{"id":"https://openalex.org/W4386597030","doi":"https://doi.org/10.1109/icip49359.2023.10222496","title":"Implicit Attention-Based Cross-Modal Collaborative Learning for Action Recognition","display_name":"Implicit Attention-Based Cross-Modal Collaborative Learning for Action Recognition","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386597030","doi":"https://doi.org/10.1109/icip49359.2023.10222496"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5084986359","display_name":"Jianghao Zhang","orcid":"https://orcid.org/0000-0002-5245-507X"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghao Zhang","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064738683","display_name":"Xian Zhong","orcid":"https://orcid.org/0000-0002-5242-0467"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhong","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564555","display_name":"Wenxuan Liu","orcid":"https://orcid.org/0000-0002-4417-6628"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Liu","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103140908","display_name":"Kui Jiang","orcid":"https://orcid.org/0000-0002-4055-7503"},"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":"Kui Jiang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024393567","display_name":"Zhengwei Yang","orcid":"https://orcid.org/0000-0002-8190-1438"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengwei Yang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401164","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0003-3846-9157"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3020","last_page":"3024"},"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":0.9926999807357788,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9919000267982483,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7720674276351929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7286630868911743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.653106153011322},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6308466196060181},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6290066838264465},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.605825662612915},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5450246334075928},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5408355593681335},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4786059558391571},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.47148963809013367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45005205273628235},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41639429330825806},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37160420417785645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10422158241271973},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.07171067595481873}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7720674276351929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286630868911743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.653106153011322},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6308466196060181},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6290066838264465},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.605825662612915},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5450246334075928},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5408355593681335},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4786059558391571},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.47148963809013367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45005205273628235},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41639429330825806},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37160420417785645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10422158241271973},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.07171067595481873},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1422118355","display_name":null,"funder_award_id":"62171325","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1629549548","display_name":null,"funder_award_id":"62271361","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W2106996050","https://openalex.org/W2126579184","https://openalex.org/W2473890477","https://openalex.org/W2614128781","https://openalex.org/W2795597953","https://openalex.org/W2799176631","https://openalex.org/W2921102529","https://openalex.org/W2962793481","https://openalex.org/W2963645879","https://openalex.org/W2964212735","https://openalex.org/W2981385151","https://openalex.org/W2990503944","https://openalex.org/W2994669106","https://openalex.org/W3089351764","https://openalex.org/W3091959638","https://openalex.org/W3092499653","https://openalex.org/W3092651603","https://openalex.org/W3108892828","https://openalex.org/W3119401101","https://openalex.org/W3120229390","https://openalex.org/W3124692185","https://openalex.org/W3126721948","https://openalex.org/W3155080005","https://openalex.org/W3177141386","https://openalex.org/W3203934469","https://openalex.org/W3209480014","https://openalex.org/W4307288543","https://openalex.org/W4312843817","https://openalex.org/W4375839990","https://openalex.org/W4376133174","https://openalex.org/W4382449787","https://openalex.org/W4386071639","https://openalex.org/W6600983433","https://openalex.org/W6783988961","https://openalex.org/W6784043113","https://openalex.org/W6789526315"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Human":[0],"action":[1,19,66],"recognition":[2],"is":[3],"an":[4,58],"active":[5],"research":[6],"topic":[7],"in":[8],"recent":[9],"years.":[10],"Multiple":[11],"modalities":[12],"often":[13],"convey":[14],"heterogeneous":[15],"but":[16,41],"potentially":[17],"complementary":[18],"information":[20,107],"that":[21],"single":[22],"modality":[23,82,106],"does":[24],"not":[25],"hold.":[26],"Some":[27],"efforts":[28],"have":[29],"been":[30],"resoted":[31],"to":[32,36,46,79,121],"explore":[33],"cross-modal":[34,123],"representation":[35,83,94,112],"promote":[37],"the":[38,47,97,105,110,139],"modeling":[39],"capability,":[40],"with":[42,75],"limited":[43],"improvement":[44],"due":[45],"simple":[48],"fusion":[49],"of":[50,143],"different":[51],"modalities.":[52],"To":[53],"this":[54],"end,":[55],"we":[56,69,90],"propose":[57],"impliCit":[59],"attention-based":[60],"Cross-modal":[61],"Collaborative":[62],"Learning":[63],"(C3L)":[64],"for":[65],"recognition.":[67],"Specifically,":[68],"apply":[70],"a":[71,92],"Modality":[72,99],"Generalization":[73],"network":[74],"Grayscale":[76],"enhancement":[77],"(MGG)":[78],"learn":[80],"specific":[81],"and":[84,87,136,141],"interaction":[85],"(infrared":[86],"RGB).":[88],"Then,":[89],"construct":[91],"unified":[93],"space":[95],"through":[96],"Uniform":[98],"Representation":[100],"module":[101],"(UMR),":[102],"which":[103],"preserves":[104],"while":[108],"enhancing":[109],"overall":[111],"ability.":[113],"Finally,":[114],"feature":[115],"extractors":[116],"adaptively":[117],"leverage":[118],"modality-specific":[119],"knowledge":[120],"realize":[122],"collaborative":[124],"learning.":[125],"Extensive":[126],"experiments":[127],"conducted":[128],"on":[129],"three":[130],"widely-used":[131],"public":[132],"benchmarks":[133],"InfAR,":[134],"HMDB51,":[135],"UCF101,":[137],"demonstrate":[138],"effectiveness":[140],"strength":[142],"our":[144],"proposed":[145],"method.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}