{"id":"https://openalex.org/W4387969346","doi":"https://doi.org/10.1145/3581783.3612345","title":"Video Entailment via Reaching a Structure-Aware Cross-modal Consensus","display_name":"Video Entailment via Reaching a Structure-Aware Cross-modal Consensus","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969346","doi":"https://doi.org/10.1145/3581783.3612345"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612345","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-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/A5101501874","display_name":"Xuan Yao","orcid":"https://orcid.org/0009-0000-8115-3954"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuan Yao","raw_affiliation_strings":["Institute of Automation, CAS & School of Artificial Intelligence, UCAS, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8115-3954","affiliations":[{"raw_affiliation_string":"Institute of Automation, CAS & School of Artificial Intelligence, UCAS, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014526931","display_name":"Junyu Gao","orcid":"https://orcid.org/0000-0002-8105-5497"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Gao","raw_affiliation_strings":["Institute of Automation, CAS & School of Artificial Intelligence, UCAS, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8105-5497","affiliations":[{"raw_affiliation_string":"Institute of Automation, CAS & School of Artificial Intelligence, UCAS, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737264","display_name":"Mengyuan Chen","orcid":"https://orcid.org/0009-0001-8155-0930"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyuan Chen","raw_affiliation_strings":["Institute of Automation, CAS & School of Artificial Intelligence, UCAS, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8155-0930","affiliations":[{"raw_affiliation_string":"Institute of Automation, CAS & School of Artificial Intelligence, UCAS, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":["Institute of Automation, CAS, School of Artificial Intelligence, UCAS, & Peng Cheng Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"Institute of Automation, CAS, School of Artificial Intelligence, UCAS, & Peng Cheng Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101501874"],"corresponding_institution_ids":["https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.3532,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60344288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4240","last_page":"4249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.795876145362854},{"id":"https://openalex.org/keywords/textual-entailment","display_name":"Textual entailment","score":0.6262507438659668},{"id":"https://openalex.org/keywords/statement","display_name":"Statement (logic)","score":0.5424246788024902},{"id":"https://openalex.org/keywords/logical-consequence","display_name":"Logical consequence","score":0.5334879159927368},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5334470868110657},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5250796675682068},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5190834999084473},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5157259106636047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5019626617431641},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46647483110427856},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4453175365924835},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42818695306777954},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4158180356025696},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11023378372192383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795876145362854},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.6262507438659668},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.5424246788024902},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.5334879159927368},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5334470868110657},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5250796675682068},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5190834999084473},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5157259106636047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019626617431641},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46647483110427856},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4453175365924835},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42818695306777954},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4158180356025696},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11023378372192383},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612345","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G1498893086","display_name":null,"funder_award_id":"62036012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2037785589","display_name":null,"funder_award_id":"U21B2044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2407878474","display_name":null,"funder_award_id":"62072286","