{"id":"https://openalex.org/W4379806333","doi":"https://doi.org/10.1145/3591106.3592233","title":"Less is More: Decoupled High-Semantic Encoding for Action Recognition","display_name":"Less is More: Decoupled High-Semantic Encoding for Action Recognition","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806333","doi":"https://doi.org/10.1145/3591106.3592233"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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/A5101879419","display_name":"Chun Zhang","orcid":"https://orcid.org/0000-0002-8441-8679"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chun Zhang","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054081908","display_name":"Keyan Ren","orcid":"https://orcid.org/0000-0002-7332-2882"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyan Ren","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031366348","display_name":"Qingyun Bian","orcid":"https://orcid.org/0009-0003-3334-9508"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyun Bian","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101982424","display_name":"Yu Shi","orcid":"https://orcid.org/0009-0008-8088-5510"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Faculty of Information Technology,, Beijing University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology,, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101879419"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50224673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"262","last_page":"271"},"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":0.9976000189781189,"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":0.9775000214576721,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8482924103736877},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6521914005279541},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6195879578590393},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5369482040405273},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.513545036315918},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.510424792766571},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48714563250541687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48551511764526367},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4553563594818115},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.41847410798072815},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1568429172039032},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10191386938095093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482924103736877},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6521914005279541},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6195879578590393},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5369482040405273},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.513545036315918},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.510424792766571},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48714563250541687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48551511764526367},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4553563594818115},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.41847410798072815},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1568429172039032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10191386938095093},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2550143307","https://openalex.org/W2560662850","https://openalex.org/W2625366777","https://openalex.org/W2952132648","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2963916161","https://openalex.org/W2990503944","https://openalex.org/W3017081301","https://openalex.org/W3106502557","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4224291442","https://openalex.org/W4280490805","https://openalex.org/W4312614039","https://openalex.org/W4312658081","https://openalex.org/W4313156423"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W4283332100"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,73,159],"how":[4],"to":[5,27,90,137],"improve":[6],"the":[7,10,93,146],"efficiency":[8,58],"of":[9,65,95,145,154],"action":[11,48],"recognition":[12,49],"framework":[13,46,170],"by":[14,132],"optimizing":[15],"its":[16],"complicated":[17],"feature":[18],"extraction":[19],"pipelines":[20],"and":[21,59,83,165,190],"enhancing":[22],"explainability,":[23],"benefiting":[24],"future":[25],"adaptation":[26],"more":[28],"complex":[29],"visual":[30,74],"understanding":[31,75],"tasks":[32],"(e.g.":[33],"video":[34],"captioning).":[35],"To":[36],"achieve":[37],"this":[38],"task,":[39],"we":[40],"propose":[41],"a":[42,139,185],"novel":[43],"decoupled":[44,80],"two-stream":[45],"for":[47,56,114],"-":[50],"HSAR,":[51],"which":[52],"utilizes":[53],"high-semantic":[54,98,141],"features":[55,99,118],"increased":[57],"provides":[60],"well-founded":[61],"explanations":[62],"in":[63,148],"terms":[64],"spatial-temporal":[66,126],"perceptions":[67],"that":[68,168],"will":[69],"benefit":[70],"further":[71,129],"expansions":[72],"tasks.":[76],"The":[77,143],"inputs":[78],"are":[79,128],"into":[81],"spatial":[82,123],"temporal":[84,117],"streams":[85],"with":[86,175],"designated":[87],"encoders":[88],"aiming":[89],"extract":[91],"only":[92],"pinnacle":[94],"representations,":[96],"gaining":[97],"while":[100],"reducing":[101],"computation":[102,178],"costs":[103],"greatly.":[104],"A":[105],"lightweight":[106],"Temporal":[107],"Motion":[108],"Transformer":[109],"(TMT)":[110],"module":[111,150],"is":[112],"proposed":[113],"globally":[115],"modeling":[116],"through":[119],"self-attention,":[120],"omitting":[121],"redundant":[122],"features.":[124],"Decoupled":[125],"embeddings":[127],"merged":[130],"dynamically":[131],"an":[133],"attention":[134,147],"fusion":[135],"model":[136],"form":[138],"joint":[140],"representation.":[142],"visualization":[144],"each":[149],"offers":[151],"intuitive":[152],"interpretations":[153],"HSAR\u2019s":[155],"explainability.":[156],"Extensive":[157],"experiments":[158],"three":[160],"widely-used":[161],"benchmarks":[162],"(Kinetics400,":[163],"600,":[164],"Sthv2)":[166],"show":[167],"our":[169],"achieves":[171],"high":[172],"prediction":[173],"accuracy":[174,189],"significantly":[176],"reduced":[177],"(only":[179],"64.07":[180],"GFLOPs":[181],"per":[182],"clip),":[183],"offering":[184],"great":[186],"trade-off":[187],"between":[188],"computational":[191],"costs.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}