{"id":"https://openalex.org/W4391307018","doi":"https://doi.org/10.1109/vcip59821.2023.10402629","title":"MotionMLP: End-to-End Action Recognition with Motion Aware Vision MLP","display_name":"MotionMLP: End-to-End Action Recognition with Motion Aware Vision MLP","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4391307018","doi":"https://doi.org/10.1109/vcip59821.2023.10402629"},"language":"en","primary_location":{"id":"doi:10.1109/vcip59821.2023.10402629","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip59821.2023.10402629","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 Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-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/A5040983509","display_name":"Xiangning Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4387152954","display_name":"Ministry of Culture and Tourism","ror":"https://ror.org/04zsc3j83","country_code":null,"type":"government","lineage":["https://openalex.org/I4387152954"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangning Ruan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism","Beijing University of Posts and Telecommunications, China","Beijing Key Laboratory of Network System and Network Culture, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism","institution_ids":["https://openalex.org/I4387152954"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Network System and Network Culture, China","institution_ids":["https://openalex.org/I4210108629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053619472","display_name":"Zhicheng Zhao","orcid":"https://orcid.org/0000-0001-6506-7298"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4387152954","display_name":"Ministry of Culture and Tourism","ror":"https://ror.org/04zsc3j83","country_code":null,"type":"government","lineage":["https://openalex.org/I4387152954"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Zhao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing Key Laboratory of Network System and Network Culture, China","Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism","Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Network System and Network Culture, China","institution_ids":["https://openalex.org/I4210108629"]},{"raw_affiliation_string":"Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism","institution_ids":["https://openalex.org/I4387152954"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101754632","display_name":"Fei Su","orcid":"https://orcid.org/0000-0003-4245-4687"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4387152954","display_name":"Ministry of Culture and Tourism","ror":"https://ror.org/04zsc3j83","country_code":null,"type":"government","lineage":["https://openalex.org/I4387152954"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Su","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China","Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism","Beijing Key Laboratory of Network System and Network Culture, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism","institution_ids":["https://openalex.org/I4387152954"]},{"raw_affiliation_string":"Beijing Key Laboratory of Network System and Network Culture, China","institution_ids":["https://openalex.org/I4210108629"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040983509"],"corresponding_institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4210108629","https://openalex.org/I4387152954"],"apc_list":null,"apc_paid":null,"fwci":0.123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4615405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"27","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8622965216636658},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.7782802581787109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6767212748527527},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6337992548942566},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.559228241443634},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5435866713523865},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5117392539978027},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.48910003900527954},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4804358184337616},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4531860053539276},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41226184368133545},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13149863481521606},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10149267315864563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8622965216636658},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.7782802581787109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6767212748527527},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6337992548942566},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.559228241443634},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5435866713523865},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5117392539978027},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.48910003900527954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4804358184337616},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4531860053539276},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41226184368133545},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13149863481521606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10149267315864563},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip59821.2023.10402629","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip59821.2023.10402629","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 Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1923404803","https://openalex.org/W1926645898","https://openalex.org/W2016053056","https://openalex.org/W2105101328","https://openalex.org/W2126579184","https://openalex.org/W2156303437","https://openalex.org/W2194775991","https://openalex.org/W2342776425","https://openalex.org/W2507009361","https://openalex.org/W2606212668","https://openalex.org/W2618530766","https://openalex.org/W2948242301","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963886665","https://openalex.org/W2964037671","https://openalex.org/W3094454579","https://openalex.org/W3110190397","https://openalex.org/W3145385912","https://openalex.org/W3157506437","https://openalex.org/W3176780013","https://openalex.org/W3185605671","https://openalex.org/W3186979696","https://openalex.org/W4212819272","https://openalex.org/W4214747681","https://openalex.org/W4221167396","https://openalex.org/W4310282783","https://openalex.org/W4312853765","https://openalex.org/W4386057769","https://openalex.org/W4387055524","https://openalex.org/W6600983433","https://openalex.org/W6637373629","https://openalex.org/W6682864246","https://openalex.org/W6784660784","https://openalex.org/W6795140394","https://openalex.org/W6799423381","https://openalex.org/W6810265253","https://openalex.org/W6846747260"],"related_works":["https://openalex.org/W4297270893","https://openalex.org/W2577671007","https://openalex.org/W1591216093","https://openalex.org/W3091300685","https://openalex.org/W2912100719","https://openalex.org/W2331280411","https://openalex.org/W2963330455","https://openalex.org/W2783931899","https://openalex.org/W4283332100","https://openalex.org/W4225597351"],"abstract_inverted_index":{"Action":[0],"recognition":[1],"aims":[2],"to":[3,25],"interpret":[4],"complex":[5],"spatiotemporal":[6],"patterns":[7],"in":[8],"the":[9,70,78,108,123],"video.":[10],"Current":[11],"methods":[12,21,113],"utilize":[13],"CNN":[14,129],"or":[15,97],"Transformer":[16],"structures,":[17],"requiring":[18],"extensive":[19],"pre-training":[20,95],"and":[22,41,48,74,90,116,118],"optical":[23,98],"flow":[24,99],"capture":[26],"motion":[27,63],"information.":[28],"Such":[29],"approaches":[30],"are":[31],"computationally":[32],"expensive,":[33],"necessitate":[34],"significant":[35],"storage,":[36],"cannot":[37],"be":[38],"trained":[39],"end-to-end,":[40],"typically":[42],"neglect":[43],"joint":[44],"learning":[45],"of":[46,93,122],"temporal":[47],"spatial":[49],"streams.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"MotionMLP,":[56],"a":[57],"novel":[58],"MLP":[59,79],"architecture":[60],"that":[61,105],"extracts":[62],"information":[64],"from":[65],"videos,":[66],"then":[67],"dynamically":[68],"adjusts":[69],"connection":[71],"between":[72],"tokens":[73],"static":[75],"weights":[76],"within":[77],"structure.":[80],"The":[81,101],"MotionMLP":[82,106],"solely":[83],"relies":[84,119],"on":[85,114,120],"video":[86],"frames":[87],"as":[88],"input":[89],"is":[91],"independent":[92],"any":[94],"method":[96],"computation.":[100],"experimental":[102],"results":[103],"indicate":[104],"outperforms":[107],"previous":[109],"SOTA":[110],"real-time":[111],"end-to-end":[112],"UCF101":[115],"HMDB51,":[117],"one-tenth":[121],"parameters":[124],"compared":[125],"with":[126],"typical":[127],"two-stream":[128],"approaches,":[130],"while":[131],"operating":[132],"ten":[133],"times":[134],"faster.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}