{"id":"https://openalex.org/W4293732316","doi":"https://doi.org/10.1109/tcsvt.2022.3202574","title":"Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework With Spatio-Temporal Collaboration","display_name":"Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework With Spatio-Temporal Collaboration","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4293732316","doi":"https://doi.org/10.1109/tcsvt.2022.3202574"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3202574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3202574","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2212.07592","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051997091","display_name":"Liqi Yan","orcid":"https://orcid.org/0000-0002-7077-4947"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liqi Yan","raw_affiliation_strings":["Westlake Institute for Advanced Study, Fudan University, Shanghai, China","School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake Institute for Advanced Study, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I3133055985","https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774659","display_name":"Qifan Wang","orcid":"https://orcid.org/0000-0002-7570-5756"},"institutions":[{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":["Meta AI, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016972157","display_name":"Siqi Ma","orcid":"https://orcid.org/0000-0003-3479-5713"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqi Ma","raw_affiliation_strings":["School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695181","display_name":"Jingang Wang","orcid":"https://orcid.org/0000-0002-2999-3371"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingang Wang","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003451705","display_name":"Changbin Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210163399","display_name":"Shandong First Medical University","ror":"https://ror.org/05jb9pq57","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163399"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changbin Yu","raw_affiliation_strings":["College of Artificial Intelligence and Big Data for Medical Science, Shandong First Medical University & Shandong Academy of Medical Sciences, Jinan, China","Institute for Intelligent Robots, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence and Big Data for Medical Science, Shandong First Medical University & Shandong Academy of Medical Sciences, Jinan, China","institution_ids":["https://openalex.org/I4210163399"]},{"raw_affiliation_string":"Institute for Intelligent Robots, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051997091"],"corresponding_institution_ids":["https://openalex.org/I24943067","https://openalex.org/I3133055985"],"apc_list":null,"apc_paid":null,"fwci":8.0501,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.98392183,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"33","issue":"1","first_page":"393","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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-science","display_name":"Computer science","score":0.6814034581184387},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6339659094810486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5609548091888428},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.540468692779541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36829298734664917},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3334275484085083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6814034581184387},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6339659094810486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5609548091888428},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.540468692779541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36829298734664917},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3334275484085083}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2022.3202574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3202574","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2212.07592","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.07592","pdf_url":"https://arxiv.org/pdf/2212.07592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2212.07592","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.07592","pdf_url":"https://arxiv.org/pdf/2212.07592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G492650815","display_name":null,"funder_award_id":"U21A20488","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1495267108","https://openalex.org/W1921093919","https://openalex.org/W2108598243","https://openalex.org/W2150066425","https://openalex.org/W2154383686","https://openalex.org/W2168804568","https://openalex.org/W2170714427","https://openalex.org/W2194775991","https://openalex.org/W2221898772","https://openalex.org/W2259424905","https://openalex.org/W2295107390","https://openalex.org/W2317851288","https://openalex.org/W2322480645","https://openalex.org/W2396622801","https://openalex.org/W2470139095","https://openalex.org/W2517490240","https://openalex.org/W2552414813","https://openalex.org/W2565639579","https://openalex.org/W2566588379","https://openalex.org/W2603203130","https://openalex.org/W2609883120","https://openalex.org/W2798376494","https://openalex.org/W2920326761","https://