{"id":"https://openalex.org/W7118171539","doi":"https://doi.org/10.1109/tmm.2026.3651017","title":"Efficient Human Feature Refinement for Weakly Supervised Group Activity Recognition","display_name":"Efficient Human Feature Refinement for Weakly Supervised Group Activity Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118171539","doi":"https://doi.org/10.1109/tmm.2026.3651017"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651017","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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":null,"display_name":"Yihui Zhou","orcid":"https://orcid.org/0009-0008-5295-7679"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihui Zhou","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-5295-7679","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121914582","display_name":"Hao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6853-3298","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121919482","display_name":"Zhanzhou Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanzhou Feng","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-0071-454X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055433405","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0001-9053-9314"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9053-9314","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03371112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"2226","last_page":"2237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9013000130653381,"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":0.9013000130653381,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.051899999380111694,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7947999835014343},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6758999824523926},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6385999917984009},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6054999828338623},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5264000296592712},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5202999711036682},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.4772000014781952},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47510001063346863},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43939998745918274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954000234603882},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7947999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7063000202178955},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6758999824523926},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6385999917984009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.39410001039505005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651017","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7818610668182373}],"awards":[{"id":"https://openalex.org/G2485549516","display_name":null,"funder_award_id":"2025T180410","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G2861900761","display_name":null,"funder_award_id":"2025ZD1601300","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3637388763","display_name":null,"funder_award_id":"U20B2052","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3854062921","display_name":null,"funder_award_id":"62402013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4828104523","display_name":null,"funder_award_id":"2023M730056","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G6658023004","display_name":null,"funder_award_id":"61936011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2002741386","https://openalex.org/W2010393842","https://openalex.org/W2045748173","https://openalex.org/W2053619738","https://openalex.org/W2130122588","https://openalex.org/W2132315307","https://openalex.org/W2134282114","https://openalex.org/W2161986999","https://openalex.org/W2194775991","https://openalex.org/W2259801182","https://openalex.org/W2736442062","https://openalex.org/W2765426175","https://openalex.org/W2774365946","https://openalex.org/W2895064504","https://openalex.org/W2914868535","https://openalex.org/W2922230383","https://openalex.org/W2940963663","https://openalex.org/W2963150697","https://openalex.org/W2964062686","https://openalex.org/W3035029089","https://openalex.org/W3035648302","https://openalex.org/W3095022195","https://openalex.org/W3096719817","https://openalex.org/W3108614371","https://openalex.org/W3119771537","https://openalex.org/W3204485253","https://openalex.org/W3216333260","https://openalex.org/W4210781246","https://openalex.org/W4230451144","https://openalex.org/W4312349914","https://openalex.org/W4312530435","https://openalex.org/W4312557989","https://openalex.org/W4312858532","https://openalex.org/W4312919330","https://openalex.org/W4362683543","https://openalex.org/W4381163586","https://openalex.org/W4385815582","https://openalex.org/W4386066122","https://openalex.org/W4390576774","https://openalex.org/W4396733904","https://openalex.org/W4402776102","https://openalex.org/W4403118112","https://openalex.org/W4403792480","https://openalex.org/W4404612664","https://openalex.org/W4404722534","https://openalex.org/W4407449903"],"related_works":[],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"group":[2,14,130],"activity":[3,11,131],"recognition":[4],"(WSGAR)":[5],"aims":[6],"to":[7,141],"identify":[8],"the":[9,53,67,143],"joint":[10],"of":[12,15,69,146],"a":[13,80,136],"people":[16],"without":[17],"relying":[18],"on":[19,48,166],"hand-annotated":[20],"human":[21,40,50,71],"bounding":[22,36],"boxes.":[23],"Existing":[24],"WSGAR":[25,164],"methods":[26,165],"typically":[27],"acquire":[28],"coarse":[29],"human-level":[30,87,124],"features":[31,125],"by":[32],"pooling":[33],"from":[34,52],"detected":[35],"boxes":[37],"or":[38],"applying":[39],"queries":[41],"with":[42,63,89,172],"cross":[43],"attentions.":[44],"These":[45],"approaches":[46],"focus":[47],"learning":[49,128],"relations":[51],"acquired":[54],"features.":[55],"However,":[56],"discriminative":[57,123],"person-specific":[58],"clues":[59],"might":[60],"be":[61],"confused":[62],"irrelevant":[64,117],"backgrounds,":[65],"hindering":[66],"effectiveness":[68],"downstream":[70],"relation":[72,127],"learning.":[73],"To":[74],"address":[75],"this":[76],"limitation,":[77],"we":[78],"propose":[79,135],"Human":[81,147],"Feature":[82,148],"Refinement":[83],"framework":[84],"that":[85,159],"enhances":[86],"information":[88,152],"graph":[90],"convolutional":[91],"networks":[92],"and":[93,101,108,115,129,154,169],"self-attention.":[94,109],"We":[95,133],"define":[96],"in-box":[97,113],"regions":[98],"as":[99],"tokens":[100],"learn":[102],"their":[103],"spatial":[104],"correspondence":[105],"through":[106],"GCN":[107],"By":[110],"explicitly":[111],"extracting":[112],"details":[114],"suppressing":[116],"regions,":[118],"our":[119,160],"method":[120,161],"acquires":[121],"more":[122],"for":[126],"prediction.":[132],"further":[134],"Graph-based":[137],"Token":[138],"Merging":[139],"algorithm":[140],"reduce":[142],"computation":[144,174],"cost":[145],"Refinement,":[149],"while":[150],"minimizing":[151],"loss":[153],"overfitting":[155],"risk.":[156],"Experiments":[157],"show":[158],"outperforms":[162],"previous":[163],"Volleyball,":[167],"NBA":[168],"JRDB-PAR":[170],"benchmarks,":[171],"reduced":[173],"cost.":[175]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-05T00:00:00"}