{"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-object-segmentation/papers/2","list_of":"/task/video-object-segmentation","task":"Video Object 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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":6,"rows_per_page":100,"rows":[101,200],"of":551,"counts":{"archive_papers_tagged":551,"with_a_code_link":294,"where_syntology_ran_a_sample":95,"not_listed_spam_title":0,"listed":551,"listed_where_code_ran":95,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":83,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":83,"listed_every_run_a_failure_of_syntologys_instrument":12,"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-object-segmentation","prev":"/task/video-object-segmentation","next":"/task/video-object-segmentation/papers/3","papers":[{"url":"/paper/moving-object-segmentation-all-you-need-is","slug":"moving-object-segmentation-all-you-need-is","title":"Moving Object Segmentation: All You Need Is SAM (and Flow)","date":"2024-04-18","arxiv_id":"2404.12389","repositories_listed":1,"syntology":null},{"url":"/paper/event-assisted-low-light-video-object","slug":"event-assisted-low-light-video-object","title":"Event-assisted Low-Light Video Object Segmentation","date":"2024-04-02","arxiv_id":"2404.01945","repositories_listed":1,"syntology":null},{"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/annolid-annotate-segment-and-track-anything","slug":"annolid-annotate-segment-and-track-anything","title":"Annolid: Annotate, Segment, and Track Anything You Need","date":"2024-03-27","arxiv_id":"2403.18690","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-video-object-segmentation-via-1","slug":"efficient-video-object-segmentation-via-1","title":"Efficient Video Object Segmentation via Modulated Cross-Attention Memory","date":"2024-03-26","arxiv_id":"2403.17937","repositories_listed":1,"syntology":null},{"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/video-object-segmentation-with-dynamic-query","slug":"video-object-segmentation-with-dynamic-query","title":"Video Object Segmentation with Dynamic Query Modulation","date":"2024-03-18","arxiv_id":"2403.11529","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-surgical-instrument-segmentation-in","slug":"real-time-surgical-instrument-segmentation-in","title":"Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything","date":"2024-03-12","arxiv_id":"2403.08003","repositories_listed":1,"syntology":null},{"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/videomac-video-masked-autoencoders-meet","slug":"videomac-video-masked-autoencoders-meet","title":"VideoMAC: Video Masked Autoencoders Meet ConvNets","date":"2024-02-29","arxiv_id":"2402.19082","repositories_listed":1,"syntology":null},{"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/lester-rotoscope-animation-through-video","slug":"lester-rotoscope-animation-through-video","title":"Lester: rotoscope animation through video object segmentation and tracking","date":"2024-02-15","arxiv_id":"2402.09883","repositories_listed":1,"syntology":null},{"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/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/1st-place-solution-for-5th-lsvos-challenge","slug":"1st-place-solution-for-5th-lsvos-challenge","title":"1st Place Solution for 5th LSVOS Challenge: Referring Video Object Segmentation","date":"2024-01-01","arxiv_id":"2401.00663","repositories_listed":1,"syntology":null},{"url":"/paper/tracking-with-human-intent-reasoning","slug":"tracking-with-human-intent-reasoning","title":"Tracking with Human-Intent Reasoning","date":"2023-12-29","arxiv_id":"2312.17448","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-graph-pattern-understanding-for","slug":"hierarchical-graph-pattern-understanding-for","title":"Hierarchical Graph Pattern Understanding for Zero-Shot VOS","date":"2023-12-15","arxiv_id":"2312.09525","repositories_listed":1,"syntology":null},{"url":"/paper/general-object-foundation-model-for-images","slug":"general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","arxiv_id":"2312.09158","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}},"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"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/flexible-visual-prompts-for-in-context","slug":"flexible-visual-prompts-for-in-context","title":"Flexible visual prompts for in-context learning in computer vision","date":"2023-12-11","arxiv_id":"2312.06592","repositories_listed":1,"syntology":null},{"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/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/sub-token-vit-embedding-via-stochastic","slug":"sub-token-vit-embedding-via-stochastic","title":"Sub-token ViT Embedding via Stochastic Resonance