openalex.org/W2953433552","https://openalex.org/W2953920664","https://openalex.org/W2954087924","https://openalex.org/W2954765307","https://openalex.org/W2955278847","https://openalex.org/W2955382613","https://openalex.org/W2955639361","https://openalex.org/W2956648669","https://openalex.org/W2962758679","https://openalex.org/W2962762068","https://openalex.org/W2962858109","https://openalex.org/W2962867364","https://openalex.org/W2962914239","https://openalex.org/W2963150697","https://openalex.org/W2963227409","https://openalex.org/W2963311325","https://openalex.org/W2963820951","https://openalex.org/W2963849369","https://openalex.org/W2963857746","https://openalex.org/W2966210862","https://openalex.org/W2976669726","https://openalex.org/W2977487707","https://openalex.org/W2980189057","https://openalex.org/W2982723417","https://openalex.org/W2982770724","https://openalex.org/W2983061571","https://openalex.org/W2985775862","https://openalex.org/W2993182889","https://openalex.org/W2996881884","https://openalex.org/W3034244618","https://openalex.org/W3034681942","https://openalex.org/W3034826836","https://openalex.org/W3034896357","https://openalex.org/W3034930876","https://openalex.org/W3035295069","https://openalex.org/W3035478146","https://openalex.org/W3035709993","https://openalex.org/W3045477169","https://openalex.org/W3081167590","https://openalex.org/W3082755608","https://openalex.org/W3084173793","https://openalex.org/W3085685449","https://openalex.org/W3086436251","https://openalex.org/W3095753995","https://openalex.org/W3100953775","https://openalex.org/W3104778224","https://openalex.org/W3106546328","https://openalex.org/W3106763294","https://openalex.org/W3109073404","https://openalex.org/W3109372619","https://openalex.org/W3110109236","https://openalex.org/W3110159886","https://openalex.org/W3112530000","https://openalex.org/W3121052081","https://openalex.org/W3127727546","https://openalex.org/W3167095230","https://openalex.org/W3167225078","https://openalex.org/W3174598330","https://openalex.org/W3176027594","https://openalex.org/W3176336346","https://openalex.org/W3176692018","https://openalex.org/W3180169285","https://openalex.org/W3180638445","https://openalex.org/W3181286780","https://openalex.org/W3188394685","https://openalex.org/W3191142899","https://openalex.org/W3206120323","https://openalex.org/W3206199195","https://openalex.org/W3212940248","https://openalex.org/W4205432963","https://openalex.org/W4281764208","https://openalex.org/W4285118488","https://openalex.org/W4285600262","https://openalex.org/W4312322023","https://openalex.org/W4313177625","https://openalex.org/W6763430915","https://openalex.org/W6765150368","https://openalex.org/W6767465851"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Instance":[0],"segmentation":[1,127,197],"in":[2,12,22,41,190,198],"videos,":[3,42],"which":[4,87,109],"aims":[5],"to":[6,63,77,106,114,129,175],"segment":[7],"and":[8,60,71,123,145,157,163],"track":[9],"multiple":[10],"objects":[11],"video":[13],"frames,":[14],"has":[15],"garnered":[16],"a":[17,30,84,172],"flurry":[18],"of":[19,139,183],"research":[20],"attention":[21],"recent":[23],"years.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,51,82],"present":[29],"novel":[31],"weakly":[32,192],"supervised":[33,161,193],"framework":[34,120],"with":[35,103],"Spatio-Temporal":[36],"Collaboration":[37],"for":[38,67,195],"instance":[39,74,126,196],"Segmentation":[40],"namely":[43],"STC-Seg.":[44],"Concretely,":[45],"STC-Seg":[46,169],"demonstrates":[47],"four":[48],"contributions.":[49],"First,":[50],"leverage":[52],"the":[53,79,112,131,142,176,181,187,191],"complementary":[54],"representations":[55],"from":[56],"unsupervised":[57],"depth":[58],"estimation":[59],"optical":[61],"flow":[62],"produce":[64],"effective":[65],"pseudo-labels":[66],"training":[68,90],"deep":[69],"networks":[70],"predicting":[72],"high-quality":[73],"masks.":[75],"Second,":[76],"enhance":[78],"mask":[80],"generation,":[81],"devise":[83],"puzzle":[85],"loss,":[86],"enables":[88,124],"end-to-end":[89],"using":[91],"box-level":[92],"annotations.":[93],"Third,":[94],"our":[95,119,152],"tracking":[96],"module":[97],"jointly":[98],"utilizes":[99],"bounding-box":[100],"diagonal":[101],"points":[102],"spatio-temporal":[104],"discrepancy":[105],"model":[107],"movements,":[108],"largely":[110],"improves":[111],"robustness":[113],"different":[115],"object":[116],"appearances.":[117],"Finally,":[118],"is":[121],"flexible":[122],"image-level":[125],"methods":[128],"operate":[130],"video-level":[132],"task.":[133],"We":[134,166],"conduct":[135],"an":[136,184],"extensive":[137],"set":[138],"experiments":[140],"on":[141],"KITTI":[143],"MOTS":[144],"YT-VIS":[146],"datasets.":[147],"Experimental":[148],"results":[149],"demonstrate":[150],"that":[151,168],"method":[153],"achieves":[154],"strong":[155],"performance":[156],"even":[158],"outperforms":[159],"fully":[160],"TrackR-CNN":[162],"MaskTrack":[164],"R-CNN.":[165],"believe":[167],"can":[170],"be":[171],"valuable":[173],"addition":[174],"community,":[177],"as":[178],"it":[179],"reflects":[180],"tip":[182],"iceberg":[185],"about":[186],"innovative":[188],"opportunities":[189],"paradigm":[194],"videos.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":9}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2022-08-31T00:00:00"}