{"id":"https://openalex.org/W4413144927","doi":"https://doi.org/10.1109/cvpr52734.2025.00810","title":"LiVOS: Light Video Object Segmentation with Gated Linear Matching","display_name":"LiVOS: Light Video Object Segmentation with Gated Linear Matching","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144927","doi":"https://doi.org/10.1109/cvpr52734.2025.00810"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005624296","display_name":"Qin Liu","orcid":"https://orcid.org/0000-0001-6342-5311"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin Liu","raw_affiliation_strings":["UNC Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358528","display_name":"Jianfeng Wang","orcid":"https://orcid.org/0000-0003-3080-6657"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianfeng Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009867415","display_name":"Zhengyuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengyuan Yang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110673725","display_name":"Linjie Li","orcid":"https://orcid.org/0000-0002-9817-1793"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Linjie Li","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108030232","display_name":"Kevin Lin","orcid":"https://orcid.org/0000-0001-8944-1336"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kevin Lin","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108610850","display_name":"Marc Niethammer","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Niethammer","raw_affiliation_strings":["UNC Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100436541","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0003-1727-2670"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6813,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95331555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8668","last_page":"8678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6983963251113892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.696097731590271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6713468432426453},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6382843255996704},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.510267972946167},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.49852538108825684},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49474307894706726},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.43547290563583374},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3211345672607422},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1349979043006897},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05507969856262207}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6983963251113892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.696097731590271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6713468432426453},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6382843255996704},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.510267972946167},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.49852538108825684},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49474307894706726},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.43547290563583374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3211345672607422},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1349979043006897},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05507969856262207}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W4301594054","https://openalex.org/W2737719445","https://openalex.org/W2794488505","https://openalex.org/W2898210368","https://openalex.org/W4239098401","https://openalex.org/W2501551404","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Semi-supervised":[0],"video":[1,49,183],"object":[2],"segmentation":[3],"(VOS)":[4],"has":[5],"been":[6],"largely":[7],"driven":[8],"by":[9],"space-time":[10],"memory":[11,22,35,62,72,164],"(STM)":[12],"networks,":[13],"which":[14],"store":[15],"past":[16],"frame":[17,27],"features":[18],"in":[19],"a":[20,60,75,85,99,170],"spatiotemporal":[21],"to":[23,38,84,109,113],"segment":[24],"the":[25,39,80,106,122,146,177],"current":[26],"via":[28,68],"softmax":[29,43],"attention.":[30],"However,":[31],"STM":[32],"networks":[33],"face":[34],"limitations":[36],"due":[37],"quadratic":[40,81],"complexity":[41],"of":[42,124],"matching,":[44,97],"restricting":[45],"their":[46],"applicability":[47],"as":[48],"length":[50],"and":[51,134,144,153,165,181],"resolution":[52],"increase.":[53],"To":[54,90],"address":[55],"this,":[56],"we":[57,93],"propose":[58],"LiVOS,":[59],"lightweight":[61],"network":[63],"that":[64,78],"employs":[65],"linear":[66,69,96],"matching":[67,73],"attention,":[70],"reformulating":[71],"into":[74],"recurrent":[76],"process":[77],"reduces":[79],"attention":[82],"matrix":[83,102,108],"constant-size,":[86],"spatiotemporal-agnostic":[87],"2D":[88],"state.":[89],"enhance":[91],"selectivity,":[92],"introduce":[94],"gated":[95],"where":[98],"data-dependent":[100],"gate":[101],"is":[103],"multiplied":[104],"with":[105,148,160],"state":[107],"control":[110],"what":[111],"information":[112],"retain":[114],"or":[115],"discard.":[116],"Experiments":[117],"on":[118,132,138,169],"diverse":[119],"benchmarks":[120],"demonstrated":[121],"effectiveness":[123],"our":[125],"method.":[126],"It":[127],"achieved":[128],"64.8":[129],"${\\mathcal{J}}\\&":[130,136],"{\\mathcal{F}}$":[131,137],"MOSE":[133],"85.1":[135],"DAVIS,":[139],"surpassing":[140],"all":[141],"non-STM":[142],"methods":[143,159],"narrowing":[145],"gap":[147],"STM-based":[149,158],"approaches.":[150],"For":[151],"longer":[152],"higher-resolution":[154],"videos,":[155],"it":[156],"matched":[157],"53%":[161],"less":[162],"GPU":[163],"supports":[166],"4096p":[167],"inference":[168],"32G":[171],"consumer-grade":[172],"GPU-a":[173],"previously":[174],"cost-prohibitive":[175],"capability-opening":[176],"door":[178],"for":[179],"long":[180],"high-resolution":[182],"foundation":[184],"models.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-08T08:33:18.762332","created_date":"2025-10-10T00:00:00"}