{"id":"https://openalex.org/W4310877696","doi":"https://doi.org/10.1145/3572776","title":"HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition","display_name":"HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition","publication_year":2022,"publication_date":"2022-12-02","ids":{"openalex":"https://openalex.org/W4310877696","doi":"https://doi.org/10.1145/3572776"},"language":"en","primary_location":{"id":"doi:10.1145/3572776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572776","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.09760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075142476","display_name":"Zejia Weng","orcid":"https://orcid.org/0000-0001-9706-6484"},"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":"Zejia Weng","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Info. Processing, School of CS, Fudan University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Info. Processing, School of CS, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","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":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Info. Processing, School of CS, Fudan University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Info. Processing, School of CS, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024600500","display_name":"Hengduo Li","orcid":"https://orcid.org/0000-0001-5314-6853"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hengduo Li","raw_affiliation_strings":["Department of Computer Science, University of Maryland, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Maryland, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"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":"Jingjing Chen","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Info. Processing, School of CS, Fudan University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Info. Processing, School of CS, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","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":["Shanghai Key Lab of Intelligent Info. Processing, School of CS, Fudan University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Info. Processing, School of CS, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075142476"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.8167,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73634222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"20","issue":"2","first_page":"1","last_page":"18"},"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":0.9998000264167786,"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":0.9986000061035156,"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":0.8301773071289062},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7757517099380493},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7752131819725037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5854020714759827},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5745061635971069},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.5221876502037048},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5202785134315491},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4760294258594513},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3356969952583313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301773071289062},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7757517099380493},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7752131819725037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5854020714759827},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5745061635971069},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.5221876502037048},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5202785134315491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4760294258594513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3356969952583313},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3572776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572776","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2104.09760","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.09760","pdf_url":"https://arxiv.org/pdf/2104.09760","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.09760","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.09760","pdf_url":"https://arxiv.org/pdf/2104.09760","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6809183074","display_name":null,"funder_award_id":"Project No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6994314671","display_name":null,"funder_award_id":"62102092","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1483393862","https://openalex.org/W1777628566","https://openalex.org/W1989469598","https://openalex.org/W2093367888","https://openalex.org/W2464235600","https://openalex.org/W2558122535","https://openalex.org/W2612445135","https://openalex.org/W2613984758","https://openalex.org/W2626250971","https://openalex.org/W2900471873","https://openalex.org/W2912684514","https://openalex.org/W2946719178","https://openalex.org/W2963246338","https://openalex.org/W2963315828","https://openalex.org/W2964045146","https://openalex.org/W2986131686","https://openalex.org/W3002271958","https://openalex.org/W3002552512","https://openalex.org/W3009238340","https://openalex.org/W3015483809","https://openalex.org/W3091825536","https://openalex.org/W3147147958","https://openalex.org/W3171349866","https://openalex.org/W4210324837","https://openalex.org/W4220913778","https://openalex.org/W4281737392","https://openalex.org/W4286421014","https://openalex.org/W4297775537","https://openalex.org/W4313034430","https://openalex.org/W6629009817","https://openalex.org/W6647811946","https://openalex.org/W6763301817","https://openalex.org/W6773226109","https://openalex.org/W6804654437"],"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/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Videos":[0],"are":[1,97],"multimodal":[2,11,50,161],"in":[3,99],"nature.":[4],"Conventional":[5],"video":[6,55,146],"recognition":[7],"pipelines":[8],"typically":[9],"fuse":[10],"features":[12,120],"for":[13,35,53,163],"improved":[14,164],"performance.":[15],"However,":[16],"this":[17],"is":[18,88],"not":[19],"only":[20],"computationally":[21,75],"expensive":[22,76],"but":[23],"also":[24],"neglects":[25],"the":[26,91,152,155],"fact":[27],"that":[28,96,106],"different":[29,33],"videos":[30],"rely":[31],"on":[32,59,83,108,143],"modalities":[34,110],"predictions.":[36],"This":[37,87],"article":[38],"introduces":[39],"Hierarchical":[40],"and":[41,68,80,121,149,151],"Conditional":[42],"Modality":[43],"Selection":[44],"(HCMS),":[45],"a":[46,60,84,100,112],"simple":[47],"yet":[48],"efficient":[49,54],"learning":[51],"framework":[52],"recognition.":[56],"HCMS":[57],"operates":[58],"low-cost":[61],"modality,":[62],"i.e.,":[63],"audio":[64],"clues,":[65,82],"by":[66,90],"default,":[67],"dynamically":[69],"decides":[70],"on-the-fly":[71],"whether":[72,127],"to":[73,124,128],"use":[74],"modalities,":[77],"including":[78],"appearance":[79],"motion":[81],"per-input":[85],"basis.":[86],"achieved":[89],"collaboration":[92],"of":[93],"three":[94],"LSTMs":[95,105],"organized":[98],"hierarchical":[101],"manner.":[102],"In":[103],"particular,":[104],"operate":[107],"high-cost":[109],"contain":[111],"gating":[113],"module,":[114],"which":[115],"takes":[116],"as":[117],"inputs":[118],"lower-level":[119],"historical":[122,137],"information":[123,162],"adaptively":[125],"determine":[126],"activate":[129],"its":[130],"corresponding":[131],"modality;":[132],"otherwise,":[133],"it":[134],"simply":[135],"reuses":[136],"information.":[138],"We":[139],"conduct":[140],"extensive":[141],"experiments":[142],"two":[144],"large-scale":[145],"benchmarks,":[147],"FCVID":[148],"ActivityNet,":[150],"results":[153],"demonstrate":[154],"proposed":[156],"approach":[157],"can":[158],"effectively":[159],"explore":[160],"classification":[165],"performance":[166],"while":[167],"requiring":[168],"much":[169],"less":[170],"computation.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2022-12-19T00:00:00"}