Transformers","date":"2023-10-06","arxiv_id":"2310.03967","repositories_listed":1,"syntology":null},{"url":"/paper/treating-motion-as-option-with-output","slug":"treating-motion-as-option-with-output","title":"Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation","date":"2023-09-26","arxiv_id":"2309.14786","repositories_listed":1,"syntology":null},{"url":"/paper/panovos-bridging-non-panoramic-and-panoramic","slug":"panovos-bridging-non-panoramic-and-panoramic","title":"PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation","date":"2023-09-21","arxiv_id":"2309.12303","repositories_listed":1,"syntology":null},{"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/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/learning-cross-modal-affinity-for-referring","slug":"learning-cross-modal-affinity-for-referring","title":"Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples","date":"2023-09-05","arxiv_id":"2309.02041","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-boxes-and-masks-a-multi-object","slug":"integrating-boxes-and-masks-a-multi-object","title":"Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation","date":"2023-08-25","arxiv_id":"2308.13266","repositories_listed":1,"syntology":null},{"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/isomer-isomerous-transformer-for-zero-shot","slug":"isomer-isomerous-transformer-for-zero-shot","title":"Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation","date":"2023-08-13","arxiv_id":"2308.06693","repositories_listed":1,"syntology":null},{"url":"/paper/tracking-anything-in-high-quality","slug":"tracking-anything-in-high-quality","title":"Tracking Anything in High Quality","date":"2023-07-26","arxiv_id":"2307.13974","repositories_listed":1,"syntology":null},{"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/holistic-prototype-attention-network-for-few","slug":"holistic-prototype-attention-network-for-few","title":"Holistic Prototype Attention Network for Few-Shot VOS","date":"2023-07-16","arxiv_id":"2307.07933","repositories_listed":1,"syntology":null},{"url":"/paper/multiscale-memory-comparator-transformer-for","slug":"multiscale-memory-comparator-transformer-for","title":"Multiscale Memory Comparator Transformer for Few-Shot Video Segmentation","date":"2023-07-15","arxiv_id":"2307.07812","repositories_listed":1,"syntology":null},{"url":"/paper/refsam-efficiently-adapting-segmenting","slug":"refsam-efficiently-adapting-segmenting","title":"RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation","date":"2023-07-03","arxiv_id":"2307.00997","repositories_listed":1,"syntology":null},{"url":"/paper/segment-anything-meets-point-tracking","slug":"segment-anything-meets-point-tracking","title":"Segment Anything Meets Point Tracking","date":"2023-07-03","arxiv_id":"2307.01197","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"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) · 5 unverified","sample_list":"/paper/segment-anything-meets-point-tracking#ran","syntology_url":"https://syntology.ai/paper/2307.01197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01197"}},"official":{"repos":["syscv/sam-pt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/losh-long-short-text-joint-prediction-network","slug":"losh-long-short-text-joint-prediction-network","title":"LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation","date":"2023-06-14","arxiv_id":"2306.08736","repositories_listed":1,"syntology":null},{"url":"/paper/soc-semantic-assisted-object-cluster-for","slug":"soc-semantic-assisted-object-cluster-for","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","date":"2023-05-26","arxiv_id":"2305.17011","repositories_listed":1,"syntology":null},{"url":"/paper/referred-by-multi-modality-a-unified-temporal","slug":"referred-by-multi-modality-a-unified-temporal","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","date":"2023-05-25","arxiv_id":"2305.16318","repositories_listed":1,"syntology":null},{"url":"/paper/readmem-robust-embedding-association-for-a","slug":"readmem-robust-embedding-association-for-a","title":"READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object Segmentation","date":"2023-05-22","arxiv_id":"2305.12823","repositories_listed":1,"syntology":null},{"url":"/paper/uvosam-a-mask-free-paradigm-for-unsupervised","slug":"uvosam-a-mask-free-paradigm-for-unsupervised","title":"UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model","date":"2023-05-22","arxiv_id":"2305.12659","repositories_listed":1,"syntology":null},{"url":"/paper/personalize-segment-anything-model-with-one","slug":"personalize-segment-anything-model-with-one","title":"Personalize Segment Anything Model with One Shot","date":"2023-05-04","arxiv_id":"2305.03048","repositories_listed":1,"syntology":null},{"url":"/paper/bootstrapping-objectness-from-videos-by","slug":"bootstrapping-objectness-from-videos-by","title":"Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping","date":"2023-04-17","arxiv_id":"2304.08025","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-video-object-segmentation-via-space","slug":"boosting-video-object-segmentation-via-space","title":"Boosting Video Object Segmentation via Space-time Correspondence Learning","date":"2023-04-13","arxiv_id":"2304.06211","repositories_listed":1,"syntology":null},{"url":"/paper/clvos23-a-long-video-object-segmentation","slug":"clvos23-a-long-video-object-segmentation","title":"CLVOS23: A Long Video Object Segmentation Dataset for Continual Learning","date":"2023-04-09","arxiv_id":"2304.04259","repositories_listed":1,"syntology":null},{"url":"/paper/co-attention-propagation-network-for-zero","slug":"co-attention-propagation-network-for-zero","title":"Co-attention