{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/dvis-daq-improving-video-segmentation-via","title":"DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries","arxiv_id":"2404.00086","date":"2024-03-29","proceeding":null,"authors":["Yikang Zhou","Tao Zhang","Shunping Ji","Shuicheng Yan","Xiangtai Li"],"abstract":"Modern video segmentation methods adopt object queries to perform inter-frame association and demonstrate satisfactory performance in tracking continuously appearing objects despite large-scale motion and transient occlusion. However, they all underperform on newly emerging and disappearing objects that are common in the real world because they attempt to model object emergence and disappearance through feature transitions between background and foreground queries that have significant feature gaps. We introduce Dynamic Anchor Queries (DAQ) to shorten the transition gap between the anchor and target queries by dynamically generating anchor queries based on the features of potential candidates. Furthermore, we introduce a query-level object Emergence and Disappearance Simulation (EDS) strategy, which unleashes DAQ's potential without any additional cost. Finally, we combine our proposed DAQ and EDS with DVIS to obtain DVIS-DAQ. Extensive experiments demonstrate that DVIS-DAQ achieves a new state-of-the-art (SOTA) performance on five mainstream video segmentation benchmarks. Code and models are available at \\url{https://github.com/SkyworkAI/DAQ-VS}.","url_abs":"https://arxiv.org/abs/2404.00086v5","url_pdf":"https://arxiv.org/pdf/2404.00086v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dvis-daq-improving-video-segmentation-via","repo_url":"https://github.com/skyworkai/daq-vs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"dvis-daq-improving-video-segmentation-via","repo_url":"https://github.com/zhang-tao-whu/DVIS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dvis-daq-improving-video-segmentation-via","repo_url":"https://github.com/zhang-tao-whu/DVIS_Plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"video-instance-segmentation","task_name":"Video Instance Segmentation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-instance-segmentation-on-ovis-1","task":"Video Instance Segmentation","dataset":"OVIS validation","model":"DVIS-DAQ(VIT-L, Offline)","rank_in_archive_order":1,"of":44,"metrics":{"AP50":"83.8","AP75":"62.9","mask AP":"57.1"},"uses_additional_data":true},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-2","task":"Video Instance Segmentation","dataset":"YouTube-VIS 2021","model":"DVIS-DAQ(VIT-L, Offline)","rank_in_archive_order":2,"of":26,"metrics":{"AP50":"86.1","AP75":"72.2","AR1":"49.6","AR10":"70.7","mask AP":"64.5"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2404.00086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00086"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhang-tao-whu/DVIS_Plus","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhang-tao-whu/DVIS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/skyworkai/daq-vs","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"listed":{"samples":5,"ran":1,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"c69fa2c17b83883c","entry":"get_classification_logits","repo":"zhang-tao-whu/DVIS_Plus","repo_kind":"listed","path":"DVIS_Plus/ov_dvis/video_dvis_modules_ov.py","file_url":"https://github.com/zhang-tao-whu/DVIS_Plus/blob/HEAD/DVIS_Plus/ov_dvis/video_dvis_modules_ov.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c69fa2c17b83883c"}},{"code_sha256_prefix":"9b916842dbe58636","entry":"filter_empty_instances","repo":"zhang-tao-whu/DVIS","repo_kind":"listed","path":"dvis/data_video/dataset_mapper.py","file_url":"https://github.com/zhang-tao-whu/DVIS/blob/HEAD/dvis/data_video/dataset_mapper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b916842dbe58636"}},{"code_sha256_prefix":"a21a61e41d986b6a","entry":"filter_images_with_only_crowd_annotations","repo":"zhang-tao-whu/DVIS","repo_kind":"listed","path":"dvis/data_video/build.py","file_url":"https://github.com/zhang-tao-whu/DVIS/blob/HEAD/dvis/data_video/build.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a21a61e41d986b6a"}},{"code_sha256_prefix":"33aa671cbd444b19","entry":"loss_reid","repo":"zhang-tao-whu/DVIS_Plus","repo_kind":"listed","path":"DVIS_DAQ/dvis_Plus/ctvis.py","file_url":"https://github.com/zhang-tao-whu/DVIS_Plus/blob/HEAD/DVIS_DAQ/dvis_Plus/ctvis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33aa671cbd444b19"}},{"code_sha256_prefix":"0eb0a29a32434f4d","entry":"loss_reid","repo":"zhang-tao-whu/DVIS_Plus","repo_kind":"listed","path":"DVIS_DAQ/dvis_Plus/utils.py","file_url":"https://github.com/zhang-tao-whu/DVIS_Plus/blob/HEAD/DVIS_DAQ/dvis_Plus/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0eb0a29a32434f4d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}