{"id":"https://openalex.org/W4386502564","doi":"https://doi.org/10.1145/3587716.3587761","title":"Multi-semantic Representation with Transformer Network for Video Classification","display_name":"Multi-semantic Representation with Transformer Network for Video Classification","publication_year":2023,"publication_date":"2023-02-17","ids":{"openalex":"https://openalex.org/W4386502564","doi":"https://doi.org/10.1145/3587716.3587761"},"language":"en","primary_location":{"id":"doi:10.1145/3587716.3587761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3587716.3587761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 15th International Conference on Machine Learning and Computing","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/A5033224121","display_name":"Yuxi Sun","orcid":"https://orcid.org/0000-0002-3040-5880"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxi Sun","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3040-5880","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047086387","display_name":"Tianzhe Xiao","orcid":"https://orcid.org/0009-0008-7343-4391"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tonghuan Xiao","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-7343-4391","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063318300","display_name":"Xutao Li","orcid":"https://orcid.org/0000-0003-1894-984X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xutao Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1894-984X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002523892","display_name":"Yunming Ye","orcid":"https://orcid.org/0000-0002-1807-8581"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunming Ye","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1807-8581","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033224121"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10293388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"274","last_page":"278"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"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":0.9966999888420105,"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":0.7964106798171997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6615215539932251},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6174745559692383},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5496545433998108},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49812960624694824},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4524584412574768},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.44848737120628357},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43964889645576477},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4182612895965576},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32528021931648254},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.13225024938583374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964106798171997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6615215539932251},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6174745559692383},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5496545433998108},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49812960624694824},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4524584412574768},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.44848737120628357},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43964889645576477},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4182612895965576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32528021931648254},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.13225024938583374},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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:10.1145/3587716.3587761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3587716.3587761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 15th International Conference on Machine Learning and Computing","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":12,"referenced_works":["https://openalex.org/W2126579184","https://openalex.org/W2186222003","https://openalex.org/W4234552385","https://openalex.org/W4301409532","https://openalex.org/W6600001191","https://openalex.org/W6600238479","https://openalex.org/W6600263792","https://openalex.org/W6600577311","https://openalex.org/W6601205648","https://openalex.org/W6604277135","https://openalex.org/W6604663618","https://openalex.org/W6813542777"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2183306018","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W1886884218","https://openalex.org/W1910826599"],"abstract_inverted_index":{"Video":[0,19],"classification":[1,68,180],"is":[2,70,169],"an":[3,28,125],"important":[4],"and":[5,16,24,34,67,100,115,154],"challenging":[6],"task.":[7],"Videos":[8],"usually":[9,43],"contain":[10],"a":[11,80,101,148,162,177],"series":[12],"of":[13,91,112,118,133,147],"key":[14],"actions":[15,33],"motion":[17],"patterns.":[18],"classifiers":[20],"need":[21],"to":[22,55,143,171],"learn":[23],"describe":[25],"them":[26],"with":[27],"embedding":[29,126,157],"vector.":[30,127],"Generally,":[31],"these":[32,141,151],"patterns":[35],"imply":[36],"different":[37,131],"semantic":[38,47,96],"information.":[39],"However,":[40],"existing":[41],"methods":[42],"only":[44],"consider":[45],"single-level":[46],"features,":[48],"such":[49],"as":[50],"the":[51,57,76,109,116,119,155],"last":[52,120],"pooling":[53],"layer,":[54],"represent":[56],"entire":[58],"video.":[59,149,173],"Complex":[60],"video":[61,86,113,179],"content":[62],"cannot":[63],"be":[64],"effectively":[65],"represented,":[66],"accuracy":[69],"not":[71],"good":[72],"enough.":[73],"To":[74],"address":[75],"limitation,":[77],"we":[78],"propose":[79],"novel":[81],"multi-semantic":[82,145,152],"representation":[83],"method":[84,89,185],"for":[85],"classification.":[87],"Our":[88],"consists":[90],"several":[92],"transformer":[93,106],"network":[94],"blocks,":[95],"graph":[97,137],"attention":[98,138],"modules,":[99],"feature":[102,163],"fusion":[103,164],"module.":[104,165],"Each":[105],"block":[107,121],"extracts":[108],"visual":[110,134],"features":[111,117,142],"frames":[114],"are":[122,159],"transformed":[123],"into":[124],"These":[128],"blocks":[129],"indicate":[130],"levels":[132],"features.":[135],"The":[136,166],"module":[139],"uses":[140],"generate":[144],"vectors":[146,153],"Finally,":[150],"previous":[156],"vector":[158,168],"fused":[160,167],"by":[161],"applied":[170],"classify":[172],"Extensive":[174],"experiments":[175],"on":[176],"benchmark":[178],"dataset":[181],"demonstrate":[182],"that":[183],"our":[184],"outperforms":[186],"various":[187],"state-of-the-art":[188],"methods.":[189]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}