Propagation Network for Zero-Shot Video Object Segmentation","date":"2023-04-08","arxiv_id":"2304.03910","repositories_listed":1,"syntology":null},{"url":"/paper/dropmae-masked-autoencoders-with-spatial","slug":"dropmae-masked-autoencoders-with-spatial","title":"DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks","date":"2023-04-02","arxiv_id":"2304.00571","repositories_listed":1,"syntology":null},{"url":"/paper/reliability-hierarchical-memory-network-for","slug":"reliability-hierarchical-memory-network-for","title":"Reliability-Hierarchical Memory Network for Scribble-Supervised Video Object Segmentation","date":"2023-03-25","arxiv_id":"2303.14384","repositories_listed":1,"syntology":null},{"url":"/paper/two-shot-video-object-segmentation","slug":"two-shot-video-object-segmentation","title":"Two-shot Video Object Segmentation","date":"2023-03-21","arxiv_id":"2303.12078","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-multi-source-predictor-for-zero-shot","slug":"adaptive-multi-source-predictor-for-zero-shot","title":"Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation","date":"2023-03-18","arxiv_id":"2303.10383","repositories_listed":1,"syntology":null},{"url":"/paper/unified-mask-embedding-and-correspondence","slug":"unified-mask-embedding-and-correspondence","title":"Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation","date":"2023-03-17","arxiv_id":"2303.10100","repositories_listed":1,"syntology":null},{"url":"/paper/guided-slot-attention-for-unsupervised-video","slug":"guided-slot-attention-for-unsupervised-video","title":"Guided Slot Attention for Unsupervised Video Object Segmentation","date":"2023-03-15","arxiv_id":"2303.08314","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-unseen-object-instance","slug":"self-supervised-unseen-object-instance","title":"Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction","date":"2023-02-07","arxiv_id":"2302.03793","repositories_listed":1,"syntology":null},{"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/end-to-end-video-matting-with-trimap","slug":"end-to-end-video-matting-with-trimap","title":"End-to-End Video Matting With Trimap Propagation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/video-object-segmentation-aware-video-frame","slug":"video-object-segmentation-aware-video-frame","title":"Video Object Segmentation-aware Video Frame Interpolation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/video-state-changing-object-segmentation","slug":"video-state-changing-object-segmentation","title":"Video State-Changing Object Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/1st-place-solution-for-youtubevos-challenge-1","slug":"1st-place-solution-for-youtubevos-challenge-1","title":"1st Place Solution for YouTubeVOS Challenge 2022: Referring Video Object Segmentation","date":"2022-12-27","arxiv_id":"2212.14679","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-learn-better-for-video-object","slug":"learning-to-learn-better-for-video-object","title":"Learning to Learn Better for Video Object Segmentation","date":"2022-12-05","arxiv_id":"2212.02112","repositories_listed":1,"syntology":null},{"url":"/paper/domain-alignment-and-temporal-aggregation-for","slug":"domain-alignment-and-temporal-aggregation-for","title":"Dual Prototype Attention for Unsupervised Video Object Segmentation","date":"2022-11-22","arxiv_id":"2211.12036","repositories_listed":1,"syntology":null},{"url":"/paper/lvos-a-benchmark-for-long-term-video-object","slug":"lvos-a-benchmark-for-long-term-video-object","title":"LVOS: A Benchmark for Long-term Video Object Segmentation","date":"2022-11-18","arxiv_id":"2211.10181","repositories_listed":1,"syntology":null},{"url":"/paper/two-level-temporal-relation-model-for-online","slug":"two-level-temporal-relation-model-for-online","title":"Two-Level Temporal Relation Model for Online Video Instance Segmentation","date":"2022-10-30","arxiv_id":"2210.16795","repositories_listed":1,"syntology":null},{"url":"/paper/vlt-vision-language-transformer-and-query","slug":"vlt-vision-language-transformer-and-query","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2022-10-28","arxiv_id":"2210.15871","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/vlt-vision-language-transformer-and-query#ran","syntology_url":"https://syntology.ai/paper/2210.15871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15871"}},"official":{"repos":["henghuiding/Vision-Language-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-amodal-video-object","slug":"self-supervised-amodal-video-object","title":"Self-supervised Amodal Video Object Segmentation","date":"2022-10-23","arxiv_id":"2210.12733","repositories_listed":1,"syntology":null},{"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/self-supervised-video-representation-learning-12","slug":"self-supervised-video-representation-learning-12","title":"Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders","date":"2022-10-09","arxiv_id":"2210.04154","repositories_listed":1,"syntology":null},{"url":"/paper/burst-a-benchmark-for-unifying-object","slug":"burst-a-benchmark-for-unifying-object","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","date":"2022-09-25","arxiv_id":"2209.12118","repositories_listed":1,"syntology":null},{"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/unsupervised-video-object-segmentation-via","slug":"unsupervised-video-object-segmentation-via","title":"Unsupervised