11239"}},"official":{"repos":["silky1708/locate"],"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"]}}},{"url":"/paper/mevis-a-large-scale-benchmark-for-video","slug":"mevis-a-large-scale-benchmark-for-video","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","date":"2023-08-16","arxiv_id":"2308.08544","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mevis-a-large-scale-benchmark-for-video#ran","syntology_url":"https://syntology.ai/paper/2308.08544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08544"}},"official":{"repos":["henghuiding/MeViS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/predicting-masked-tokens-in-stochastic","slug":"predicting-masked-tokens-in-stochastic","title":"Stochastic positional embeddings improve masked image modeling","date":"2023-07-31","arxiv_id":"2308.00566","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/predicting-masked-tokens-in-stochastic#ran","syntology_url":"https://syntology.ai/paper/2308.00566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00566"}},"official":{"repos":["amirbar/stop"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","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"}},"official":{"repos":["bo-miao/sgmg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/onlinerefer-a-simple-online-baseline-for","slug":"onlinerefer-a-simple-online-baseline-for","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","date":"2023-07-18","arxiv_id":"2307.09356","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/onlinerefer-a-simple-online-baseline-for#ran","syntology_url":"https://syntology.ai/paper/2307.09356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09356"}},"official":{"repos":["wudongming97/onlinerefer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rectifying-noisy-labels-with-sequential-prior","slug":"rectifying-noisy-labels-with-sequential-prior","title":"Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation","date":"2023-07-12","arxiv_id":"2307.05898","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rectifying-noisy-labels-with-sequential-prior#ran","syntology_url":"https://syntology.ai/paper/2307.05898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05898"}},"official":{"repos":["beileicui/ms-tfal"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/video-object-segmentation-in-panoptic-wild","slug":"video-object-segmentation-in-panoptic-wild","title":"Video Object Segmentation in Panoptic Wild Scenes","date":"2023-05-08","arxiv_id":"2305.04470","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-object-segmentation-in-panoptic-wild#ran","syntology_url":"https://syntology.ai/paper/2305.04470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04470"}},"official":{"repos":["yoxu515/viposeg-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/seggpt-segmenting-everything-in-context","slug":"seggpt-segmenting-everything-in-context","title":"SegGPT: Segmenting Everything In Context","date":"2023-04-06","arxiv_id":"2304.03284","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seggpt-segmenting-everything-in-context#ran","syntology_url":"https://syntology.ai/paper/2304.03284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03284"}},"official":{"repos":["baaivision/painter"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/croc-cross-view-online-clustering-for-dense","slug":"croc-cross-view-online-clustering-for-dense","title":"CrOC: Cross-View Online Clustering for Dense Visual Representation Learning","date":"2023-03-23","arxiv_id":"2303.13245","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/croc-cross-view-online-clustering-for-dense#ran","syntology_url":"https://syntology.ai/paper/2303.13245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13245"}},"official":{"repos":["stegmuel/croc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"official":{"repos":["amazon-science/polygon-transformer"],"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"]}}},{"url":"/paper/mose-a-new-dataset-for-video-object","slug":"mose-a-new-dataset-for-video-object","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","date":"2023-02-03","arxiv_id":"2302.01872","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":1,"n_no_contract":3,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mose-a-new-dataset-for-video-object#ran","syntology_url":"https://syntology.ai/paper/2302.01872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01872"}},"official":{"repos":["henghuiding/MOSE-api"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/global-spectral-filter-memory-network-for","slug":"global-spectral-filter-memory-network-for","title":"Global Spectral Filter Memory Network for Video Object Segmentation","date":"2022-10-11","arxiv_id":"2210.05567","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/global-spectral-filter-memory-network-for#ran","syntology_url":"https://syntology.ai/paper/2210.05567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05567"}},"official":{"repos":["workforai/gsfm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/epic-kitchens-visor-benchmark-video","slug":"epic-kitchens-visor-benchmark-video","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","date":"2022-09-26","arxiv_id":"2209.13064","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/epic-kitchens-visor-benchmark-video#ran","syntology_url":"https://syntology.ai/paper/2209.13064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.13064"}},"official":{"repos":["epic-kitchens/visor-hos","epic-kitchens/visor-vos","epic-kitchens/visor-wdtcf"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simple-and-powerful-global-optimization-for","slug":"a-simple-and-powerful-global-optimization-for","title":"A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation","date":"2022-09-19","arxiv_id":"2209.09341","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-simple-and-powerful-global-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2209.09341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09341"}},"official":{"repos":["ponimatkin/ssl-vos"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/treating-motion-as-option-to-reduce-motion","slug":"treating-motion-as-option-to-reduce-motion","title":"Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation","date":"2022-09-04","arxiv_id":"2209.03138","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/treating-motion-as-option-to-reduce-motion#ran","syntology_url":"https://syntology.ai/paper/2209.03138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03138"}},"official":{"repos":["suhwan-cho/tmo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/per-clip-video-object-segmentation-1","slug":"per-clip-video-object-segmentation-1","title":"Per-Clip Video Object