{"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/3","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":9,"rows_per_page":100,"rows":[201,300],"of":895,"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","prev":"/task/video-semantic-segmentation/papers/2","next":"/task/video-semantic-segmentation/papers/4","papers":[{"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/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/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/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/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/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/3rd-place-solution-for-pvuw2023-vss-track-a","slug":"3rd-place-solution-for-pvuw2023-vss-track-a","title":"3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW","date":"2023-06-04","arxiv_id":"2306.02291","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/spatio-temporal-pixel-level-contrastive","slug":"spatio-temporal-pixel-level-contrastive","title":"Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation","date":"2023-03-25","arxiv_id":"2303.14361","repositories_listed":1,"syntology":null},{"url":"/paper/tube-link-a-flexible-cross-tube-baseline-for","slug":"tube-link-a-flexible-cross-tube-baseline-for","title":"Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation","date":"2023-03-22","arxiv_id":"2303.12782","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/global-knowledge-calibration-for-fast-open","slug":"global-knowledge-calibration-for-fast-open","title":"Global Knowledge Calibration for Fast Open-Vocabulary Segmentation","date":"2023-03-16","arxiv_id":"2303.09181","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/instmove-instance-motion-for-object-centric","slug":"instmove-instance-motion-for-object-centric","title":"InstMove: Instance Motion for Object-centric Video Segmentation","date":"2023-03-14","arxiv_id":"2303.08132","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-semantic-segmentation-by-altering","slug":"efficient-semantic-segmentation-by-altering","title":"Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos","date":"2023-03-13","arxiv_id":"2303.07224","repositories_listed":1,"syntology":null},{"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/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/audio-visual-segmentation-with-semantics","slug":"audio-visual-segmentation-with-semantics","title":"Audio-Visual Segmentation with Semantics","date":"2023-01-30","arxiv_id":"2301.13190","repositories_listed":1,"syntology":null},{"url":"/paper/video-semantic-segmentation-with-inter-frame","slug":"video-semantic-segmentation-with-inter-frame","title":"Video Semantic Segmentation with Inter-Frame Feature Fusion and Inner-Frame Feature Refinement","date":"2023-01-10","arxiv_id":"2301.03832","repositories_listed":1,"syntology":null},{"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/context-aware-relative-object-queries-to","slug":"context-aware-relative-object-queries-to","title":"Context-Aware Relative Object Queries To Unify Video Instance and Panoptic Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/multispectral-video-semantic-segmentation-a","slug":"multispectral-video-semantic-segmentation-a","title":"Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline","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/robust-online-video-instance-segmentation","slug":"robust-online-video-instance-segmentation","title":"Robust Online Video Instance Segmentation with Track Queries","date":"2022-11-16","arxiv_id":"2211.09108","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptive-video-semantic-segmentation","slug":"domain-adaptive-video-semantic-segmentation","title":"Domain Adaptive Video Semantic Segmentation via Cross-Domain Moving Object Mixing","date":"2022-11-04","arxiv_id":"2211.02307","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/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/eiseg-an-efficient-interactive-segmentation","slug":"eiseg-an-efficient-interactive-segmentation","title":"EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle","date":"2022-10-17","arxiv_id":"2210.08788","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/multi-modal-segment-assemblage-network-for-ad","slug":"multi-modal-segment-assemblage-network-for-ad","title":"Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward","date":"2022-09-25","arxiv_id":"2209.12164","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/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/adversarial-pixel-restoration-as-a-pretext","slug":"adversarial-pixel-restoration-as-a-pretext","title":"Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations","date":"2022-07-18","arxiv_id":"2207.08803","repositories_listed":1,"syntology":null},{"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/personalized-pca-decoupling-shared-and-unique","slug":"personalized-pca-decoupling-shared-and-unique","title":"Personalized PCA: Decoupling Shared and Unique Features","date":"2022-07-17","arxiv_id":"2207.08041","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/domain-adaptive-video-segmentation-via-1","slug":"domain-adaptive-video-segmentation-via-1","title":"Domain Adaptive Video Segmentation via Temporal Pseudo Supervision","date":"2022-07-06","arxiv_id":"2207.02372","repositories_listed":1,"syntology":null},{"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/an-image-processing-pipeline-for-camera-trap","slug":"an-image-processing-pipeline-for-camera-trap","title":"An Image Processing Pipeline for Camera Trap Time-Lapse Recordings","date":"2022-06-10","arxiv_id":"2206.05159","repositories_listed":1,"syntology":null},{"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/streaming-multiscale-deep-equilibrium-models","slug":"streaming-multiscale-deep-equilibrium-models","title":"Representation Recycling for Streaming Video Analysis","date":"2022-04-28","arxiv_id":"2204.13492","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/video-k-net-a-simple-strong-and-unified","slug":"video-k-net-a-simple-strong-and-unified","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","date":"2022-04-10","arxiv_id":"2204.04656","repositories_listed":1,"syntology":null},{"url":"/paper/coarse-to-fine-feature-mining-for-video","slug":"coarse-to-fine-feature-mining-for-video","title":"Learning Local and Global Temporal Contexts for Video Semantic Segmentation","date":"2022-04-07","arxiv_id":"2204.03330","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/modeling-motion-with-multi-modal-features-for","slug":"modeling-motion-with-multi-modal-features-for","title":"Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation","date":"2022-04-06","arxiv_id":"2204.02547","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/min-max-similarity-a-contrastive-learning","slug":"min-max-similarity-a-contrastive-learning","title":"Min-Max Similarity: A Contrastive Semi-Supervised Deep Learning Network for Surgical Tools Segmentation","date":"2022-03-29","arxiv_id":"2203.15177","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/delta-distillation-for-efficient-video","slug":"delta-distillation-for-efficient-video","title":"Delta Distillation for Efficient Video Processing","date":"2022-03-17","arxiv_id":"2203.09594","repositories_listed":1,"syntology":null},{"url":"/paper/object-discovery-and-representation-networks","slug":"object-discovery-and-representation-networks","title":"Object discovery and representation networks","date":"2022-03-16","arxiv_id":"2203.08777","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-context-for-robust-maritime-obstacle","slug":"temporal-context-for-robust-maritime-obstacle","title":"Temporal Context for Robust Maritime Obstacle Detection","date":"2022-03-10","arxiv_id":"2203.05352","repositories_listed":1,"syntology":null},{"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/borrowing-from-yourself-faster-future-video","slug":"borrowing-from-yourself-faster-future-video","title":"Borrowing from yourself: Faster future video segmentation with partial channel update","date":"2022-02-11","arxiv_id":"2202.05748","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/semi-supervised-video-semantic-segmentation","slug":"semi-supervised-video-semantic-segmentation","title":"Semi-Supervised Video Semantic Segmentation With Inter-Frame Feature Reconstruction","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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},{"url":"/paper/siamese-network-with-interactive-transformer","slug":"siamese-network-with-interactive-transformer","title":"Siamese Network with Interactive Transformer for Video Object Segmentation","date":"2021-12-28","arxiv_id":"2112.13983","repositories_listed":1,"syntology":null}],"record_sha256":"f1951b66881d02e87eb79cfe3f2c68a11c0fc1f469a5b5ff2cc814080a5ffd49","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}