Video Object Segmentation via Prototype Memory Network","date":"2022-09-08","arxiv_id":"2209.03712","repositories_listed":1,"syntology":null},{"url":"/paper/swem-towards-real-time-video-object-1","slug":"swem-towards-real-time-video-object-1","title":"SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization","date":"2022-08-22","arxiv_id":"2208.10128","repositories_listed":1,"syntology":null},{"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/multi-attention-network-for-compressed-video","slug":"multi-attention-network-for-compressed-video","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","date":"2022-07-26","arxiv_id":"2207.12622","repositories_listed":1,"syntology":null},{"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/hierarchical-feature-alignment-network-for","slug":"hierarchical-feature-alignment-network-for","title":"Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation","date":"2022-07-18","arxiv_id":"2207.08485","repositories_listed":1,"syntology":null},{"url":"/paper/learning-quality-aware-dynamic-memory-for","slug":"learning-quality-aware-dynamic-memory-for","title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","date":"2022-07-16","arxiv_id":"2207.07922","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-quality-aware-dynamic-memory-for#ran","syntology_url":"https://syntology.ai/paper/2207.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07922"}},"official":{"repos":["workforai/qdmn"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"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/siammask-a-framework-for-fast-online-object","slug":"siammask-a-framework-for-fast-online-object","title":"SiamMask: A Framework for Fast Online Object Tracking and Segmentation","date":"2022-07-05","arxiv_id":"2207.02088","repositories_listed":1,"syntology":null},{"url":"/paper/r-2vos-robust-referring-video-object","slug":"r-2vos-robust-referring-video-object","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","date":"2022-07-04","arxiv_id":"2207.01203","repositories_listed":1,"syntology":null},{"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/differentiable-soft-masked-attention","slug":"differentiable-soft-masked-attention","title":"Differentiable Soft-Masked Attention","date":"2022-06-01","arxiv_id":"2206.00182","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-dynamic-embedding-for-video-object","slug":"recurrent-dynamic-embedding-for-video-object","title":"Recurrent Dynamic Embedding for Video Object Segmentation","date":"2022-05-08","arxiv_id":"2205.03761","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-video-object-segmentation-based-on","slug":"boosting-video-object-segmentation-based-on","title":"Boosting Video Object Segmentation based on Scale Inconsistency","date":"2022-05-02","arxiv_id":"2205.01197","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-memory-management-for-video-object","slug":"adaptive-memory-management-for-video-object","title":"Adaptive Memory Management for Video Object Segmentation","date":"2022-04-13","arxiv_id":"2204.06626","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-motion-compensated-network-for","slug":"implicit-motion-compensated-network-for","title":"Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation","date":"2022-04-06","arxiv_id":"2204.02791","repositories_listed":1,"syntology":null},{"url":"/paper/in-n-out-generative-learning-for-dense","slug":"in-n-out-generative-learning-for-dense","title":"In-N-Out Generative Learning for Dense Unsupervised Video Segmentation","date":"2022-03-29","arxiv_id":"2203.15312","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-transductive-inference-for-few-shot","slug":"temporal-transductive-inference-for-few-shot","title":"Temporal Transductive Inference for Few-Shot Video Object Segmentation","date":"2022-03-27","arxiv_id":"2203.14308","repositories_listed":1,"syntology":null},{"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/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/revisiting-click-based-interactive-video","slug":"revisiting-click-based-interactive-video","title":"Revisiting Click-based Interactive Video Object Segmentation","date":"2022-03-03","arxiv_id":"2203.01784","repositories_listed":1,"syntology":null},{"url":"/paper/box-supervised-video-segmentation-proposal","slug":"box-supervised-video-segmentation-proposal","title":"Box Supervised Video Segmentation Proposal Network","date":"2022-02-14","arxiv_id":"2202.07025","repositories_listed":1,"syntology":null},{"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/wnet-audio-guided-video-object-segmentation","slug":"wnet-audio-guided-video-object-segmentation","title":"Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross-Modal Denoising Networks","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"2a55ca04689322e4ec952cc3794873616cc5d4ff026099ba18fcb21fae4dcb12","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}