{"id":"https://openalex.org/W2497983802","doi":"https://doi.org/10.1109/tpami.2016.2598340","title":"Learning to Segment Human by Watching YouTube","display_name":"Learning to Segment Human by Watching YouTube","publication_year":2016,"publication_date":"2016-08-05","ids":{"openalex":"https://openalex.org/W2497983802","doi":"https://doi.org/10.1109/tpami.2016.2598340","mag":"2497983802","pmid":"https://pubmed.ncbi.nlm.nih.gov/27514037"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2016.2598340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2016.2598340","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1710.01457","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education, China","Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education, China","institution_ids":[]},{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087043856","display_name":"Yunchao Wei","orcid":"https://orcid.org/0000-0002-2812-8781"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yunchao Wei","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education, China","Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education, China","institution_ids":[]},{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029978692","display_name":"Yunpeng Chen","orcid":"https://orcid.org/0000-0002-9830-8980"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yunpeng Chen","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047385834","display_name":"Xiaohui Shen","orcid":"https://orcid.org/0000-0001-7739-339X"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohui Shen","raw_affiliation_strings":["Adobe Research, San Jose, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, CA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianchao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianchao Yang","raw_affiliation_strings":["SnapChat Inc., Venice, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SnapChat Inc., Venice, CA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["360 AI Institute and National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Institute and National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0967,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92542463,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"39","issue":"7","first_page":"1462","last_page":"1468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8846451640129089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8153883218765259},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7455490827560425},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6968221664428711},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5744990110397339},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5160505175590515},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5040139555931091},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4929823875427246},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46458083391189575},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.44292309880256653},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.44220221042633057},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43296903371810913},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4109506607055664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3635498285293579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8846451640129089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8153883218765259},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7455490827560425},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6968221664428711},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5744990110397339},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5160505175590515},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5040139555931091},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4929823875427246},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46458083391189575},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.44292309880256653},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.44220221042633057},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43296903371810913},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4109506607055664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3635498285293579},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2016.2598340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2016.2598340","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:27514037","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27514037","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:1710.01457","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.01457","pdf_url":"https://arxiv.org/pdf/1710.01457","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:1710.01457","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.01457","pdf_url":"https://arxiv.org/pdf/1710.01457","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G6558565582","display_name":null,"funder_award_id":"61622214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W88868203","https://openalex.org/W95926497","https://openalex.org/W159595522","https://openalex.org/W219040644","https://openalex.org/W589665618","https://openalex.org/W1495267108","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1908985308","https://openalex.org/W1923115158","https://openalex.org/W1923697677","https://openalex.org/W1927251054","https://openalex.org/W1938976761","https://openalex.org/W1948751323","https://openalex.org/W1951304353","https://openalex.org/W1964763677","https://openalex.org/W1966601141","https://openalex.org/W1973054923","https://openalex.org/W2031489346","https://openalex.org/W2081613070","https://openalex.org/W2097117768","https://openalex.org/W2105297725","https://openalex.org/W2116877738","https://openalex.org/W2117539524","https://openalex.org/W2117741877","https://openalex.org/W2124592697","https://openalex.org/W2144794286","https://openalex.org/W2155598147","https://openalex.org/W2160160833","https://openalex.org/W2168804568","https://openalex.org/W2212123867","https://openalex.org/W2221898772","https://openalex.org/W2270657321","https://openalex.org/W2293193551","https://openalex.org/W2471138382","https://openalex.org/W2618530766","https://openalex.org/W2962835968","https://openalex.org/W2963563573","https://openalex.org/W3103722964","https://openalex.org/W6603613150","https://openalex.org/W6606481039","https://openalex.org/W6617526114","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6640295612","https://openalex.org/W6688657083"],"related_works":["https://openalex.org/W2493838176","https://openalex.org/W4297686120","https://openalex.org/W4376620596","https://openalex.org/W3177249605","https://openalex.org/W2534152068","https://openalex.org/W3138508047","https://openalex.org/W1972515067","https://openalex.org/W1689909837","https://openalex.org/W4293054914","https://openalex.org/W4313315626"],"abstract_inverted_index":{"An":[0],"intuition":[1],"on":[2,37,166,216],"human":[3,9,31,52,59,75,119,131,154,218],"segmentation":[4,53,81,173,219],"is":[5,10,61,101],"that":[6,176],"when":[7],"a":[8,13,46,212],"moving":[11],"in":[12,143],"video,":[14],"the":[15,29,72,96,106,113,129,135,140,144,148,151,167,177,202,217],"video-context":[16,73,152],"(e.g.,":[17],"appearance":[18],"and":[19,78,134],"motion":[20],"clues)":[21],"may":[22],"potentially":[23],"infer":[24],"reasonable":[25],"mask":[26,76],"information":[27],"for":[28,51],"whole":[30],"body.":[32],"Inspired":[33],"by":[34,105,122,139,199],"this,":[35],"based":[36,80],"popular":[38],"deep":[39],"convolutional":[40],"neural":[41],"networks":[42],"(CNN),":[43],"we":[44],"explore":[45],"very-weakly":[47],"supervised":[48],"learning":[49,83],"framework":[50,179],"task,":[54],"where":[55],"only":[56],"an":[57],"imperfect":[58,130],"detector":[60],"available":[62],"along":[63],"with":[64,125,190,201],"massive":[65],"weakly-labeled":[66],"YouTube":[67],"videos.":[68],"In":[69,95,147,197],"our":[70,209],"solution,":[71],"guided":[74],"inference":[77],"CNN":[79,141],"network":[82],"iterate":[84],"to":[85,161],"mutually":[86],"enhance":[87],"each":[88,99],"other":[89],"until":[90],"no":[91],"further":[92],"improvement":[93],"gains.":[94],"first":[97],"step,":[98,150],"video":[100,108],"decomposed":[102],"into":[103],"supervoxels":[104,114],"unsupervised":[107],"segmentation.":[109],"The":[110],"superpixels":[111],"within":[112],"are":[115,156],"then":[116],"classified":[117],"as":[118,158],"or":[120,193],"non-human":[121],"graph":[123],"optimization":[124],"unary":[126],"energies":[127],"from":[128,205],"detection":[132],"results":[133,184],"predicted":[136],"confidence":[137],"maps":[138],"trained":[142],"previous":[145,187],"iteration.":[146],"second":[149],"derived":[153],"masks":[155,204],"used":[157],"direct":[159],"labels":[160],"train":[162],"CNN.":[163],"Extensive":[164],"experiments":[165],"challenging":[168],"PASCAL":[169,206],"VOC":[170,207],"2012":[171],"semantic":[172],"benchmark":[174],"demonstrate":[175],"proposed":[178],"has":[180],"already":[181],"achieved":[182],"superior":[183],"than":[185],"all":[186],"weakly-supervised":[188],"methods":[189],"object":[191],"class":[192],"bounding":[194],"box":[195],"annotations.":[196],"addition,":[198],"augmenting":[200],"annotated":[203],"2012,":[208],"method":[210],"reaches":[211],"new":[213],"state-of-the-art":[214],"performance":[215],"task.":[220]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}