{"id":"https://openalex.org/W4415537377","doi":"https://doi.org/10.1145/3746027.3762095","title":"Progressive Large-Scale Modeling via Temporal-Spatial Focus Connector for Micro-Action Recognition","display_name":"Progressive Large-Scale Modeling via Temporal-Spatial Focus Connector for Micro-Action Recognition","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537377","doi":"https://doi.org/10.1145/3746027.3762095"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762095","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiankun Li","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-5121-1682","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"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/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiupu Chen","raw_affiliation_strings":["School of Artificial Intelligence, Henan University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1036-6762","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Henan University, Zhengzhou, China","institution_ids":["https://openalex.org/I173899330"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huabao Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-4300-3017","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/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"],"raw_orcid":"https://orcid.org/0000-0001-5059-4423","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/A5048129965","display_name":"Depeng Li","orcid":"https://orcid.org/0000-0002-2281-7535"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depeng Li","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2281-7535","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081245089","display_name":"Zhigang Zeng","orcid":"https://orcid.org/0000-0003-4587-3588"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Zeng","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-4587-3588","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14222","last_page":"14228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9717000126838684,"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/discriminative-model","display_name":"Discriminative model","score":0.7383000254631042},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6320000290870667},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5616000294685364},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4903999865055084},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.47200000286102295},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4571000039577484},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.3828999996185303},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3700000047683716},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3594000041484833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657999992370605},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7383000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6442000269889832},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6320000290870667},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5616000294685364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5493000149726868},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.47200000286102295},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3594000041484833},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762095","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":16,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W2618799552","https://openalex.org/W2990152177","https://openalex.org/W3035180180","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W4214612132","https://openalex.org/W4312560592","https://openalex.org/W4386057769","https://openalex.org/W4391216149","https://openalex.org/W4403791337","https://openalex.org/W4403791375","https://openalex.org/W4403791396","https://openalex.org/W4403791421","https://openalex.org/W4406983084"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10,178,192],"video":[3,194],"action":[4],"recognition":[5,29],"have":[6],"achieved":[7],"remarkable":[8],"performance":[9],"coarse-grained":[11],"macro-action":[12],"classification":[13],"by":[14],"leveraging":[15],"large-scale":[16,66],"visual":[17],"backbones":[18,67],"and":[19,39,60,92,110,132,160,185],"transformer":[20],"architectures.":[21],"However,":[22],"extending":[23],"these":[24],"successes":[25],"to":[26,35,65,86],"fine-grained":[27,193],"micro-action":[28,54,105],"remains":[30],"a":[31,50,120,139,152],"fundamental":[32],"challenge":[33],"due":[34],"the":[36,69,74,96,113,173,179,187,190],"subtlety,":[37],"brevity,":[38],"low":[40],"motion":[41,101],"intensity":[42],"of":[43,76,115,170,189],"micro-actions.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,118,137],"propose":[49,138],"high-capacity":[51],"framework":[52],"for":[53,104],"recognition,":[55],"enhancing":[56,157],"both":[57],"representation":[58],"learning":[59],"decision":[61,142],"robustness.":[62],"We":[63],"scale":[64],"using":[68],"VideoMAEv2":[70],"Giant":[71],"model,":[72],"enabling":[73],"extraction":[75],"finer":[77],"spatial-temporal":[78],"features.":[79],"A":[80],"Temporal-Spatial":[81],"Connector":[82],"(TSC)":[83],"is":[84],"introduced":[85],"dynamically":[87],"highlight":[88],"discriminative":[89],"temporal":[90],"frames":[91],"spatial":[93],"regions,":[94],"strengthening":[95],"model's":[97],"focus":[98],"on":[99,172],"subtle":[100],"cues":[102],"critical":[103],"identification.":[106],"To":[107],"stabilize":[108],"optimization":[109],"fully":[111],"exploit":[112],"capacity":[114],"large":[116],"models,":[117],"design":[119],"four-phase":[121],"progressive":[122],"training":[123],"strategy,":[124],"encompassing":[125],"linear":[126],"probing,":[127],"full":[128],"fine-tuning,":[129],"connector-specific":[130],"optimization,":[131],"classifier":[133],"head":[134],"refinement.":[135],"Furthermore,":[136],"novel":[140],"ensemble":[141],"mechanism":[143],"that":[144],"integrates":[145],"Top-K":[146],"predictions":[147],"from":[148],"diverse":[149],"models":[150],"via":[151],"Large":[153],"Language":[154],"Model":[155],"(LLM),":[156],"prediction":[158],"consistency":[159],"robustness":[161],"through":[162],"multimodel":[163],"consensus.":[164],"Our":[165],"method":[166],"achieves":[167],"an":[168],"F1mean":[169],"76.54%":[171],"MA-52":[174],"dataset,":[175],"ranking":[176],"3rd":[177],"2025":[180],"Micro-Action":[181],"Analysis":[182],"Grand":[183],"Challenge":[184],"advancing":[186],"state":[188],"art":[191],"understanding.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}