{"id":"https://openalex.org/W4415707586","doi":"https://doi.org/10.1109/tpami.2025.3627224","title":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","display_name":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","publication_year":2025,"publication_date":"2025-10-30","ids":{"openalex":"https://openalex.org/W4415707586","doi":"https://doi.org/10.1109/tpami.2025.3627224","pmid":"https://pubmed.ncbi.nlm.nih.gov/41166614"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3627224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3627224","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/A5103041611","display_name":"Mengshi Qi","orcid":"https://orcid.org/0000-0002-6955-6635"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengshi Qi","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China","State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-6955-6635","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040389265","display_name":"Changsheng Lv","orcid":"https://orcid.org/0000-0001-8485-3905"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Lv","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China","State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710713","display_name":"Huad\u00f3ng Ma","orcid":"https://orcid.org/0000-0002-7199-5047"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huadong Ma","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China","State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-7199-5047","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76596661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"48","issue":"3","first_page":"2514","last_page":"2527"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.20739999413490295,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.20739999413490295,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.20090000331401825,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1467999964952469,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9063000082969666},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6690999865531921},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.616100013256073},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5698000192642212},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.4307999908924103},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.40529999136924744},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.3885999917984009},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33820000290870667},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.3278000056743622}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9063000082969666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7172999978065491},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6690999865531921},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5830000042915344},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5698000192642212},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.3885999917984009},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3627224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3627224","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:41166614","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41166614","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":[],"awards":[{"id":"https://openalex.org/G4090645656","display_name":null,"funder_award_id":"62202063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G693838417","display_name":null,"funder_award_id":"L243027","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G7829524489","display_name":null,"funder_award_id":"U24B20176","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8349737903","display_name":null,"funder_award_id":"62572072","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/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2079735306","https://openalex.org/W2163922914","https://openalex.org/W2176287621","https://openalex.org/W2194775991","https://openalex.org/W2223745868","https://openalex.org/W2560730294","https://openalex.org/W2737047298","https://openalex.org/W2771558241","https://openalex.org/W2963115613","https://openalex.org/W2963530300","https://openalex.org/W2963902384","https://openalex.org/W2971974407","https://openalex.org/W2998617917","https://openalex.org/W3014195143","https://openalex.org/W3034603995","https://openalex.org/W3035017890","https://openalex.org/W3035651653","https://openalex.org/W3085812513","https://openalex.org/W3090449556","https://openalex.org/W3096831136","https://openalex.org/W3108230874","https://openalex.org/W3128401049","https://openalex.org/W3176232375","https://openalex.org/W3176404283","https://openalex.org/W3176445421","https://openalex.org/W3195399086","https://openalex.org/W3206218097","https://openalex.org/W4200436929","https://openalex.org/W4214681287","https://openalex.org/W4221155360","https://openalex.org/W4224121216","https://openalex.org/W4285004868","https://openalex.org/W4312380001","https://openalex.org/W4312639100","https://openalex.org/W4312761939","https://openalex.org/W4312780067","https://openalex.org/W4312864639","https://openalex.org/W4379929708","https://openalex.org/W4380303580","https://openalex.org/W4385682256","https://openalex.org/W4386071994","https://openalex.org/W4386116948","https://openalex.org/W4388189274","https://openalex.org/W4390872352","https://openalex.org/W4394627367","https://openalex.org/W4394744359","https://openalex.org/W4413146582"],"related_works":[],"abstract_inverted_index":{"In":[0,195],"this":[1],"paper,":[2],"we":[3,129,159,197],"propose":[4],"a":[5,114,124,131,161,183],"new":[6],"Robust":[7],"Disentangled":[8],"Counterfactual":[9],"Learning":[10],"(RDCL)":[11],"approach":[12],"for":[13],"physical":[14,24,83,143],"audiovisual":[15],"commonsense":[16,25],"reasoning.":[17],"The":[18],"task":[19],"aims":[20],"to":[21,39,59,118,135,166],"infer":[22],"objects'":[23],"based":[26],"on":[27],"both":[28],"video":[29],"and":[30,69,99,176,207,212],"audio":[31],"input,":[32],"with":[33,123],"the":[34,41,48,55,70,79,104,108,120,137,154,168,173,204,214],"main":[35],"challenge":[36],"being":[37],"how":[38],"imitate":[40],"reasoning":[42,74,139,205],"ability":[43,75,140],"of":[44,50,54,63,72,81,209],"humans,":[45],"even":[46],"in":[47,66,76,103],"scenario":[49],"missing":[51,169],"modalities.":[52],"Most":[53],"current":[56],"methods":[57,211],"fail":[58],"take":[60],"full":[61],"advantage":[62],"different":[64,147],"characteristics":[65],"multi-modal":[67],"data,":[68],"lack":[71],"causal":[73],"models":[77],"impedes":[78],"progress":[80],"implicit":[82],"knowledge":[84,144],"inference.":[85],"To":[86,152],"address":[87],"these":[88],"issues,":[89],"our":[90,200],"proposed":[91,180,201],"RDCL":[92],"method":[93,165,181,202],"decouples":[94],"videos":[95],"into":[96,190],"static":[97],"(time-invariant)":[98],"dynamic":[100],"(time-varying)":[101],"factors":[102],"latent":[105],"space":[106],"using":[107],"disentangled":[109],"sequential":[110],"encoder,":[111],"which":[112],"adopts":[113],"variational":[115],"autoencoder":[116],"(VAE)":[117],"maximize":[119],"mutual":[121],"information":[122],"contrastive":[125],"loss":[126],"function.":[127],"Furthermore,":[128],"introduce":[130,160],"counterfactual":[132,150],"learning":[133,164],"module":[134,185],"augment":[136],"model's":[138],"by":[141,171],"modeling":[142],"relationships":[145],"among":[146],"objects":[148],"under":[149],"intervention.":[151],"alleviate":[153],"incomplete":[155],"modality":[156],"data":[157,170],"issue,":[158],"robust":[162],"multimodal":[163],"recover":[167],"decomposing":[172],"shared":[174],"features":[175],"model-specific":[177],"features.":[178],"Our":[179],"is":[182],"plug-and-play":[184],"that":[186,199],"can":[187],"be":[188],"incorporated":[189],"any":[191],"baseline,":[192],"including":[193],"VLMs.":[194],"experiments,":[196],"show":[198],"improves":[203],"accuracy":[206],"robustness":[208],"baseline":[210],"achieves":[213],"state-of-the-art":[215],"performance.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-07T06:11:34.122080","created_date":"2025-10-30T00:00:00"}