{"id":"https://openalex.org/W4405778924","doi":"https://doi.org/10.1109/tmm.2024.3521668","title":"Video Instance Segmentation Without Using Mask and Identity Supervision","display_name":"Video Instance Segmentation Without Using Mask and Identity Supervision","publication_year":2024,"publication_date":"2024-12-25","ids":{"openalex":"https://openalex.org/W4405778924","doi":"https://doi.org/10.1109/tmm.2024.3521668"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521668","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":null,"display_name":"Ge Li","orcid":"https://orcid.org/0009-0007-3601-0015"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Li","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0007-3601-0015","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037129512","display_name":"Jiale Cao","orcid":"https://orcid.org/0000-0002-5160-6841"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Cao","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-5160-6841","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017943691","display_name":"Hanqing Sun","orcid":"https://orcid.org/0000-0002-8022-4172"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210088164","display_name":"Changchun Institute of Optics, Fine Mechanics and Physics","ror":"https://ror.org/012rct222","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210088164"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanqing Sun","raw_affiliation_strings":["Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-8022-4172","affiliations":[{"raw_affiliation_string":"Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210088164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022929869","display_name":"Rao Muhammad Anwer","orcid":"https://orcid.org/0000-0002-9041-2214"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Rao Muhammad Anwer","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","Mohamed bin Zayed University of Artificial Intelligence, UAE"],"raw_orcid":"https://orcid.org/0000-0002-9041-2214","affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089409762","display_name":"Jin Xie","orcid":"https://orcid.org/0000-0001-6978-8834"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xie","raw_affiliation_strings":["School of Big Data and Software Engineering, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-6978-8834","affiliations":[{"raw_affiliation_string":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Khan","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","Mohamed bin Zayed University of Artificial Intelligence, UAE"],"raw_orcid":"https://orcid.org/0000-0002-4263-3143","affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086887025","display_name":"Yanwei Pang","orcid":"https://orcid.org/0000-0001-6670-3727"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-6670-3727","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17445174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"224","last_page":"235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9864000082015991,"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/T11448","display_name":"Face recognition and analysis","score":0.9864000082015991,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9750000238418579,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7833454608917236},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5925452709197998},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5678975582122803},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5543083548545837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5453478693962097},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.44130805134773254},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.40200161933898926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.359866201877594},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.09310322999954224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833454608917236},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5925452709197998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5678975582122803},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5543083548545837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5453478693962097},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.44130805134773254},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.40200161933898926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.359866201877594},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.09310322999954224},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521668","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2199262417","display_name":null,"funder_award_id":"62206031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5074938571","display_name":null,"funder_award_id":"62271346","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7594118645","display_name":null,"funder_award_id":"62401538","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2963150697","https://openalex.org/W2982723417","https://openalex.org/W2982770724","https://openalex.org/W2993182889","https://openalex.org/W3034328552","https://openalex.org/W3034499084","https://openalex.org/W3034650337","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3106546328","https://openalex.org/W3109372619","https://openalex.org/W3110109236","https://openalex.org/W3113410735","https://openalex.org/W3139267983","https://openalex.org/W3167949052","https://openalex.org/W3169933013","https://openalex.org/W3171516518","https://openalex.org/W3173326549","https://openalex.org/W3173980723","https://openalex.org/W3180169285","https://openalex.org/W3181286780","https://openalex.org/W3194146976","https://openalex.org/W3199130398","https://openalex.org/W3202509201","https://openalex.org/W3212555189","https://openalex.org/W4214613769","https://openalex.org/W4285200620","https://openalex.org/W4293464712","https://openalex.org/W4312275238","https://openalex.org/W4312294051","https://openalex.org/W4312573566","https://openalex.org/W4312815172","https://openalex.org/W4312837597","https://openalex.org/W4313007081","https://openalex.org/W4313016235","https://openalex.org/W4313192411","https://openalex.org/W4382240664","https://openalex.org/W4386071623","https://openalex.org/W6757817989","https://openalex.org/W6770717842","https://openalex.org/W6784094891","https://openalex.org/W6796494355","https://openalex.org/W6797162190","https://openalex.org/W6809716307","https://openalex.org/W6839371072","https://openalex.org/W6843861238","https://openalex.org/W6848927509","https://openalex.org/W6851407990"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W2502309190","https://openalex.org/W4395685956","https://openalex.org/W3159516372","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Video":[0],"instance":[1,85,93,99,125,135],"segmentation":[2],"(VIS)":[3],"is":[4,13,54],"a":[5,25,37,77,130],"challenging":[6],"vision":[7],"problem":[8],"in":[9,24,133,143],"which":[10,165],"the":[11,21,60,159,162,168,172,181,192,198],"task":[12],"to":[14],"simultaneously":[15],"detect,":[16],"segment,":[17],"and":[18,51,56,80,88,101,115,156,175],"track":[19],"all":[20],"object":[22],"instances":[23],"video.":[26],"Most":[27],"existing":[28],"VIS":[29,63,178],"approaches":[30],"rely":[31],"on":[32,149],"pixel-level":[33],"mask":[34,68,90,110],"supervision":[35],"within":[36,129],"frame":[38],"as":[39,41],"well":[40],"instance-level":[42],"identity":[43,72],"annotation":[44],"across":[45,140],"frames.":[46],"However,":[47],"obtaining":[48],"these":[49],"\u2018mask":[50],"identity\u2019":[52],"annotations":[53,69],"time-consuming":[55],"expensive.":[57],"We":[58],"propose":[59],"first":[61,96],"mask-identity-free":[62,187],"framework":[64],"that":[65],"neither":[66],"utilizes":[67],"nor":[70],"requires":[71],"supervision.":[73],"Accordingly,":[74],"we":[75],"introduce":[76],"query":[78,86,94,104,117],"contrast":[79,87,95],"exchange":[81,118],"network":[82],"(QCEN)":[83],"comprising":[84],"query-exchanged":[89,109],"learning.":[91,107],"The":[92,108],"performs":[97],"cross-frame":[98],"matching":[100],"then":[102],"conducts":[103],"feature":[105],"contrastive":[106],"learning":[111],"exploits":[112],"both":[113],"intra-video":[114],"inter-video":[116],"properties:":[119],"exchanging":[120,138],"queries":[121,139],"of":[122,161,191],"an":[123],"identical":[124],"from":[126],"different":[127],"frames":[128],"video":[131],"results":[132,142],"consistent":[134],"masks,":[136],"whereas":[137],"videos":[141],"all-zero":[144],"background":[145],"masks.":[146],"Extensive":[147],"experiments":[148],"three":[150],"benchmarks":[151],"(YouTube-VIS":[152],"2019,":[153],"YouTube-VIS":[154,182],"2021,":[155],"OVIS)":[157],"reveal":[158],"merits":[160],"proposed":[163],"approach,":[164],"significantly":[166],"reduces":[167],"performance":[169,195],"gap":[170],"between":[171],"identify-free":[173],"baseline":[174,194],"our":[176,186],"mask-identify-free":[177],"method.":[179],"On":[180],"2019":[183],"validation":[184],"set,":[185],"approach":[188],"achieves":[189],"91.4%":[190],"stronger-supervision-based":[193],"when":[196],"utilizing":[197],"same":[199],"ImageNet":[200],"pre-trained":[201],"model.":[202]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}