{"id":"https://openalex.org/W4403791396","doi":"https://doi.org/10.1145/3664647.3688975","title":"Advancing Micro-Action Recognition with Multi-Auxiliary Heads and Hybrid Loss Optimization","display_name":"Advancing Micro-Action Recognition with Multi-Auxiliary Heads and Hybrid Loss Optimization","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791396","doi":"https://doi.org/10.1145/3664647.3688975"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3688975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101431986","display_name":"Qiankun Li","orcid":"https://orcid.org/0000-0001-5121-1682"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":true,"raw_author_name":"Qiankun Li","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008207535","display_name":"Xiaolong Huang","orcid":"https://orcid.org/0009-0005-5502-2535"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiaolong Huang","raw_affiliation_strings":["Mila - Quebec AI Institute & Concordia University, Canada, Canada"],"affiliations":[{"raw_affiliation_string":"Mila - Quebec AI Institute & Concordia University, Canada, Canada","institution_ids":["https://openalex.org/I4210164802","https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176737","display_name":"Huabao Chen","orcid":"https://orcid.org/0009-0003-4300-3017"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Huabao Chen","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113308298","display_name":"Feng He","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng He","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021521914","display_name":"Qiupu Chen","orcid":"https://orcid.org/0000-0003-1036-6762"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Qiupu Chen","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103123751","display_name":"Zengfu Wang","orcid":"https://orcid.org/0000-0003-1859-900X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Zengfu Wang","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101431986"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":1.4957,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84152845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11313","last_page":"11319"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.996399998664856,"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":0.9911999702453613,"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":0.643711268901825},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5131319165229797},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.46234384179115295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31818944215774536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.643711268901825},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5131319165229797},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.46234384179115295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31818944215774536},{"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/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:10.1145/3664647.3688975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":33,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1755205674","https://openalex.org/W1983364832","https://openalex.org/W2126579184","https://openalex.org/W2752782242","https://openalex.org/W2883429621","https://openalex.org/W2963155035","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2971680695","https://openalex.org/W2990503944","https://openalex.org/W3126721948","https://openalex.org/W3129409502","https://openalex.org/W3145450063","https://openalex.org/W3177709384","https://openalex.org/W3196414989","https://openalex.org/W3216270236","https://openalex.org/W4280490805","https://openalex.org/W4304091718","https://openalex.org/W4304091966","https://openalex.org/W4304092138","https://openalex.org/W4312560592","https://openalex.org/W4313126982","https://openalex.org/W4386057769","https://openalex.org/W4386071576","https://openalex.org/W4387815075","https://openalex.org/W4388191389","https://openalex.org/W4389776602","https://openalex.org/W4390872366","https://openalex.org/W4391216149","https://openalex.org/W4396910024","https://openalex.org/W4404724811"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Video":[0],"action":[1,23,52],"recognition":[2,24,39,53],"has":[3],"been":[4],"a":[5,132],"hot":[6],"research":[7],"direction":[8],"in":[9,141,147],"computer":[10],"vision,":[11],"with":[12,149],"most":[13],"existing":[14],"technologies":[15],"focusing":[16],"on":[17,49,135],"coarse-grained":[18],"macro-action":[19],"recognition.":[20,68],"However,":[21],"fine-grained":[22,91],"remains":[25],"challenging.":[26],"Micro-actions,":[27],"characterized":[28],"by":[29],"high":[30],"fine-grained,":[31],"low-intensity,":[32],"and":[33,40,61,73,84,92,100,109,121],"brief,":[34],"are":[35],"crucial":[36],"for":[37,89],"emotion":[38],"psychological":[41],"assessment":[42],"applications.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"build":[48],"popular":[50],"video":[51],"frameworks":[54],"as":[55],"foundation":[56],"models,":[57],"introducing":[58],"multi-auxiliary":[59],"heads":[60,77],"hybrid":[62],"loss":[63,103],"optimization":[64],"to":[65,80],"advance":[66],"micro-action":[67],"Specifically,":[69],"the":[70,82,113,118,136,142],"Frame-Level":[71],"pred":[72],"Coarse-Grained":[74],"Body-Action":[75],"auxiliary":[76],"work":[78],"collaboratively":[79],"enhance":[81],"model":[83],"Fine-Grained":[85],"Micro-Action":[86,143],"primary":[87],"head":[88],"perceiving":[90],"capturing":[93],"keyframes.":[94],"Incorporating":[95],"F1":[96],"loss,":[97,99],"ArcFace":[98],"weighted":[101],"multi-task":[102],"improves":[104],"training":[105],"stability,":[106],"convergence":[107],"speed,":[108],"performance.":[110],"Additionally,":[111],"integrating":[112],"optical":[114],"flow":[115],"modality":[116],"enriches":[117],"model's":[119],"diversity,":[120],"ensemble":[122],"learning":[123],"across":[124],"all":[125],"foundational":[126],"models.":[127],"Finally,":[128],"our":[129],"method":[130],"achieves":[131],"75.37%":[133],"F1-mean":[134],"MA-52":[137],"dataset,":[138],"ranking":[139],"1st":[140],"Analysis":[144],"Grand":[145],"Challenge":[146],"conjunction":[148],"ACM":[150],"MM'24.":[151],"The":[152],"code":[153],"is":[154],"available":[155],"at":[156],"https://github.com/qklee-lz/ACMMM2024-MAC.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}