{"id":"https://openalex.org/W2751713519","doi":"https://doi.org/10.1109/icme.2017.8019335","title":"A joint model for action localization and classification in untrimmed video with visual attention","display_name":"A joint model for action localization and classification in untrimmed video with visual attention","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2751713519","doi":"https://doi.org/10.1109/icme.2017.8019335","mag":"2751713519"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2017.8019335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","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/A5035177668","display_name":"Weimian Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weimian Li","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017052768","display_name":"Wenmin Wang","orcid":"https://orcid.org/0000-0003-2664-4413"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenmin Wang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034398151","display_name":"Xiongtao Chen","orcid":"https://orcid.org/0000-0002-6349-8737"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongtao Chen","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084797829","display_name":"Jinzhuo Wang","orcid":"https://orcid.org/0000-0002-9464-4426"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinzhuo Wang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447691","display_name":"Ge Li","orcid":"https://orcid.org/0000-0003-0140-0949"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Li","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035177668"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.3641,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68810109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"619","last_page":"624"},"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":0.9990000128746033,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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":0.8221142888069153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7126067280769348},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6577861905097961},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6049332618713379},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.548485517501831},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5063391923904419},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.500485897064209},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48284727334976196},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48235195875167847},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43161553144454956},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4218423068523407},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12621158361434937},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10497239232063293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221142888069153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7126067280769348},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6577861905097961},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6049332618713379},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.548485517501831},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5063391923904419},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.500485897064209},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48284727334976196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48235195875167847},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43161553144454956},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4218423068523407},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12621158361434937},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10497239232063293},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2017.8019335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1484210532","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1534763723","https://openalex.org/W1724369340","https://openalex.org/W1927052826","https://openalex.org/W1944615693","https://openalex.org/W1983364832","https://openalex.org/W1993229407","https://openalex.org/W2020163092","https://openalex.org/W2024868105","https://openalex.org/W2119717200","https://openalex.org/W2142194269","https://openalex.org/W2147527908","https://openalex.org/W2156303437","https://openalex.org/W2172806452","https://openalex.org/W2470774766","https://openalex.org/W2533739470","https://openalex.org/W2554238388","https://openalex.org/W2951527505","https://openalex.org/W2963321993","https://openalex.org/W4294557331","https://openalex.org/W6632082525","https://openalex.org/W6648464962","https://openalex.org/W6682137061","https://openalex.org/W6682864246","https://openalex.org/W6729922797"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126"],"abstract_inverted_index":{"In":[0,118],"this":[1],"paper,":[2],"we":[3,160],"introduce":[4],"a":[5,57,66,81,133,157],"joint":[6],"model":[7,52,125,144],"that":[8,162],"learns":[9],"to":[10,33,38,61,105,139],"directly":[11],"localize":[12],"the":[13,35,87,152],"temporal":[14,76],"bounds":[15],"of":[16,74,84,89,95],"actions":[17,27],"in":[18,115,171],"untrimmed":[19],"videos":[20],"as":[21,23],"well":[22],"precisely":[24],"classify":[25],"what":[26],"occur.":[28],"Most":[29],"existing":[30],"approaches":[31],"tend":[32],"scan":[34],"whole":[36],"video":[37,67,97],"generate":[39],"action":[40],"instances,":[41],"which":[42,112],"are":[43],"really":[44],"inefficient.":[45],"Instead,":[46],"inspired":[47],"by":[48,78,110],"human":[49],"perception,":[50],"our":[51,124,143,163],"is":[53,72,93,108,113],"formulated":[54],"based":[55],"on":[56,145],"recurrent":[58],"neural":[59],"network":[60],"observe":[62],"different":[63,120],"locations":[64],"within":[65],"over":[68],"time.":[69],"And,":[70],"it":[71,91,149],"capable":[73],"producing":[75],"localizations":[77],"only":[79],"observing":[80],"fixed":[82],"number":[83],"fragments,":[85],"and":[86,128,131,148],"amount":[88],"computation":[90],"performs":[92],"independent":[94],"input":[96],"size.":[98],"The":[99],"decision":[100],"policy":[101],"for":[102,135],"determining":[103],"where":[104],"look":[106],"next":[107],"learned":[109],"REINFORCE":[111],"powerful":[114],"non-differentiable":[116],"settings.":[117],"addition,":[119],"from":[121],"relevant":[122],"ways,":[123],"runs":[126],"localization":[127],"classification":[129],"serially,":[130],"possesses":[132],"strategy":[134],"extracting":[136],"appropriate":[137],"features":[138],"classify.":[140],"We":[141],"evaluate":[142],"ActivityNet":[146],"dataset,":[147],"greatly":[150],"outperforms":[151],"baseline.":[153],"Moreover,":[154],"compared":[155],"with":[156],"recent":[158],"approach,":[159],"show":[161],"serial":[164],"design":[165],"can":[166],"bring":[167],"about":[168],"9%":[169],"increase":[170],"detection":[172],"performance.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}