Segmentation","date":"2022-08-03","arxiv_id":"2208.01924","repositories_listed":1,"syntology":{"n":12,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":12,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/per-clip-video-object-segmentation-1#ran","syntology_url":"https://syntology.ai/paper/2208.01924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01924"}},"official":{"repos":["pkyong95/PCVOS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/mining-relations-among-cross-frame-affinities","slug":"mining-relations-among-cross-frame-affinities","title":"Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation","date":"2022-07-21","arxiv_id":"2207.10436","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mining-relations-among-cross-frame-affinities#ran","syntology_url":"https://syntology.ai/paper/2207.10436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10436"}},"official":{"repos":["guoleisun/vss-mrcfa"],"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"]}}},{"url":"/paper/semantic-aware-fine-grained-correspondence","slug":"semantic-aware-fine-grained-correspondence","title":"Semantic-Aware Fine-Grained Correspondence","date":"2022-07-21","arxiv_id":"2207.10456","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semantic-aware-fine-grained-correspondence#ran","syntology_url":"https://syntology.ai/paper/2207.10456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10456"}},"official":{"repos":["alxead/sfc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/in-defense-of-online-models-for-video","slug":"in-defense-of-online-models-for-video","title":"In Defense of Online Models for Video Instance Segmentation","date":"2022-07-21","arxiv_id":"2207.10661","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/in-defense-of-online-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2207.10661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10661"}},"official":{"repos":["wjf5203/vnext"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tackling-background-distraction-in-video","slug":"tackling-background-distraction-in-video","title":"Tackling Background Distraction in Video Object Segmentation","date":"2022-07-14","arxiv_id":"2207.06953","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tackling-background-distraction-in-video#ran","syntology_url":"https://syntology.ai/paper/2207.06953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06953"}},"official":{"repos":["suhwan-cho/tbd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/language-bridged-spatial-temporal-interaction-1","slug":"language-bridged-spatial-temporal-interaction-1","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","date":"2022-06-08","arxiv_id":"2206.03789","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-bridged-spatial-temporal-interaction-1#ran","syntology_url":"https://syntology.ai/paper/2206.03789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03789"}},"official":{"repos":["dzh19990407/lbdt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-deeper-dive-into-what-deep-spatiotemporal-1","slug":"a-deeper-dive-into-what-deep-spatiotemporal-1","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","date":"2022-06-06","arxiv_id":"2206.02846","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-deeper-dive-into-what-deep-spatiotemporal-1#ran","syntology_url":"https://syntology.ai/paper/2206.02846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02846"}},"official":{"repos":["YorkUCVIL/Static-Dynamic-Interpretability"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/local-global-context-aware-transformer-for","slug":"local-global-context-aware-transformer-for","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","date":"2022-03-18","arxiv_id":"2203.09773","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/local-global-context-aware-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2203.09773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09773"}},"official":{"repos":["leonnnop/locater"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mlseg-image-and-video-segmentation-as-multi","slug":"mlseg-image-and-video-segmentation-as-multi","title":"RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation","date":"2022-03-08","arxiv_id":"2203.04187","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mlseg-image-and-video-segmentation-as-multi#ran","syntology_url":"https://syntology.ai/paper/2203.04187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04187"}},"official":{"repos":["openseg-group/mlseg","openseg-group/rankseg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/end-to-end-semi-supervised-learning-for-video","slug":"end-to-end-semi-supervised-learning-for-video","title":"End-to-End Semi-Supervised Learning for Video Action Detection","date":"2022-03-08","arxiv_id":"2203.04251","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-semi-supervised-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2203.04251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04251"}},"official":{"repos":["AKASH2907/End-to-End-Semi-Supervised-Learning-for-Video-Action-Detection"],"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","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"}},"official":{"repos":["wjn922/referformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mask2former-for-video-instance-segmentation","slug":"mask2former-for-video-instance-segmentation","title":"Mask2Former for Video Instance Segmentation","date":"2021-12-20","arxiv_id":"2112.10764","repositories_listed":6,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mask2former-for-video-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2112.10764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10764"}},"official":{"repos":["facebookresearch/Mask2Former"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/end-to-end-referring-video-object","slug":"end-to-end-referring-video-object","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","date":"2021-11-29","arxiv_id":"2111.14821","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-referring-video-object#ran","syntology_url":"https://syntology.ai/paper/2111.14821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14821"}},"official":{"repos":["mttr2021/MTTR"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/paper/vil-100-a-new-dataset-and-a-baseline-model","slug":"vil-100-a-new-dataset-and-a-baseline-model","title":"VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection","date":"2021-08-19","arxiv_id":"2108.08482","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vil-100-a-new-dataset-and-a-baseline-model#ran","syntology_url":"https://syntology.ai/paper/2108.08482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.08482"}},"official":{"repos":["yujun0-0/mma-net"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/full-duplex-strategy-for-video-object","slug":"full-duplex-strategy-for-video-object","title":"Full-Duplex