{"id":"https://openalex.org/W4372348095","doi":"https://doi.org/10.1109/icassp49357.2023.10097076","title":"Learning from the Raw Domain: Cross Modality Distillation for Compressed Video Action Recognition","display_name":"Learning from the Raw Domain: Cross Modality Distillation for Compressed Video Action Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348095","doi":"https://doi.org/10.1109/icassp49357.2023.10097076"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5068621276","display_name":"Yufan Liu","orcid":"https://orcid.org/0000-0002-8426-9335"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufan Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems","School of Artificial Intelligence, University of Chinese Academy of Sciences","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047838263","display_name":"Jiajiong Cao","orcid":"https://orcid.org/0000-0001-8311-5820"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajiong Cao","raw_affiliation_strings":["Ant Financial Service Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Financial Service Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082570989","display_name":"Weiming Bai","orcid":"https://orcid.org/0000-0002-6168-2987"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Bai","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems","School of Artificial Intelligence, University of Chinese Academy of Sciences","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109346446","display_name":"Bing Li","orcid":"https://orcid.org/0000-0002-5888-6735"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems","PeopleAI, Inc","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"PeopleAI, Inc","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114549594","display_name":"Weiming Hu","orcid":"https://orcid.org/0000-0001-9237-8825"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Hu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems","School of Artificial Intelligence, University of Chinese Academy of Sciences","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9904999732971191,"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":0.7994149327278137},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6290400624275208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6141759157180786},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6076567769050598},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5825597047805786},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5655511021614075},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5058957934379578},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43914994597435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3919524550437927},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3450046181678772},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14248549938201904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08025035262107849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994149327278137},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6290400624275208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141759157180786},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6076567769050598},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5825597047805786},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5655511021614075},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5058957934379578},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43914994597435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3919524550437927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3450046181678772},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14248549938201904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08025035262107849},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335919","display_name":"Major Projects of Guangdong Education Department for Foundation Research and Applied Research","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W2108598243","https://openalex.org/W2115907784","https://openalex.org/W2126579184","https://openalex.org/W2770804203","https://openalex.org/W2955192706","https://openalex.org/W2963370182","https://openalex.org/W2963524571","https://openalex.org/W2963901365","https://openalex.org/W2990152177","https://openalex.org/W2996901793","https://openalex.org/W3015830103","https://openalex.org/W3034600407","https://openalex.org/W3035619757","https://openalex.org/W3035697644","https://openalex.org/W3092651603","https://openalex.org/W3127290523","https://openalex.org/W3175528717","https://openalex.org/W3194397797","https://openalex.org/W3211119616","https://openalex.org/W4214727094","https://openalex.org/W4283328744","https://openalex.org/W4323647559","https://openalex.org/W6600983433","https://openalex.org/W6790594157","https://openalex.org/W6803603938","https://openalex.org/W6839461871"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W3203142394","https://openalex.org/W2374013449","https://openalex.org/W4302615923","https://openalex.org/W73545470","https://openalex.org/W1583422155","https://openalex.org/W3213252596","https://openalex.org/W1649619740","https://openalex.org/W1534006406"],"abstract_inverted_index":{"Video":[0],"action":[1],"recognition":[2],"is":[3,25,101],"faced":[4],"with":[5,40],"the":[6,50,61,66,69,87,91,105,116,119],"challenges":[7],"of":[8,118],"both":[9],"huge":[10],"computation":[11],"burden":[12],"and":[13,76,90,124],"performance":[14],"requirements.":[15],"Using":[16],"compressed":[17,92],"domain":[18,89],"data,":[19],"which":[20],"saves":[21],"much":[22],"decoding":[23],"computation,":[24],"a":[26,54,110],"possible":[27],"solution.":[28],"Unfortunately,":[29],"existing":[30],"compressed-domain-based":[31],"(CD)":[32],"methods":[33],"fail":[34],"to":[35,48,59,64,82,103],"obtain":[36],"high":[37],"performance,":[38],"compared":[39],"state-of-the-art":[41],"(SOTA)":[42],"raw-domain-based":[43],"(RD)":[44],"methods.":[45],"In":[46,72],"order":[47],"solve":[49],"problem,":[51],"we":[52],"propose":[53],"cross-modality":[55],"knowledge":[56,67,75,78,98],"distillation":[57],"method":[58,121],"force":[60],"CD":[62,106],"model":[63,107],"learn":[65,108],"from":[68],"RD":[70],"model.":[71],"particular,":[73],"spatial":[74],"temporal":[77],"are":[79],"first":[80],"constructed":[81],"align":[83],"feature":[84],"space":[85],"between":[86],"raw":[88],"domain.":[93],"Then,":[94],"an":[95],"adaptively":[96],"multi-path":[97],"learning":[99],"scheme":[100],"presented":[102],"help":[104],"in":[109,122],"more":[111],"efficient":[112],"way.":[113],"Experiments":[114],"verify":[115],"effectiveness":[117],"proposed":[120],"large-scale":[123],"small-scale":[125],"datasets.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}