{"id":"https://openalex.org/W2896918494","doi":"https://doi.org/10.1145/3265987.3265988","title":"Multi-task Joint Learning for Videos in the Wild","display_name":"Multi-task Joint Learning for Videos in the Wild","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2896918494","doi":"https://doi.org/10.1145/3265987.3265988","mag":"2896918494"},"language":"en","primary_location":{"id":"doi:10.1145/3265987.3265988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3265987.3265988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild","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/A5110886196","display_name":"Yong Woo Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Won Hong","raw_affiliation_strings":["Yonsei University, Seoul, Rebublic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Rebublic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008685230","display_name":"Hoseong Kim","orcid":"https://orcid.org/0000-0002-1583-1558"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoseong Kim","raw_affiliation_strings":["Yonsei University, Seoul, Rebublic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Rebublic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049739329","display_name":"Hyeran Byun","orcid":"https://orcid.org/0000-0002-3082-3214"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeran Byun","raw_affiliation_strings":["Yonsei University, Seoul, Rebublic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Rebublic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.106,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46788369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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":0.995199978351593,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9944000244140625,"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":0.7676721811294556},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7019766569137573},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6724697351455688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4380491077899933},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.340038001537323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09824901819229126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676721811294556},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7019766569137573},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6724697351455688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4380491077899933},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.340038001537323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09824901819229126},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3265987.3265988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3265987.3265988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W2016053056","https://openalex.org/W2117539524","https://openalex.org/W2122476475","https://openalex.org/W2126579184","https://openalex.org/W2612257250","https://openalex.org/W2618530766","https://openalex.org/W2619947201","https://openalex.org/W2770201307","https://openalex.org/W2772114784","https://openalex.org/W2949650786","https://openalex.org/W2951912364","https://openalex.org/W2952186347","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W2030530201","https://openalex.org/W2081647779","https://openalex.org/W3096054746","https://openalex.org/W3107474891","https://openalex.org/W3199858452","https://openalex.org/W1607472309","https://openalex.org/W2351267244","https://openalex.org/W4237750775","https://openalex.org/W3128051602","https://openalex.org/W2370597599"],"abstract_inverted_index":{"Most":[0],"of":[1,51,58,69,78,96,195],"the":[2,49,52,56,66,76,83,90,99,124,132,158,163,184,193],"conventional":[3,133,187],"state-of-the-art":[4],"methods":[5],"for":[6,98,150,202],"video":[7,111],"analysis":[8],"achieve":[9],"outstanding":[10],"performance":[11],"by":[12,144],"combining":[13,145],"two":[14,196],"or":[15,26],"more":[16],"different":[17,67,72,94,148,151],"inputs,":[18],"e.g.":[19],"an":[20,27],"RGB":[21,125,198],"image,":[22,25],"a":[23,31,93,114,139],"motion":[24],"audio":[28,127,200],"signal,":[29],"in":[30,48,147,162,175],"two-stream":[32,134,188],"manner.":[33],"Although":[34],"these":[35],"approaches":[36],"generate":[37],"pronounced":[38],"performance,":[39],"it":[40],"underlines":[41],"that":[42,61,88],"each":[43,59,79,109,169,173,203],"considered":[44],"feature":[45,112,174],"is":[46],"tantamount":[47],"classification":[50],"video.":[53],"This":[54],"dilutes":[55],"nature":[57,77,85,141],"class":[60,63,84,101,140,170],"every":[62],"depends":[64],"on":[65,123,157,172],"levels":[68],"information":[70],"from":[71],"features.":[73,128],"To":[74],"incorporate":[75],"class,":[80],"we":[81,106],"present":[82],"specific":[86,142],"fusion":[87,135],"combines":[89],"features":[91,146],"with":[92],"level":[95],"weights":[97],"optimal":[100],"result.":[102],"In":[103],"this":[104],"work,":[105],"first":[107],"represent":[108],"frame-level":[110],"as":[113],"spectral":[115],"image":[116],"to":[117,137,166],"train":[118],"convolutional":[119],"neural":[120],"networks":[121],"(CNNs)":[122],"and":[126,199],"We":[129,153],"then":[130],"revise":[131],"method":[136,156],"form":[138],"one":[143],"weight":[149],"classes.":[152],"evaluate":[154],"our":[155],"Comprehensive":[159],"Video":[160],"Understanding":[161],"Wild":[164],"dataset":[165],"understand":[167],"how":[168],"reacted":[171],"wild":[176],"videos.":[177],"Our":[178],"experimental":[179],"results":[180],"not":[181],"only":[182],"show":[183],"advantage":[185],"over":[186],"fusion,":[189],"but":[190],"also":[191],"illustrate":[192],"correlation":[194],"features:":[197],"signal":[201],"class.":[204]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}