{"id":"https://openalex.org/W3093103595","doi":"https://doi.org/10.1145/3394171.3416301","title":"Toward Accurate Person-level Action Recognition in Videos of Crowed Scenes","display_name":"Toward Accurate Person-level Action Recognition in Videos of Crowed Scenes","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093103595","doi":"https://doi.org/10.1145/3394171.3416301","mag":"3093103595"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3416301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3416301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.08365","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Yuan","raw_affiliation_strings":["National Univerisity of Singapore & YiTu Technology, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Univerisity of Singapore & YiTu Technology, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yichen Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yichen Zhou","raw_affiliation_strings":["National Univerisity of Singapore & YiTu Technology, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Univerisity of Singapore & YiTu Technology, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuning Chang","orcid":null},"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":"Shuning Chang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziyuan Huang","orcid":null},"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":"Ziyuan Huang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yupeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yupeng Chen","raw_affiliation_strings":["YiTu Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"YiTu Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuecheng Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuecheng Nie","raw_affiliation_strings":["YiTu Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"YiTu Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Wang","orcid":null},"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":"Tao Wang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiashi Feng","orcid":null},"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":"Jiashi Feng","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shuicheng Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["YiTu Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"YiTu Technology, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4694","last_page":"4698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9977999925613403,"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/action","display_name":"Action (physics)","score":0.7026000022888184},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6402999758720398},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5537999868392944},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.545799970626831},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5099999904632568},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3379000127315521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758400022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7221999764442444},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7026000022888184},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5099999904632568},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.508899986743927},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28200000524520874}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394171.3416301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3416301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.08365","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.08365","pdf_url":"https://arxiv.org/pdf/2010.08365","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:2010.08365","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.08365","pdf_url":"https://arxiv.org/pdf/2010.08365","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1970850659","https://openalex.org/W2102605133","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2565639579","https://openalex.org/W2594507094","https://openalex.org/W2618799552","https://openalex.org/W2737258237","https://openalex.org/W2752782242","https://openalex.org/W2903758693","https://openalex.org/W2959289524","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W2982593143","https://openalex.org/W2990503944","https://openalex.org/W3034239448"],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"and":[1,19,48,67,114],"recognizing":[2],"human":[3,85],"action":[4,59,98],"in":[5,31,45,160,168],"videos":[6],"with":[7,28,117],"crowed":[8],"scenes":[9,66,119,134],"is":[10,74,136],"a":[11,83,148],"challenging":[12],"problem":[13,30],"due":[14],"to":[15,26,76,87,101,143],"the":[16,39,46,63,78,89,103,111,121,126,133,139,145,161],"complex":[17,49],"environment":[18],"diversity":[20],"events.":[21],"Prior":[22],"works":[23],"always":[24],"fail":[25],"deal":[27],"this":[29,52],"two":[32],"aspects:":[33],"(1)":[34],"lacking":[35,42],"utilizing":[36],"information":[37,64,105,135],"of":[38,65,92,129],"scenes;":[40],"(2)":[41],"training":[43],"data":[44,116],"crowd":[47],"scenes.":[50],"In":[51],"paper,":[53],"we":[54,81],"focus":[55],"on":[56,109],"improving":[57],"spatio-temporal":[58,104],"recognition":[60,99],"by":[61,138],"fully-utilizing":[62],"collecting":[68],"new":[69,115],"data.":[70],"A":[71],"top-down":[72],"strategy":[73],"used":[75],"overcome":[77],"limitations.":[79],"Specifically,":[80],"adopt":[82],"strong":[84],"detector":[86],"detect":[88],"spatial":[90],"location":[91],"each":[93],"frame.":[94],"We":[95],"then":[96],"apply":[97],"models":[100],"learn":[102],"from":[106,120],"video":[107],"frames":[108],"both":[110],"HIE":[112],"dataset":[113],"diverse":[118],"internet,":[122],"which":[123],"can":[124],"improve":[125],"generalization":[127],"ability":[128],"our":[130,150],"model.":[131],"Besides,":[132],"extracted":[137],"semantic":[140],"segmentation":[141],"model":[142],"assistant":[144],"process.":[146],"As":[147],"result,":[149],"method":[151],"achieved":[152],"an":[153],"average":[154],"26.05":[155],"wf\\_mAP":[156],"(ranking":[157],"1st":[158],"place":[159],"ACM":[162],"MM":[163],"grand":[164],"challenge":[165],"2020:":[166],"Human":[167],"Events).":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-10-22T00:00:00"}