{"id":"https://openalex.org/W4415709221","doi":"https://doi.org/10.1109/icme59968.2025.11210121","title":"Contrastive Invariant Risk Minimization for Grounded Situation Recognition","display_name":"Contrastive Invariant Risk Minimization for Grounded Situation Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709221","doi":"https://doi.org/10.1109/icme59968.2025.11210121"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5045800438","display_name":"Zhaoquan Yuan","orcid":"https://orcid.org/0000-0002-4083-5155"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoquan Yuan","raw_affiliation_strings":["Southwest Jiaotong University,School of Computing and Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Computing and Artificial Intelligence","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chengbin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengbin Zhao","raw_affiliation_strings":["Southwest Jiaotong University,School of Computing and Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Computing and Artificial Intelligence","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010492811","display_name":"Yuting Tang","orcid":"https://orcid.org/0000-0001-8443-7098"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Tang","raw_affiliation_strings":["Southwest Jiaotong University,School of Computing and Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Computing and Artificial Intelligence","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049770051","display_name":"Lishu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093645","display_name":"National Time Service Center","ror":"https://ror.org/00655qp86","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210093645"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lishu Guo","raw_affiliation_strings":["Chinese Academy of Sciences,National Time Service Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,National Time Service Center","institution_ids":["https://openalex.org/I4210093645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011680564","display_name":"Xiao Wu","orcid":"https://orcid.org/0000-0002-8322-8558"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wu","raw_affiliation_strings":["Southwest Jiaotong University,School of Computing and Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Computing and Artificial Intelligence","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046510603","display_name":"Chris Xu","orcid":"https://orcid.org/0000-0002-3493-6427"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34774829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.49790000915527344,"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":0.49790000915527344,"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/T10028","display_name":"Topic Modeling","score":0.17159999907016754,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.03180000185966492,"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/discriminative-model","display_name":"Discriminative model","score":0.730400025844574},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5188000202178955},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4952000081539154},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.44350001215934753},{"id":"https://openalex.org/keywords/continuation","display_name":"Continuation","score":0.43230000138282776},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.4068000018596649},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.3675000071525574},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3538999855518341}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.730400025844574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6061000227928162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5705999732017517},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4860999882221222},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.428600013256073},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2847000062465668},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2779835924","wikidata":"https://www.wikidata.org/wiki/Q146786","display_name":"Plural","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2017875634","https://openalex.org/W2143891888","https://openalex.org/W2423576022","https://openalex.org/W2560747010","https://openalex.org/W2604673901","https://openalex.org/W2962766617","https://openalex.org/W2963346996","https://openalex.org/W3003365594","https://openalex.org/W3034425145","https://openalex.org/W3035399403","https://openalex.org/W3096609285","https://openalex.org/W3096682293","https://openalex.org/W3204222276","https://openalex.org/W3206987730","https://openalex.org/W4200630531","https://openalex.org/W4230097545","https://openalex.org/W4292433237","https://openalex.org/W4312605942","https://openalex.org/W4312900708","https://openalex.org/W4387968372","https://openalex.org/W4411244520"],"related_works":[],"abstract_inverted_index":{"Grounded":[0],"situation":[1],"recognition":[2],"(GSR)":[3],"is":[4,97,106,130,142],"a":[5,67,87,109,153],"comprehensive":[6],"structured":[7],"scene":[8],"understanding":[9],"task":[10,69,149],"that":[11,146],"predicts":[12],"the":[13,21,29,34,37,85,100,121,125,143,148,161,166],"salient":[14],"activity":[15,22],"(verb),":[16],"entities":[17,35],"(nouns)":[18],"involved":[19],"in":[20,47,59,176],"with":[23],"their":[24,48],"roles,":[25],"as":[26,28,66,138,152],"well":[27],"corresponding":[30],"bounding-box":[31],"groundings":[32],"of":[33,150,155,168],"from":[36],"given":[38],"image.":[39],"Existing":[40],"I.I.D.-based":[41],"methods":[42,175],"for":[43,78,95,116],"GSR":[44,65,96,151],"are":[45],"limited":[46],"ability":[49],"to":[50,112,132],"recognize":[51],"novel":[52,88],"verb-noun":[53],"combinations.":[54],"To":[55,119],"address":[56],"this":[57,60,141],"problem,":[58],"paper,":[61],"we":[62,139],"novelly":[63],"consider":[64],"Non-I.I.D.":[68],"and":[70,75,80,124],"focus":[71],"on":[72,84,160],"learning":[73,129],"verb-invariant":[74],"role-specific":[76],"representations":[77,115],"verb":[79,117],"noun":[81],"predictions.":[82],"Based":[83],"causality,":[86],"Contrastive":[89],"Invariant":[90],"Risk":[91],"Minimization":[92],"(CIRM)":[93],"model":[94],"proposed.":[98],"In":[99],"proposed":[101,170],"CIRM,":[102],"invariant":[103,114],"risk":[104],"minimization":[105],"integrated":[107],"into":[108],"transformer":[110],"architecture":[111],"learn":[113,133],"prediction.":[118],"enhance":[120],"intra-verb":[122],"compactness":[123],"inter-verb":[126],"separability,":[127],"contrastive":[128],"utilized":[131],"discriminative":[134],"features.":[135],"As":[136],"far":[137],"know,":[140],"first":[144],"work":[145],"regards":[147],"problem":[154],"out-of-distribution":[156],"generalization.":[157],"Extensive":[158],"experiments":[159],"benchmark":[162],"SWiG":[163],"dataset":[164],"demonstrate":[165],"effectiveness":[167],"our":[169],"CIRM":[171],"over":[172],"other":[173],"state-of-the-art":[174],"all":[177],"evaluation":[178],"metrics.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}