{"id":"https://openalex.org/W4415536494","doi":"https://doi.org/10.1145/3746027.3755085","title":"DMC <sup>3</sup> : Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering","display_name":"DMC <sup>3</sup> : Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536494","doi":"https://doi.org/10.1145/3746027.3755085"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755085","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.20285","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038063326","display_name":"Jiayi Zou","orcid":"https://orcid.org/0009-0003-8821-6358"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Zou","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-8821-6358","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024701469","display_name":"Chaofan Chen","orcid":"https://orcid.org/0000-0001-7970-7698"},"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"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaofan Chen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7970-7698","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3438","last_page":"3447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9955000281333923,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9941999912261963,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9732999801635742},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.605400025844574},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5026999711990356},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4602999985218048},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.3772999942302704}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9732999801635742},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.605400025844574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.554099977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493000149726868},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48510000109672546},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.398499995470047},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.3772999942302704},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31380000710487366},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755085","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.20285","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.20285","pdf_url":"https://arxiv.org/pdf/2510.20285","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.20285","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.20285","pdf_url":"https://arxiv.org/pdf/2510.20285","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2998166190","https://openalex.org/W3034891989","https://openalex.org/W3168640669","https://openalex.org/W3196930868","https://openalex.org/W3204924011","https://openalex.org/W3205786327","https://openalex.org/W3207758636","https://openalex.org/W4200631219","https://openalex.org/W4213019189","https://openalex.org/W4327808327","https://openalex.org/W4379929708","https://openalex.org/W4385571516","https://openalex.org/W4386076314","https://openalex.org/W4387676019","https://openalex.org/W4388430346","https://openalex.org/W4390873954","https://openalex.org/W4402753952","https://openalex.org/W4403780703","https://openalex.org/W4405754155","https://openalex.org/W4408354204"],"related_works":[],"abstract_inverted_index":{"Egocentric":[0],"Video":[1],"Question":[2],"Answering":[3],"(Egocentric":[4],"VideoQA)":[5],"plays":[6],"an":[7,71],"important":[8],"role":[9],"in":[10,129],"egocentric":[11,72],"video":[12],"understanding,":[13],"which":[14,69],"refers":[15],"to":[16,95,140],"answering":[17],"questions":[18],"based":[19],"on":[20,171,181],"first-person":[21,44],"videos.":[22],"Although":[23],"existing":[24],"methods":[25],"have":[26],"made":[27],"progress":[28],"through":[29,106],"the":[30,38,43,122,126,130,142,145,150,156,159,172,185],"paradigm":[31],"of":[32,177],"pre-training":[33],"and":[34,51,80,98,103,110,149,169,174,179],"fine-tuning,":[35],"they":[36],"ignore":[37],"unique":[39],"challenges":[40],"posed":[41],"by":[42],"perspective,":[45],"such":[46],"as":[47],"understanding":[48],"multiple":[49],"events":[50],"recognizing":[52],"hand-object":[53],"interactions.":[54],"To":[55],"deal":[56],"with":[57,121],"these":[58,118],"challenges,":[59],"we":[60,136],"propose":[61],"a":[62,75,81,90],"Dual-Modal":[63],"Counterfactual":[64],"Contrastive":[65],"Construction":[66],"(DMC3)":[67],"framework,":[68],"contains":[70],"videoqa":[73],"baseline,":[74],"counterfactual":[76,82,91,131],"sample":[77,92,147,152],"construction":[78,93],"module":[79,94],"sample-involved":[83,132],"contrastive":[84,133,138],"optimization.":[85],"Specifically,":[86],"We":[87,116],"first":[88],"develop":[89],"generate":[96],"positive":[97,151],"negative":[99,160],"samples":[100,119,124],"for":[101],"textual":[102],"visual":[104],"modalities":[105],"event":[107],"description":[108],"paraphrasing":[109],"core":[111],"interaction":[112],"mining,":[113],"respectively.":[114],"Then,":[115],"feed":[117],"together":[120],"original":[123,146],"into":[125],"baseline.":[127],"Finally,":[128],"optimization":[134],"module,":[135],"apply":[137],"loss":[139],"minimize":[141],"distance":[143,157],"between":[144],"features":[148],"features,":[153],"while":[154],"maximizing":[155],"from":[158],"samples.":[161],"Experiments":[162],"show":[163],"that":[164],"our":[165],"method":[166],"achieve":[167],"52.51%":[168],"46.04%":[170],"normal":[173],"indirect":[175],"splits":[176],"EgoTaskQA,":[178],"13.2%":[180],"QAEGO4D,":[182],"both":[183],"reaching":[184],"state-of-the-art":[186],"performance.":[187]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-25T00:00:00"}