{"id":"https://openalex.org/W4360993849","doi":"https://doi.org/10.1109/tpami.2023.3261659","title":"Progressive Instance-Aware Feature Learning for Compositional Action Recognition","display_name":"Progressive Instance-Aware Feature Learning for Compositional Action Recognition","publication_year":2023,"publication_date":"2023-03-27","ids":{"openalex":"https://openalex.org/W4360993849","doi":"https://doi.org/10.1109/tpami.2023.3261659","pmid":"https://pubmed.ncbi.nlm.nih.gov/37030795"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3261659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3261659","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/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":true,"raw_author_name":"Rui Yan","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075290241","display_name":"Lingxi Xie","orcid":"https://orcid.org/0000-0003-4831-9451"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxi Xie","raw_affiliation_strings":["Huawei Inc., Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Huawei Inc., Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"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, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618147","display_name":"Liyan Zhang","orcid":"https://orcid.org/0000-0002-1549-3317"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyan Zhang","raw_affiliation_strings":["College of Computer Science and Technology, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]},{"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, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100716371"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":6.7402,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.97825348,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"45","issue":"8","first_page":"10317","last_page":"10330"},"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":0.9994000196456909,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7593921422958374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7081449627876282},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.635604202747345},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6191701889038086},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6005992889404297},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5906509757041931},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.544448971748352},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5236470699310303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45227745175361633},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4424024224281311},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09236270189285278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7593921422958374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7081449627876282},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.635604202747345},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6191701889038086},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6005992889404297},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5906509757041931},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.544448971748352},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5236470699310303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45227745175361633},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4424024224281311},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09236270189285278},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014796","descriptor_name":"Visual Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3261659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3261659","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37030795","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37030795","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"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/G5558408212","display_name":null,"funder_award_id":"62072245","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/G6329772822","display_name":null,"funder_award_id":"61925204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7255707686","display_name":null,"funder_award_id":"62172212","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1536680647","https://openalex.org/W1927052826","https://openalex.org/W1947481528","https://openalex.org/W1983364832","https://openalex.org/W2016589492","https://openalex.org/W2031342017","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2116435618","https://openalex.org/W2118688707","https://openalex.org/W2126579184","https://openalex.org/W2156303437","https://openalex.org/W2212534599","https://openalex.org/W2277195237","https://openalex.org/W2337252826","https://openalex.org/W2507009361","https://openalex.org/W2604763608","https://openalex.org/W2613576910","https://openalex.org/W2619034550","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2770804203","https://openalex.org/W2806331055","https://openalex.org/W2808707363","https://openalex.org/W2883275382","https://openalex.org/W2888810615","https://openalex.org/W2911273949","https://openalex.org/W2951702519","https://openalex.org/W2963091558","https://openalex.org/W2963524571","https://openalex.org/W2963563276","https://openalex.org/W2963699792","https://openalex.org/W2963907629","https://openalex.org/W2964080601","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2996132992","https://openalex.org/W2997668427","https://openalex.org/W3010874390","https://openalex.org/W3034257141","https://openalex.org/W3034309634","https://openalex.org/W3034572008","https://openalex.org/W3034679267","https://openalex.org/W3035180180","https://openalex.org/W3035303837","https://openalex.org/W3096719817","https://openalex.org/W3107580728","https://openalex.org/W3115964123","https://openalex.org/W3120335880","https://openalex.org/W3131075173","https://openalex.org/W3152380984","https://openalex.org/W3177934633","https://openalex.org/W3205691536","https://openalex.org/W4251009746","https://openalex.org/W4288093753","https://openalex.org/W4294306266","https://openalex.org/W4295312788","https://openalex.org/W4297772798","https://openalex.org/W4297808394","https://openalex.org/W4301259831","https://openalex.org/W4385245566","https://openalex.org/W6600983433","https://openalex.org/W6634221342","https://openalex.org/W6677326919","https://openalex.org/W6677477928","https://openalex.org/W6682864246","https://openalex.org/W6691096134","https://openalex.org/W6736057607","https://openalex.org/W6738467200","https://openalex.org/W6738893770","https://openalex.org/W6739901393","https://openalex.org/W6748655984","https://openalex.org/W6751936687","https://openalex.org/W6752365561","https://openalex.org/W6766978945","https://openalex.org/W6769024994","https://openalex.org/W6771829773","https://openalex.org/W6781776314","https://openalex.org/W6844194202","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147","https://openalex.org/W2358868262"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,6,8,70,98,101,134],"enable":[3],"the":[4,21,39,51,136],"model":[5,137],"generalize":[7],"unseen":[9],"\"action-objects\"":[10],"(compositional":[11],"action),":[12],"previous":[13],"methods":[14,37],"encode":[15],"multiple":[16],"pieces":[17],"of":[18,26,43,53,78,175,182],"information":[19,45],"(i.e.,":[20,46],"appearance,":[22],"position,":[23],"and":[24,30,48,74,126,160,179],"identity":[25],"visual":[27,54],"instances)":[28],"independently":[29],"concatenate":[31],"them":[32],"for":[33,83],"classification.":[34],"However,":[35],"these":[36],"ignore":[38],"potential":[40],"supervisory":[41],"role":[42],"instance":[44],"position":[47,130,181],"identity)":[49],"in":[50,108,123,145,173],"process":[52],"perception.":[55],"To":[56],"this":[57,88],"end,":[58],"we":[59],"present":[60],"a":[61],"novel":[62],"framework,":[63],"namely":[64],"Progressive":[65],"Instance-aware":[66],"Feature":[67,106,121],"Learning":[68],"(PIFL),":[69],"progressively":[71],"extract,":[72],"reason,":[73],"predict":[75],"dynamic":[76],"cues":[77],"moving":[79],"instances":[80,94],"from":[81,92,131],"videos":[82],"compositional":[84,154],"action":[85,155,170],"recognition.":[86],"Specifically,":[87],"framework":[89],"extracts":[90],"features":[91,116],"foreground":[93],"that":[95],"are":[96],"likely":[97],"be":[99],"relevant":[100],"human":[102],"actions":[103],"(Position-aware":[104],"Appearance":[105],"Extraction":[107],"Section":[109,124,146],"III-B1),":[110],"performs":[111],"identity-aware":[112],"reasoning":[113],"among":[114],"instance-centric":[115],"with":[117],"semantic-specific":[118],"interactions":[119],"(Identity-aware":[120],"Interaction":[122],"III-B2),":[125],"finally":[127],"predicts":[128],"instances'":[129],"observed":[132],"states":[133],"force":[135],"into":[138],"perceiving":[139],"their":[140],"movement":[141],"(Semantic-aware":[142],"Position":[143],"Prediction":[144],"III-B3).":[147],"We":[148],"evaluate":[149],"our":[150],"approach":[151,163],"on":[152],"two":[153],"recognition":[156,171],"benchmarks,":[157],"namely,":[158],"Something-Else":[159],"IKEA-Assembly.":[161],"Our":[162],"achieves":[164],"consistent":[165],"accuracy":[166],"gain":[167],"beyond":[168],"off-the-shelf":[169],"algorithms":[172],"terms":[174],"both":[176],"ground":[177],"truth":[178],"detected":[180],"instances.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}