{"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":"/method/vpsnet","slug":"vpsnet","name":"VPSNet","full_name":"Video Panoptic Segmentation Network","full_name_withheld":false,"description_markdown":"**Video Panoptic Segmentation Network**, or **VPSNet**, is a model for video panoptic segmentation. On top of UPSNet, which is a method for image panoptic segmentation, VPSNet is designed to take an additional frame as the reference to correlate time information at two levels: pixel-level fusion and object-level tracking. To pick up the complementary feature points in the reference frame, a flow-based feature map alignment module is introduced along with an asymmetric attention block that computes similarities between the target and reference features to fuse them into one-frame shape. Additionally, to associate object instances across time, \r\n an object track head is added which learns the correspondence between the instances in the target and reference frames based\r\non their RoI feature similarity.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Video Panoptic Segmentation","paper":"/paper/video-panoptic-segmentation-1","first_author":"Dahun Kim","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/video-panoptic-segmentation-1"},"source":{"url":"https://arxiv.org/abs/2006.11339v1","title":"Video Panoptic Segmentation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Video Panoptic Segmentation Models","url":"/methods/category/video-panoptic-segmentation-models","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/video-panoptic-segmentation-1","slug":"video-panoptic-segmentation-1","title":"Video Panoptic Segmentation","date":"2020-06-19","arxiv_id":"2006.11339","n_code_links":1,"syntology":null}],"papers_shown":1,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":1,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":1,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"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"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":1},{"task":"/task/panoptic-segmentation","name":"Panoptic Segmentation","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1},{"task":"/task/video-instance-segmentation","name":"Video Instance Segmentation","papers":1},{"task":"/task/video-panoptic-segmentation","name":"Video Panoptic Segmentation","papers":1},{"task":"/task/video-recognition","name":"Video Recognition","papers":1},{"task":"/task/video-segmentation","name":"Video Segmentation","papers":1},{"task":"/task/video-semantic-segmentation","name":"Video Semantic Segmentation","papers":1}],"tasks_shown":9,"n_tasks":9,"usage_by_year":[{"year":"2020","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/vpsnet"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=VPSNet","read_at":"2026-10-05T01:03:47+00:00","query":"VPSNet","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2006.11339","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'VPSNet' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"01c205b813573c3e6f39370d4a84fdec2ccb434c969ddf1481c2e71a04f36e4f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}