{"id":"https://openalex.org/W2759312805","doi":"https://doi.org/10.1109/iscas.2017.8050638","title":"Better deep visual attention with reinforcement learning in action recognition","display_name":"Better deep visual attention with reinforcement learning in action recognition","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2759312805","doi":"https://doi.org/10.1109/iscas.2017.8050638","mag":"2759312805"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2017.8050638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2017.8050638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100367353","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-1816-1457"},"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":"Gang Wang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Nanshan District, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Nanshan District, Shenzhen, China","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, Nanshan District, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Nanshan District, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025540890","display_name":"Jingzhuo Wang","orcid":"https://orcid.org/0000-0001-5276-4588"},"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":"Jingzhuo Wang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Nanshan District, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Nanshan District, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025685539","display_name":"Yaohua Bu","orcid":"https://orcid.org/0009-0005-3024-0704"},"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":"Yaohua Bu","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Nanshan District, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Nanshan District, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10036","display_name":"Advanced Neural Network Applications","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":0.789456844329834},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.78183513879776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7403919696807861},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.6733838319778442},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.6300802826881409},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6114846467971802},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5600040555000305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5455545783042908},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.526246964931488},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49389487504959106},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47868210077285767},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44854962825775146},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.44786587357521057},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4365406632423401},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.13572797179222107},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.10028353333473206},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.08792021870613098},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06532987952232361}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789456844329834},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.78183513879776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7403919696807861},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.6733838319778442},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.6300802826881409},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6114846467971802},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5600040555000305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5455545783042908},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.526246964931488},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49389487504959106},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47868210077285767},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44854962825775146},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.44786587357521057},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4365406632423401},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.13572797179222107},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.10028353333473206},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.08792021870613098},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06532987952232361},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas.2017.8050638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2017.8050638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Circuits and Systems (ISCAS)","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":19,"referenced_works":["https://openalex.org/W136504859","https://openalex.org/W855623855","https://openalex.org/W1514535095","https://openalex.org/W1850742715","https://openalex.org/W1902237438","https://openalex.org/W1923404803","https://openalex.org/W1944615693","https://openalex.org/W2097117768","https://openalex.org/W2147527908","https://openalex.org/W2156303437","https://openalex.org/W2172806452","https://openalex.org/W2516449915","https://openalex.org/W2951527505","https://openalex.org/W2962741254","https://openalex.org/W2963321993","https://openalex.org/W2963954913","https://openalex.org/W4294557331","https://openalex.org/W6682137061","https://openalex.org/W6682864246"],"related_works":["https://openalex.org/W2364252372","https://openalex.org/W4234066492","https://openalex.org/W1998063895","https://openalex.org/W1967044713","https://openalex.org/W2133470120","https://openalex.org/W4380485412","https://openalex.org/W3003749315","https://openalex.org/W2084575102","https://openalex.org/W4306253764","https://openalex.org/W2364581933"],"abstract_inverted_index":{"Deep":[0],"visual":[1,138],"attention":[2,9,44,55,67,102],"in":[3,19,45,63,119],"computer":[4],"vision":[5],"has":[6],"attracted":[7],"much":[8,127],"over":[10],"the":[11,40,61,70],"past":[12],"years,":[13],"which":[14,64,131],"achieves":[15],"great":[16],"contributions":[17],"especially":[18],"image":[20,22],"classification,":[21],"caption":[23],"and":[24,48,68,78,121],"action":[25],"recognition.":[26],"However,":[27],"due":[28],"to":[29,60,73],"taking":[30],"BP":[31],"training":[32],"wholly":[33],"or":[34],"partially,":[35],"they":[36],"can":[37,132],"not":[38,117],"show":[39],"true":[41],"power":[42],"of":[43,81],"computational":[46,129],"efficiency":[47],"focusing":[49,120],"accuracy.":[50],"Our":[51],"intuition":[52],"is":[53],"that":[54,100],"mechanism":[56],"should":[57],"be":[58,133],"similar":[59],"process":[62],"human":[65],"draw":[66],"select":[69],"next":[71],"location":[72],"focus,":[74],"by":[75,104],"observing,":[76],"analyzing":[77],"jumping":[79],"instead":[80],"existing":[82],"describing":[83],"continuous":[84],"features.":[85],"Based":[86],"on":[87],"this":[88],"insight,":[89],"we":[90],"formulate":[91],"our":[92,112],"model":[93,113],"as":[94,135],"a":[95],"recurrent":[96],"neural":[97],"network-based":[98],"agent":[99],"chooses":[101],"region":[103],"reinforcement":[105],"learning":[106],"at":[107],"each":[108],"timestep.":[109],"In":[110],"experiments,":[111],"explicitly":[114],"outperforms":[115],"baselines":[116],"only":[118],"recognizing":[122],"accuracy,":[123],"but":[124],"also":[125],"consumes":[126],"less":[128],"resources,":[130],"honored":[134],"better":[136],"deep":[137],"attention.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}