{"id":"https://openalex.org/W7113903230","doi":"https://doi.org/10.1109/tcsvt.2025.3642759","title":"MR-MAR: Multi-Layer Representation Learning for Multi-Modal Action Recognition","display_name":"MR-MAR: Multi-Layer Representation Learning for Multi-Modal Action Recognition","publication_year":2025,"publication_date":"2025-12-10","ids":{"openalex":"https://openalex.org/W7113903230","doi":"https://doi.org/10.1109/tcsvt.2025.3642759"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3642759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3642759","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Bingshuo Lu","orcid":"https://orcid.org/0009-0002-8594-5849"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingshuo Lu","raw_affiliation_strings":["School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0002-8594-5849","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhigang Liu","orcid":"https://orcid.org/0000-0003-2399-248X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Liu","raw_affiliation_strings":["School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0000-0003-2399-248X","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rongbin Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongbin Zheng","raw_affiliation_strings":["School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaiyi An","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyi An","raw_affiliation_strings":["School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinlong Xu","orcid":"https://orcid.org/0009-0009-4820-8234"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlong Xu","raw_affiliation_strings":["School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0009-4820-8234","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chunlei Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlei Gao","raw_affiliation_strings":["School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54012519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"6852","last_page":"6865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9291999936103821,"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":0.9291999936103821,"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":0.021900000050663948,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.008899999782443047,"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/motion","display_name":"Motion (physics)","score":0.6086999773979187},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5787000060081482},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5485000014305115},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.43389999866485596},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.42410001158714294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4219000041484833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361999750137329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.671999990940094},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6086999773979187},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5485000014305115},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3959999978542328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3709999918937683},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3700000047683716},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3642759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3642759","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7495818138122559}],"awards":[{"id":"https://openalex.org/G3801114779","display_name":null,"funder_award_id":"F2024501002","funder_id":"https://openalex.org/F4320322163","funder_display_name":"Natural Science Foundation of Hebei Province"},{"id":"https://openalex.org/G7640292181","display_name":null,"funder_award_id":"62306068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8319501857","display_name":null,"funder_award_id":"61973069","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"},{"id":"https://openalex.org/F4320322163","display_name":"Natural Science Foundation of Hebei Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human":[0],"daily":[1],"action":[2],"recognition":[3],"is":[4],"a":[5,37,66],"challenging":[6],"task":[7],"because":[8],"of":[9,13,79],"the":[10,21,31,76,85,91,116,121,126],"complex":[11],"structure":[12],"actions.":[14],"To":[15],"address":[16],"this":[17],"challenge,":[18],"we":[19,35,64,95],"present":[20],"Multi-layer":[22],"Representation":[23],"Learning":[24,70],"for":[25],"Multi-modal":[26,67],"Action":[27],"Recognition":[28],"(MR-MAR).":[29],"In":[30,90],"atom":[32],"encoding":[33,93],"layer,":[34,94],"design":[36],"Motion":[38,109],"Atom":[39,69],"spatial":[40,50],"Alignment":[41],"(MAA)":[42],"module":[43,72],"to":[44,73,114,137,145,151],"construct":[45],"contrastive":[46],"pairs":[47,55,60],"and":[48,88,106,156],"realize":[49],"alignment":[51],"by":[52,119],"pulling":[53],"positive":[54],"closer":[56],"while":[57],"pushing":[58],"negative":[59],"further":[61],"away.":[62],"Moreover,":[63],"devise":[65],"motion":[68,81,97,101],"(MAL)":[71],"effectively":[74],"capture":[75,115],"nonlinear":[77],"relationships":[78],"multi-modal":[80,130],"atoms,":[82],"thereby":[83],"enhancing":[84],"semantic":[86],"diversity":[87],"discriminability.":[89],"phrase":[92,110],"combine":[96],"atoms":[98],"into":[99],"multi-scale":[100],"phrases":[102],"as":[103],"high-level":[104],"representations":[105],"carry":[107],"out":[108],"Temporal":[111],"Modeling":[112],"(MTM)":[113],"temporal":[117],"patterns":[118],"updating":[120],"hidden":[122],"states.":[123],"We":[124],"evaluate":[125],"MR-MAR":[127],"on":[128,139,147,153,159],"four":[129],"benchmarks,":[131],"achieving":[132],"improvements":[133],"ranging":[134],"from":[135],"0.9%":[136],"9.4%":[138],"NTU":[140],"RGB+D":[141],"120":[142],"dataset,":[143,149,155],"0.6%":[144],"5.5%":[146],"N-UCLA":[148],"0.4%":[150],"6.2%":[152],"PKU-MMD":[154],"competitive":[157],"performance":[158],"Toyota-Smarthome":[160],"dataset.":[161]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-12-11T00:00:00"}