{"id":"https://openalex.org/W2551491964","doi":"https://doi.org/10.1109/ijcnn.2016.7727435","title":"Exploring multimodal video representation for action recognition","display_name":"Exploring multimodal video representation for action recognition","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2551491964","doi":"https://doi.org/10.1109/ijcnn.2016.7727435","mag":"2551491964"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2016.7727435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","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/A5100416961","display_name":"Cheng Wang","orcid":"https://orcid.org/0000-0001-6075-796X"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Cheng Wang","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003983595","display_name":"Haojin Yang","orcid":"https://orcid.org/0000-0002-8733-5772"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Haojin Yang","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102919398","display_name":"Christoph Meinel","orcid":"https://orcid.org/0000-0002-3410-3193"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Meinel","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100416961"],"corresponding_institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":1.169,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.85590817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1924","last_page":"1931"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9921000003814697,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7977389097213745},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6971544623374939},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6936452388763428},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6307153701782227},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5407400727272034},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4794429838657379},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4787956178188324},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4648614823818207},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.42285558581352234},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.4190976023674011},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38045117259025574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.340688019990921},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.27363866567611694},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12644556164741516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7977389097213745},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6971544623374939},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6936452388763428},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6307153701782227},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5407400727272034},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4794429838657379},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4787956178188324},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4648614823818207},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.42285558581352234},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.4190976023674011},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38045117259025574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.340688019990921},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27363866567611694},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12644556164741516},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2016.7727435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W787785461","https://openalex.org/W1595717062","https://openalex.org/W1606858007","https://openalex.org/W1686810756","https://openalex.org/W1849277567","https://openalex.org/W1867429401","https://openalex.org/W1871385855","https://openalex.org/W1947481528","https://openalex.org/W1974794302","https://openalex.org/W1977814411","https://openalex.org/W1980176153","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2039089492","https://openalex.org/W2053101950","https://openalex.org/W2069682406","https://openalex.org/W2105101328","https://openalex.org/W2108598243","https://openalex.org/W2116435618","https://openalex.org/W2126574503","https://openalex.org/W2140641199","https://openalex.org/W2142194269","https://openalex.org/W2155893237","https://openalex.org/W2156303437","https://openalex.org/W2163605009","https://openalex.org/W2163973188","https://openalex.org/W2164507085","https://openalex.org/W2164587673","https://openalex.org/W2166294429","https://openalex.org/W2184188583","https://openalex.org/W2951183276","https://openalex.org/W2951552696","https://openalex.org/W2962835968","https://openalex.org/W6606244218","https://openalex.org/W6622789128","https://openalex.org/W6637373629","https://openalex.org/W6639126518","https://openalex.org/W6639141586","https://openalex.org/W6640617836","https://openalex.org/W6677326919","https://openalex.org/W6680832002","https://openalex.org/W6682864246","https://openalex.org/W6684191040","https://openalex.org/W6686207219"],"related_works":["https://openalex.org/W1975325338","https://openalex.org/W4297270893","https://openalex.org/W2577671007","https://openalex.org/W3091300685","https://openalex.org/W2912100719","https://openalex.org/W2331280411","https://openalex.org/W2963330455","https://openalex.org/W1591216093","https://openalex.org/W2783931899","https://openalex.org/W3181401746"],"abstract_inverted_index":{"A":[0],"video":[1,52,66,107,165],"contains":[2,166],"rich":[3],"perceptual":[4],"information,":[5],"such":[6],"as":[7,69,71],"visual":[8],"appearance,":[9,67],"motion":[10,33,68],"and":[11,32,117,123,143,158,184],"audio,":[12],"which":[13,163,207],"can":[14,36,187],"be":[15,188],"used":[16],"for":[17,80,169,190],"understanding":[18],"the":[19,27,48,99,135],"activities":[20],"in":[21,43,53,162,200],"videos.":[22,44],"Recent":[23],"works":[24],"have":[25],"shown":[26],"combination":[28],"of":[29,51,101,137,151],"appearance":[30],"(spatial)":[31],"(temporal)":[34],"clues":[35],"significantly":[37],"improve":[38],"human":[39],"action":[40,54,170],"recognition":[41],"performance":[42],"To":[45],"further":[46],"explore":[47],"multimodal":[49,63,185],"representation":[50,186],"recognition,":[55],"We":[56],"propose":[57,92],"a":[58,62,95,105],"framework":[59],"to":[60,93,103,128,181,211],"learn":[61,104],"representations":[64],"from":[65],"well":[70],"audio":[72,139,167],"data.":[73],"Convolutional":[74],"Neural":[75,121],"Networks":[76],"(CNN)":[77],"are":[78,179],"trained":[79],"each":[81,164,182],"modality":[82],"respectively.":[83],"For":[84],"fusing":[85,201],"multiple":[86],"features":[87],"extracted":[88],"with":[89,120],"CNNs,":[90],"we":[91,112],"add":[94],"fusion":[96,110,116,119,147,195],"layer":[97],"on":[98,156,203],"top":[100],"CNNs":[102],"joint":[106],"representation.":[108],"In":[109],"phase,":[111],"investigate":[113],"both":[114],"early":[115],"late":[118],"Network":[122],"Support":[124],"Vector":[125],"Machine.":[126],"Compare":[127],"existing":[129],"works,":[130],"(1)":[131],"our":[132],"work":[133],"measures":[134],"benefits":[136],"taking":[138],"information":[140],"into":[141],"consideration":[142],"(2)":[144],"implements":[145],"sophisticated":[146],"methods.":[148],"The":[149,172],"effectiveness":[150],"proposed":[152,194],"approach":[153,196],"is":[154,208],"evaluated":[155],"UCF101":[157,204],"UCF101-50":[159],"(selected":[160],"subset":[161],"data)":[168],"recognition.":[171],"experimental":[173],"results":[174],"show":[175],"that":[176],"different":[177],"modalities":[178],"complementary":[180],"other":[183],"beneficial":[189],"final":[191],"prediction.":[192],"Furthermore,":[193],"achieves":[197],"85.1%":[198],"accuracy":[199],"spatial-temporal":[202],"(split":[205],"1),":[206],"very":[209],"competitive":[210],"state-of-the-art":[212],"works.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}