{"id":"https://openalex.org/W4407639645","doi":"https://doi.org/10.1109/tmm.2025.3543033","title":"Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition","display_name":"Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407639645","doi":"https://doi.org/10.1109/tmm.2025.3543033"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3543033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3543033","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":"https://openalex.org/A5017473451","display_name":"Xunsong Li","orcid":"https://orcid.org/0009-0009-5803-6691"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunsong Li","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0009-5803-6691","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102605009","display_name":"Pengzhan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Pengzhan Sun","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104285914","display_name":"Yangcen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangcen Liu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0005-1720-2199","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080093489","display_name":"Lixin Duan","orcid":"https://orcid.org/0000-0002-0723-4016"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixin Duan","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-0723-4016","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100719271","display_name":"Wen Li","orcid":"https://orcid.org/0000-0002-5559-8594"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Li","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5559-8594","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8699,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83743546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"5283","last_page":"5295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9864000082015991,"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":0.978600025177002,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.845779299736023},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5430518984794617},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.540364682674408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5320174694061279},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49737265706062317},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4522264301776886},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.448871910572052},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3871324360370636},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34928780794143677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3406539857387543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845779299736023},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5430518984794617},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.540364682674408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5320174694061279},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49737265706062317},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4522264301776886},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.448871910572052},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3871324360370636},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34928780794143677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3406539857387543},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3543033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3543033","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":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1081440678","display_name":null,"funder_award_id":"62176047","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G349670999","display_name":null,"funder_award_id":"2024NSFTD0041","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"},{"id":"https://openalex.org/G8752137738","display_name":null,"funder_award_id":"ZYGX2021YGLH208","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/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2507009361","https://openalex.org/W2565639579","https://openalex.org/W2625366777","https://openalex.org/W2806331055","https://openalex.org/W2888096830","https://openalex.org/W2898044248","https://openalex.org/W2904617485","https://openalex.org/W2913950831","https://openalex.org/W2951702519","https://openalex.org/W2962766617","https://openalex.org/W2963150697","https://openalex.org/W2963524571","https://openalex.org/W2963653352","https://openalex.org/W2964286567","https://openalex.org/W2969727121","https://openalex.org/W2976818183","https://openalex.org/W2983827899","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2999794487","https://openalex.org/W3004910693","https://openalex.org/W3034257141","https://openalex.org/W3034467781","https://openalex.org/W3034572008","https://openalex.org/W3096609285","https://openalex.org/W3120335880","https://openalex.org/W3152380984","https://openalex.org/W3164894587","https://openalex.org/W3174164794","https://openalex.org/W3199093552","https://openalex.org/W3205691536","https://openalex.org/W3206930349","https://openalex.org/W3209504420","https://openalex.org/W4214607465","https://openalex.org/W4214612132","https://openalex.org/W4226476965","https://openalex.org/W4312286390","https://openalex.org/W4312769131","https://openalex.org/W4313176000","https://openalex.org/W4322746940","https://openalex.org/W4360993849","https://openalex.org/W4367663575","https://openalex.org/W4383220251","https://openalex.org/W4386072300","https://openalex.org/W4386108484","https://openalex.org/W4393853176","https://openalex.org/W4409370047"],"related_works":["https://openalex.org/W2604548540","https://openalex.org/W1576128429","https://openalex.org/W2114275278","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W2269464716","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802"],"abstract_inverted_index":{"The":[0,164],"interactions":[1],"between":[2],"human":[3],"and":[4,29,42,124,150,178,180,230,243,256,280],"objects":[5,63,157,274],"are":[6,22,31,159],"important":[7,62,160],"for":[8,38,47,119,161,277,298],"recognizing":[9],"object-centric":[10,81,299],"actions.":[11],"Existing":[12],"methods":[13,285],"usually":[14],"adopt":[15],"a":[16,26,111,130,295],"two-stage":[17],"pipeline,":[18],"where":[19],"object":[20,45,59,122,137,201,228],"proposals":[21,138,172],"first":[23],"detected":[24],"using":[25,110],"pretrained":[27],"detector,":[28,229],"then":[30],"fed":[32],"to":[33,69,135,153,198,245],"an":[34,79,146,192,217,226],"action":[35,48,53,71,82,162,258,278,300],"recognition":[36,72,83,259],"model":[37],"extracting":[39,107],"video":[40,108,140,187,209],"features":[41,109],"learning":[43,121,276],"the":[44,52,58,155,168,182,200,208,222,232,247,267],"relations":[46],"recognition.":[49,163,301],"However,":[50],"since":[51],"prior":[54],"is":[55],"unknown":[56],"in":[57,102,216,275],"detection":[60,123],"stage,":[61],"could":[64],"be":[65,213],"easily":[66],"overlooked,":[67],"leading":[68],"inferior":[70],"performance.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,114,128,144,190,265,281],"propose":[78],"end-to-end":[80,218],"framework":[84],"that":[85,158],"simultaneously":[86,120],"performs":[87],"<underline":[88,91,94,97],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[89,92,95,98,272],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">D</u>etection":[90],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">A</u>nd":[93],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">I</u>nteraction":[96],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</u>easoning":[99],"(dubbed":[100],"DAIR)":[101],"one":[103],"stage.":[104],"Particularly,":[105],"after":[106],"base":[112],"network,":[113],"design":[115,145],"three":[116,204],"consecutive":[117],"modules":[118,205],"interaction":[125],"reasoning.":[126],"Firstly,":[127],"build":[129,191],"Patch-based":[131],"Object":[132,148,193],"Decoder":[133],"(PatchDec)":[134],"generate":[136],"from":[139],"patch":[141],"tokens.":[142],"Then,":[143],"Interactive":[147],"Refining":[149],"Aggregation":[151],"(IRA)":[152],"identify":[154],"interactive":[156],"IRA":[165],"module":[166,197],"adjusts":[167],"interactiveness":[169],"scores":[170],"of":[171,249,270],"based":[173],"on":[174,225,239,253,286],"their":[175],"relative":[176],"position":[177],"appearance,":[179],"aggregates":[181],"object-level":[183],"information":[184],"into":[185],"global":[186],"representation.":[188],"Finally,":[189],"Relation":[194],"Modeling":[195],"(ORM)":[196],"encode":[199],"relations.":[202],"These":[203],"together":[206],"with":[207],"feature":[210],"extractor":[211],"can":[212,282,293],"trained":[214],"jointly":[215],"fashion,":[219],"thus":[220],"avoiding":[221],"heavy":[223],"reliance":[224],"off-the-shelf":[227],"reducing":[231],"multi-stage":[233],"training":[234],"burden.":[235],"We":[236,289],"conduct":[237],"experiments":[238],"two":[240],"datasets,":[241],"Something-Else":[242],"Ikea-Assembly,":[244],"evaluate":[246],"performance":[248],"our":[250,291],"proposed":[251],"approach":[252],"conventional,":[254],"compositional,":[255],"few-shot":[257],"tasks.":[260],"Through":[261],"in-depth":[262],"experimental":[263],"analysis,":[264],"show":[266],"crucial":[268],"role":[269],"<italic":[271],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">interactive</i>":[273],"recognition,":[279],"outperform":[283],"state-of-the-art":[284],"both":[287],"datasets.":[288],"hope":[290],"DAIR":[292],"provide":[294],"new":[296],"perspective":[297]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}