{"id":"https://openalex.org/W7137823325","doi":"https://doi.org/10.1109/tcsvt.2026.3674923","title":"Action Recognition in RGB-D Videos via an End-to-End Cross-Modal Attention Transformer","display_name":"Action Recognition in RGB-D Videos via an End-to-End Cross-Modal Attention Transformer","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7137823325","doi":"https://doi.org/10.1109/tcsvt.2026.3674923"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3674923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3674923","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":"https://openalex.org/A5129708364","display_name":"Yujun Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yujun Ma","raw_affiliation_strings":["School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand"],"raw_orcid":"https://orcid.org/0000-0002-8014-0067","affiliations":[{"raw_affiliation_string":"School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054200099","display_name":"Benjia Zhou","orcid":"https://orcid.org/0000-0003-4883-5552"},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Benjia Zhou","raw_affiliation_strings":["Macau University of Science and Technology, Taipa, Macau, China"],"raw_orcid":"https://orcid.org/0000-0003-4883-5552","affiliations":[{"raw_affiliation_string":"Macau University of Science and Technology, Taipa, Macau, China","institution_ids":["https://openalex.org/I111950717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722123","display_name":"Hong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Hong Zhang","raw_affiliation_strings":["School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand"],"raw_orcid":"https://orcid.org/0000-0003-1206-9841","affiliations":[{"raw_affiliation_string":"School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xizheng Zhang","orcid":"https://orcid.org/0000-0003-2261-5973"},"institutions":[{"id":"https://openalex.org/I27688046","display_name":"Hunan Institute of Engineering","ror":"https://ror.org/03zj2rn70","country_code":"CN","type":"education","lineage":["https://openalex.org/I27688046"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xizheng Zhang","raw_affiliation_strings":["School of Information Science and Engineering, Hunan Institute of Engineering, Xiangtan, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0003-2261-5973","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Hunan Institute of Engineering, Xiangtan, Hunan, China","institution_ids":["https://openalex.org/I27688046"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangjian He","orcid":"https://orcid.org/0000-0001-8962-540X"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangjian He","raw_affiliation_strings":["School of Computer Science, University of Nottingham Ningbo China, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0001-8962-540X","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ruili Wang","orcid":"https://orcid.org/0000-0001-7117-2772"},"institutions":[{"id":"https://openalex.org/I27781120","display_name":"Wenzhou Medical University","ror":"https://ror.org/00rd5t069","country_code":"CN","type":"education","lineage":["https://openalex.org/I27781120"]},{"id":"https://openalex.org/I2801769982","display_name":"First Affiliated Hospital of Wenzhou Medical University","ror":"https://ror.org/03cyvdv85","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2801769982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruili Wang","raw_affiliation_strings":["Geriatrics Center, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7117-2772","affiliations":[{"raw_affiliation_string":"Geriatrics Center, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China","institution_ids":["https://openalex.org/I27781120","https://openalex.org/I2801769982"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26178442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"7","first_page":"9406","last_page":"9417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9559000134468079,"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":0.9559000134468079,"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":0.00559999980032444,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5426999926567078},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5170999765396118},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4214000105857849},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37610000371932983},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.375900000333786},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.320499986410141},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.30230000615119934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7441999912261963},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5788000226020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5539000034332275},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5426999926567078},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5170999765396118},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4016999900341034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3674923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3674923","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":[],"awards":[{"id":"https://openalex.org/G8258248349","display_name":null,"funder_award_id":"ZG2024012","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recognizing":[0],"actions":[1],"in":[2],"RGB-D":[3,177,180],"videos":[4],"necessitates":[5],"an":[6,23],"in-depth":[7],"understanding":[8],"of":[9,26,53,188],"spatial":[10],"and":[11,17,56,77,100,124,153,182],"temporal":[12],"information":[13,146],"from":[14,36,161],"both":[15],"RGB":[16,76,99],"depth":[18,78,101],"modalities,":[19,45,128],"as":[20,22,175],"well":[21],"efficient":[24],"fusion":[25,32,48],"these":[27],"data":[28],"streams.":[29],"Existing":[30],"late":[31],"approaches":[33],"often":[34],"suffer":[35],"modality":[37,55],"collapse":[38],"due":[39],"to":[40,90,115,163,191],"high":[41],"semantic":[42],"similarity":[43],"between":[44,126],"where":[46],"the":[47,50,127,185],"diminishes":[49],"distinct":[51,82],"contributions":[52],"each":[54],"compromises":[57],"overall":[58],"effectiveness.":[59],"In":[60],"this":[61],"context,":[62],"we":[63],"propose":[64],"a":[65,117],"novel":[66],"End-to-end":[67],"Cross-Modal":[68],"Attention":[69],"Transformer":[70],"(E-CMAT)":[71],"model.":[72],"Our":[73,135],"model":[74],"processes":[75],"inputs":[79],"through":[80],"two":[81],"expert":[83,143],"encoders":[84],"that":[85,120],"utilize":[86],"factorized":[87],"spatio-temporal":[88],"representations":[89],"capture":[91],"dimension-independent":[92],"features,":[93],"enhancing":[94],"motion":[95],"understanding.":[96],"The":[97],"extracted":[98],"tokens":[102],"are":[103],"subsequently":[104],"fused":[105],"via":[106],"our":[107],"innovative":[108],"cross-modal":[109,136],"attention,":[110],"which":[111],"is":[112],"applied":[113],"iteratively":[114],"ensure":[116],"robust":[118],"integration":[119],"accentuates":[121],"critical":[122],"patterns":[123],"discrepancies":[125],"thereby":[129],"facilitating":[130],"more":[131],"precise":[132],"action":[133],"recognition.":[134],"attention":[137,149],"utilizes":[138],"one":[139],"class":[140],"token":[141],"per":[142],"for":[144],"inter-expert":[145],"exchange,":[147],"focusing":[148],"on":[150,169],"salient":[151],"features":[152],"fostering":[154],"synergistic":[155],"predictions":[156],"while":[157],"reducing":[158],"computational":[159],"complexity":[160],"quadratic":[162],"linear.":[164],"Furthermore,":[165],"extensive":[166],"experiments":[167],"conducted":[168],"widely":[170],"used":[171],"benchmark":[172],"datasets,":[173],"such":[174],"NTU":[176,179],"60,":[178],"120,":[181],"THU-READ,":[183],"demonstrate":[184],"favorable":[186],"performance":[187],"E-CMAT":[189],"compared":[190],"state-of-the-art":[192],"models.":[193]},"counts_by_year":[],"updated_date":"2026-07-08T06:17:01.165560","created_date":"2026-03-18T00:00:00"}