{"id":"https://openalex.org/W4393853176","doi":"https://doi.org/10.1109/tcsvt.2024.3384392","title":"Appearance-Agnostic Representation Learning for Compositional Action Recognition","display_name":"Appearance-Agnostic Representation Learning for Compositional Action Recognition","publication_year":2024,"publication_date":"2024-04-03","ids":{"openalex":"https://openalex.org/W4393853176","doi":"https://doi.org/10.1109/tcsvt.2024.3384392"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3384392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3384392","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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":"https://openalex.org/A5029702480","display_name":"Peng Huang","orcid":"https://orcid.org/0009-0003-4102-6506"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-4102-6506","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040437528","display_name":"Xiangbo Shu","orcid":"https://orcid.org/0000-0003-4902-4663"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangbo Shu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4902-4663","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716371","display_name":"Rui Yan","orcid":"https://orcid.org/0000-0002-0694-9458"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yan","raw_affiliation_strings":["Department of Computer Science and Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0694-9458","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101280341","display_name":"Zhewei Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhewei Tu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035112538","display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9008-222X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":2.4525,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89926479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"35","issue":"4","first_page":"3039","last_page":"3053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8287000060081482,"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/T11448","display_name":"Face recognition and analysis","score":0.8287000060081482,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.7314000129699707,"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/T10057","display_name":"Face and Expression Recognition","score":0.7289000153541565,"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/representation","display_name":"Representation (politics)","score":0.6370078325271606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5649781227111816},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5463864803314209},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5294800996780396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5143548250198364},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44973224401474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3517441153526306},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3310505151748657}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6370078325271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5649781227111816},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5463864803314209},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5294800996780396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5143548250198364},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44973224401474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3517441153526306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3310505151748657},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3384392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3384392","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2043501656","display_name":null,"funder_award_id":"2023TQ0151","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G2268872017","display_name":null,"funder_award_id":"2023M731596","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G2632210744","display_name":null,"funder_award_id":"14913211","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5512729199","display_name":null,"funder_award_id":"62222207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5950360714","display_name":null,"funder_award_id":"BK20211520","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7040971259","display_name":null,"funder_award_id":"14380109","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W1944615693","https://openalex.org/W2020163092","https://openalex.org/W2068611653","https://openalex.org/W2103140817","https://openalex.org/W2105101328","https://openalex.org/W2126579184","https://openalex.org/W2194775991","https://openalex.org/W2507009361","https://openalex.org/W2625366777","https://openalex.org/W2716916105","https://openalex.org/W2736334449","https://openalex.org/W2736809457","https://openalex.org/W2739179646","https://openalex.org/W2943070176","https://openalex.org/W2962934715","https://openalex.org/W2963091558","https://openalex.org/W2963119563","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2998360624","https://openalex.org/W3021013305","https://openalex.org/W3034257141","https://openalex.org/W3107646798","https://openalex.org/W3110854813","https://openalex.org/W3126721948","https://openalex.org/W3134134173","https://openalex.org/W3138516171","https://openalex.org/W3152380984","https://openalex.org/W3205691536","https://openalex.org/W3206930349","https://openalex.org/W4205432963","https://openalex.org/W4214614183","https://openalex.org/W4280538209","https://openalex.org/W4281752744","https://openalex.org/W4284965682","https://openalex.org/W4285588963","https://openalex.org/W4297697565","https://openalex.org/W4304092632","https://openalex.org/W4309157236","https://openalex.org/W4312537474","https://openalex.org/W4312560592","https://openalex.org/W4312769131","https://openalex.org/W4385245566","https://openalex.org/W4386066282","https://openalex.org/W4386072300","https://openalex.org/W4387968684","https://openalex.org/W4389888036","https://openalex.org/W4390874575","https://openalex.org/W6605536666","https://openalex.org/W6682864246","https://openalex.org/W6784163774","https://openalex.org/W6786833581","https://openalex.org/W6791353385","https://openalex.org/W6796494063","https://openalex.org/W6797263693","https://openalex.org/W6803571913","https://openalex.org/W6810265253","https://openalex.org/W6811013733","https://openalex.org/W6840478680","https://openalex.org/W6846726380","https://openalex.org/W6851932778","https://openalex.org/W6851970734","https://openalex.org/W6852040150","https://openalex.org/W6852206773","https://openalex.org/W6852328995","https://openalex.org/W6852363314","https://openalex.org/W6852542133","https://openalex.org/W6852576551","https://openalex.org/W6852629184","https://openalex.org/W6852699137","https://openalex.org/W6852850613","https://openalex.org/W6853242345","https://openalex.org/W6858602045","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W4324271173","https://openalex.org/W1967645776","https://openalex.org/W2352227742","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"The":[0,240],"discussion":[1],"of":[2,28,110,120,125,188,221],"compositional":[3,126,232],"generalization":[4,86,219],"in":[5,89,122,203,229,246,253],"action":[6,127,180,205],"recognition,":[7],"<italic":[8,54],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[9,55,140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e</i>":[10],".,":[11],"Compositional":[12],"Action":[13],"Recognition":[14],"(CAR),":[15],"has":[16],"recently":[17],"received":[18],"increasing":[19],"attention.":[20],"CAR":[21,48],"challenges":[22],"models":[23],"to":[24,42,63,98,170],"recognize":[25],"unseen":[26],"combinations":[27],"actions":[29],"and":[30,60,81,154,166,179,200,206],"objects,":[31],"with":[32,248],"the":[33,37,106,117,123,173,186,195,218,249],"primary":[34],"challenge":[35],"being":[36],"distribution":[38],"shift":[39],"from":[40],"training":[41],"testing.":[43],"Most":[44],"previous":[45],"approaches":[46],"for":[47,144,212],"incorporate":[49],"supplementary":[50],"object":[51,79],"annotations":[52],"(":[53],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e.g</i>":[56],".":[57],"bounding":[58],"boxes":[59],"objects":[61,201],"categories)":[62],"learn":[64],"an":[65,100],"instance-centric":[66],"dynamic":[67,213],"representation.":[68],"However,":[69],"these":[70],"methods":[71,252],"inevitably":[72],"introduce":[73],"stronger":[74],"visual":[75,177],"inductive":[76],"bias,":[77,83],"including":[78],"appearance":[80],"background":[82],"that":[84],"impact":[85,187],"performance,":[87],"particularly":[88],"out-of-distribution":[90],"scenarios.":[91],"To":[92],"this":[93,95,222],"end,":[94],"work":[96],"attempts":[97],"construct":[99],"appearance-agnostic":[101,209],"de-biased":[102],"representation":[103],"by":[104],"leveraging":[105],"powerful":[107],"segmentation":[108],"capability":[109],"Segment":[111],"Anything":[112],"Model":[113],"(SAM),":[114],"which":[115,146],"is":[116],"first":[118],"exploration":[119],"SAM":[121],"field":[124],"recognition.":[128],"Specifically,":[129],"we":[130,161,193],"propose":[131],"a":[132,163],"novel":[133],"SAM-driven":[134],"Appearance-Agnostic":[135],"Representation":[136],"Learning":[137],"(A":[138],"<sup":[139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[141],"RL)":[142],"framework":[143],"CAR,":[145],"contains":[147],"two":[148],"effective":[149],"sub-modules:":[150],"Fore-Back":[151],"Mask":[152],"(FBM)":[153],"Dynamic":[155],"Relation":[156],"Modeling":[157],"(DRM).":[158],"In":[159,191],"FBM,":[160],"design":[162],"fine-grained":[164],"instance-invisible":[165],"background-removed":[167],"masking":[168],"strategy":[169],"effectively":[171],"weaken":[172],"strong":[174],"connection":[175],"between":[176,198],"cues":[178],"labels,":[181],"as":[182,184],"well":[183],"minimize":[185],"irrelevant":[189],"factors.":[190],"DRM,":[192],"explore":[194],"potential":[196],"association":[197],"subjects":[199],"involved":[202],"one":[204],"then":[207],"build":[208],"relational":[210],"descriptors":[211],"modeling.":[214],"Extensive":[215],"experiments":[216],"demonstrate":[217],"ability":[220],"work.":[223],"Notably,":[224],"FBM":[225],"achieves":[226],"significant":[227],"improvements":[228],"all":[230],"three":[231],"settings":[233],"without":[234],"adding":[235],"any":[236],"additional":[237],"model":[238],"parameters.":[239],"proposed":[241],"also":[242],"gains":[243],"state-of-the-art":[244],"performance":[245],"comparison":[247],"most":[250],"recent":[251],"CAR.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}