{"id":"https://openalex.org/W2161565164","doi":"https://doi.org/10.1145/2733373.2806222","title":"Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification","display_name":"Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification","publication_year":2015,"publication_date":"2015-10-13","ids":{"openalex":"https://openalex.org/W2161565164","doi":"https://doi.org/10.1145/2733373.2806222","mag":"2161565164"},"language":"en","primary_location":{"id":"doi:10.1145/2733373.2806222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","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/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686112","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0003-0260-1160"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427158","display_name":"Hao Ye","orcid":"https://orcid.org/0000-0002-5939-4708"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Ye","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026167547"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":31.8208,"has_fulltext":false,"cited_by_count":472,"citation_normalized_percentile":{"value":0.99727453,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"461","last_page":"470"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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":0.9980999827384949,"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/softmax-function","display_name":"Softmax function","score":0.8953844904899597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8290560245513916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7495083808898926},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6159034967422485},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6128784418106079},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5220789313316345},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5074898600578308},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4766595959663391},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4698183834552765},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4687265157699585},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4534676969051361},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4190669655799866},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34799355268478394}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8953844904899597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8290560245513916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7495083808898926},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6159034967422485},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6128784418106079},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5220789313316345},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5074898600578308},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4766595959663391},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4698183834552765},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4687265157699585},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4534676969051361},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4190669655799866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34799355268478394},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2733373.2806222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","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":66,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W154472438","https://openalex.org/W237546731","https://openalex.org/W240069591","https://openalex.org/W1542618002","https://openalex.org/W1568514080","https://openalex.org/W1686810756","https://openalex.org/W1806891645","https://openalex.org/W1920196880","https://openalex.org/W1965555842","https://openalex.org/W1979931042","https://openalex.org/W1983364832","https://openalex.org/W1993229407","https://openalex.org/W2016053056","https://openalex.org/W2024051019","https://openalex.org/W2024868105","https://openalex.org/W2025954386","https://openalex.org/W2031823405","https://openalex.org/W2035192458","https://openalex.org/W2039044448","https://openalex.org/W2062118960","https://openalex.org/W2069682406","https://openalex.org/W2079735306","https://openalex.org/W2087461551","https://openalex.org/W2093367888","https://openalex.org/W2102605133","https://openalex.org/W2105101328","https://openalex.org/W2111308925","https://openalex.org/W2112020727","https://openalex.org/W2114016557","https://openalex.org/W2116435618","https://openalex.org/W2122476475","https://openalex.org/W2123277412","https://openalex.org/W2131042978","https://openalex.org/W2136036867","https://openalex.org/W2140897751","https://openalex.org/W2141355815","https://openalex.org/W2142258645","https://openalex.org/W2142521298","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2151103935","https://openalex.org/W2155893237","https://openalex.org/W2156303437","https://openalex.org/W2163605009","https://openalex.org/W2164507085","https://openalex.org/W2164587673","https://openalex.org/W2171188027","https://openalex.org/W2184188583","https://openalex.org/W2538008885","https://openalex.org/W2950179405","https://openalex.org/W2951183276","https://openalex.org/W2951650375","https://openalex.org/W2951893483","https://openalex.org/W2952186347","https://openalex.org/W2952453038","https://openalex.org/W2953061907","https://openalex.org/W2964227963","https://openalex.org/W6600983433","https://openalex.org/W6609060481","https://openalex.org/W6655288279","https://openalex.org/W6656675045","https://openalex.org/W6674914833","https://openalex.org/W6678029491","https://openalex.org/W6685188343","https://openalex.org/W6686207219"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2899027234","https://openalex.org/W3047363187","https://openalex.org/W3119773509","https://openalex.org/W3177373753","https://openalex.org/W4309346246","https://openalex.org/W4311555960"],"abstract_inverted_index":{"Classifying":[0],"videos":[1],"according":[2],"to":[3,32,85,110,177],"content":[4],"semantics":[5],"is":[6,30,83,122,155,174],"an":[7],"important":[8,131],"problem":[9],"with":[10,165],"a":[11,21,75,166],"wide":[12],"range":[13],"of":[14,68,106,119,133],"applications.":[15],"In":[16,94],"this":[17,120],"paper,":[18],"we":[19],"propose":[20],"hybrid":[22,124],"deep":[23],"learning":[24,125],"framework":[25,126,212],"for":[26,80,91],"video":[27,135],"classification,":[28,81],"which":[29,82],"able":[31,84],"model":[33,112,129],"static":[34],"spatial":[35,50,144],"information,":[36],"short-term":[37,53,147],"motion,":[38],"as":[39,41],"well":[40],"long-term":[42],"temporal":[43,114,185],"clues":[44],"in":[45,74,150],"the":[46,49,52,107,123,134,143,146,151,163,171,178,184,198,203,219,224],"videos.":[47],"Specifically,":[48],"and":[51,87,145,160,169,195,202,221],"motion":[54,148],"features":[55,70,109,149],"are":[56,71,102,190],"extracted":[57],"separately":[58],"by":[59],"two":[60,66,108,193],"Convolutional":[61],"Neural":[62],"Networks":[63],"(CNN).":[64],"These":[65],"types":[67],"CNN-based":[69],"then":[72],"combined":[73],"regularized":[76,152],"feature":[77,89],"fusion":[78,153,161],"network":[79,154],"learn":[86],"utilize":[88],"relationships":[90],"improved":[92],"performance.":[93],"addition,":[95],"Long":[96],"Short":[97],"Term":[98],"Memory":[99],"(LSTM)":[100],"networks":[101],"applied":[103],"on":[104,192,218,223],"top":[105],"further":[111],"longer-term":[113],"clues.":[115],"The":[116],"main":[117],"contribution":[118],"work":[121],"that":[127,140],"can":[128],"several":[130],"aspects":[132],"data.":[136],"We":[137],"also":[138],"show":[139],"(1)":[141],"combining":[142],"better":[156],"than":[157],"direct":[158],"classification":[159,180],"using":[162],"CNN":[164],"softmax":[167],"layer,":[168],"(2)":[170],"sequence-based":[172],"LSTM":[173],"highly":[175],"complementary":[176],"traditional":[179],"strategy":[181],"without":[182],"considering":[183],"frame":[186],"orders.":[187],"Extensive":[188],"experiments":[189],"conducted":[191],"popular":[194],"challenging":[196],"benchmarks,":[197,210],"UCF-101":[199,220],"Human":[200],"Actions":[201],"Columbia":[204],"Consumer":[205],"Videos":[206],"(CCV).":[207],"On":[208],"both":[209],"our":[211],"achieves":[213],"very":[214],"competitive":[215],"performance:":[216],"91.3%":[217],"83.5%":[222],"CCV.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":66},{"year":2020,"cited_by_count":62},{"year":2019,"cited_by_count":62},{"year":2018,"cited_by_count":57},{"year":2017,"cited_by_count":57},{"year":2016,"cited_by_count":49},{"year":2015,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}