Strategy for Video Object Segmentation","date":"2021-08-06","arxiv_id":"2108.03151","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/full-duplex-strategy-for-video-object#ran","syntology_url":"https://syntology.ai/paper/2108.03151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03151"}},"official":{"repos":["GewelsJI/FSNet"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":15,"n_ran":7,"n_constructed":2,"n_ran_checked":7,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","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"}},"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"]}}},{"url":"/paper/rethinking-self-supervised-correspondence","slug":"rethinking-self-supervised-correspondence","title":"Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective","date":"2021-03-31","arxiv_id":"2103.17263","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-self-supervised-correspondence#ran","syntology_url":"https://syntology.ai/paper/2103.17263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.17263"}},"official":{"repos":["xvjiarui/VFS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":5,"syntology":{"n":18,"n_ran":10,"n_constructed":3,"n_ran_checked":5,"n_instrument":5,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified","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"}},"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"]}}},{"url":"/paper/triple-cooperative-video-shadow-detection","slug":"triple-cooperative-video-shadow-detection","title":"Triple-cooperative Video Shadow Detection","date":"2021-03-11","arxiv_id":"2103.06533","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/triple-cooperative-video-shadow-detection#ran","syntology_url":"https://syntology.ai/paper/2103.06533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06533"}},"official":{"repos":["eraserNut/ViSha"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/swiftnet-real-time-video-object-segmentation","slug":"swiftnet-real-time-video-object-segmentation","title":"SwiftNet: Real-time Video Object Segmentation","date":"2021-02-09","arxiv_id":"2102.04604","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":5,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/swiftnet-real-time-video-object-segmentation#ran","syntology_url":"https://syntology.ai/paper/2102.04604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04604"}},"official":{"repos":["haochenheheda/SwiftNet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sstvos-sparse-spatiotemporal-transformers-for","slug":"sstvos-sparse-spatiotemporal-transformers-for","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","date":"2021-01-21","arxiv_id":"2101.08833","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/sstvos-sparse-spatiotemporal-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2101.08833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08833"}},"official":{"repos":["dukebw/SSTVOS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generating-masks-from-boxes-by-mining-spatio","slug":"generating-masks-from-boxes-by-mining-spatio","title":"Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videos","date":"2021-01-06","arxiv_id":"2101.02196","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":2,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generating-masks-from-boxes-by-mining-spatio#ran","syntology_url":"https://syntology.ai/paper/2101.02196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.02196"}},"official":{"repos":["visionml/pytracking"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/tspnet-hierarchical-feature-learning-via","slug":"tspnet-hierarchical-feature-learning-via","title":"TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation","date":"2020-10-12","arxiv_id":"2010.05468","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tspnet-hierarchical-feature-learning-via#ran","syntology_url":"https://syntology.ai/paper/2010.05468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05468"}},"official":{"repos":["verashira/TSPNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/making-a-case-for-3d-convolutions-for-object","slug":"making-a-case-for-3d-convolutions-for-object","title":"Making a Case for 3D Convolutions for Object Segmentation in Videos","date":"2020-08-26","arxiv_id":"2008.11516","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/making-a-case-for-3d-convolutions-for-object#ran","syntology_url":"https://syntology.ai/paper/2008.11516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.11516"}},"official":{"repos":["sabarim/3DC-Seg"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":4,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/paper/temporally-distributed-networks-for-fast","slug":"temporally-distributed-networks-for-fast","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","date":"2020-04-03","arxiv_id":"2004.01800","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/temporally-distributed-networks-for-fast#ran","syntology_url":"https://syntology.ai/paper/2004.01800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01800"}},"official":null}},{"url":"/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","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/state-aware-tracker-for-real-time-video","slug":"state-aware-tracker-for-real-time-video","title":"State-Aware Tracker for Real-Time Video Object Segmentation","date":"2020-03-01","arxiv_id":"2003.00482","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/state-aware-tracker-for-real-time-video#ran","syntology_url":"https://syntology.ai/paper/2003.00482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00482"}},"official":{"repos":["MegviiDetection/video_analyst"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-semantic-video-segmentation-with","slug":"efficient-semantic-video-segmentation-with","title":"Efficient Semantic Video Segmentation with Per-frame Inference","date":"2020-02-26","arxiv_id":"2002.11433","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficient-semantic-video-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2002.11433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.11433"}},"official":null}},{"url":"/paper/zero-shot-video-object-segmentation-via-1","slug":"zero-shot-video-object-segmentation-via-1","title":"Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks","date":"2020-01-19","arxiv_id":"2001.06807","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zero-shot-video-object-segmentation-via-1#ran","syntology_url":"https://syntology.ai/paper/2001.06807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06807"}},"official":{"repos":["carrierlxk/AGNN"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"f5440b31b38cb8a006470a6c6f5f9e905d801c76008755ae6da95331891b530f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}