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2454296646","display_name":null,"funder_award_id":"62106262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2908564948","display_name":null,"funder_award_id":"62002355","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4199693610","display_name":null,"funder_award_id":"62236008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4790433124","display_name":null,"funder_award_id":"62102415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6431871145","display_name":null,"funder_award_id":"61721004","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2108598243","https://openalex.org/W2587989515","https://openalex.org/W2606982687","https://openalex.org/W2619383789","https://openalex.org/W2753311918","https://openalex.org/W2767179670","https://openalex.org/W2904452845","https://openalex.org/W2932937602","https://openalex.org/W2954137266","https://openalex.org/W2954199749","https://openalex.org/W2962681491","https://openalex.org/W2962949233","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2964018924","https://openalex.org/W2964220823","https://openalex.org/W2980037812","https://openalex.org/W2997344006","https://openalex.org/W3002271958","https://openalex.org/W3016459781","https://openalex.org/W3034188691","https://openalex.org/W3034768625","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3102887392","https://openalex.org/W3130796238","https://openalex.org/W3168154341","https://openalex.org/W3174906557","https://openalex.org/W3181758331","https://openalex.org/W3183719433","https://openalex.org/W3203592524","https://openalex.org/W3204267711","https://openalex.org/W3207927851","https://openalex.org/W3209386620","https://openalex.org/W3217340782","https://openalex.org/W4214582399","https://openalex.org/W4224329855","https://openalex.org/W4287125738","https://openalex.org/W4295046474","https://openalex.org/W4304080724","https://openalex.org/W4309026083","https://openalex.org/W4309157236","https://openalex.org/W4312245820","https://openalex.org/W4312384316","https://openalex.org/W4312560592","https://openalex.org/W4313071966","https://openalex.org/W4386065620","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W2169644218","https://openalex.org/W12963412","https://openalex.org/W2250460949","https://openalex.org/W3158371345","https://openalex.org/W3141423438","https://openalex.org/W2071098659","https://openalex.org/W2627035043","https://openalex.org/W4385571113","https://openalex.org/W2937401546"],"abstract_inverted_index":{"This":[0],"paper":[1],"targets":[2],"at":[3,235],"the":[4,33,54,62,72,97,118,125,143,162,174,181,186,203,208,212,221],"task":[5],"of":[6,71,96,120,127,226],"video":[7,50,128,148,156],"entailment,":[8,51],"which":[9,52,81,154],"aims":[10],"to":[11,88,102,112,116,141,197,207,230],"achieve":[12],"a":[13,21,28,42,90,121,135,190],"thorough":[14,92],"comprehension":[15],"and":[16,93,149,180,201,223],"draw":[17],"inferences":[18],"on":[19,40,217],"whether":[20],"natural":[22],"language":[23,150],"statement":[24,123],"entails":[25],"or":[26],"contradicts":[27],"given":[29,122],"multi-modal":[30,46],"video.":[31],"Despite":[32],"recent":[34],"progress,":[35],"most":[36],"existing":[37],"methods":[38],"focus":[39],"designing":[41],"vision-language":[43],"encoder":[44],"for":[45],"feature":[47],"extraction":[48],"in":[49,124],"ignore":[53],"underlying":[55],"consensus":[56,84,139,144,163],"knowledge":[57],"between":[58,147],"two":[59,218],"modalities,":[60,151],"hindering":[61],"reasoning":[63,193],"performance.":[64],"As":[65],"human":[66],"beings,":[67],"we":[68,110,133],"make":[69],"sense":[70,79],"world":[73],"by":[74,167,172],"synthesizing":[75],"information":[76,164,171,176,184],"from":[77,177,185],"different":[78],"perceptions,":[80],"can":[82],"acquire":[83],"among":[85],"multiple":[86],"modalities":[87],"form":[89],"more":[91],"coherent":[94],"representation":[95],"surroundings,":[98],"as":[99,101,158],"well":[100],"perform":[103],"complicated":[104],"understanding":[105],"tasks.":[106],"In":[107],"this":[108,114,131],"paper,":[109],"attempt":[111],"recreate":[113],"ability":[115],"infer":[117],"truthfulness":[119],"context":[126],"entailment.":[129],"To":[130],"end,":[132],"propose":[134],"unified":[136],"structure-aware":[137],"cross-modal":[138],"method":[140,194],"excavate":[142],"semantics":[145],"shared":[146],"thereby":[152],"incorporating":[153],"into":[155],"entailment":[157],"statement-related":[159],"clues.":[160],"Specifically,":[161],"is":[165,195,233],"achieved":[166],"filtering":[168],"away":[169],"redundant":[170],"utilizing":[173],"global":[175],"one":[178],"modality":[179],"local":[182],"complementary":[183],"other":[187],"one.":[188],"Moreover,":[189],"consensus-guided":[191],"graph":[192],"designed":[196],"explore":[198],"inter-modality":[199],"consistency":[200],"emphasize":[202],"significant":[204],"features":[205],"related":[206],"judged":[209],"statement,":[210],"generating":[211],"inference":[213],"results.":[214],"Extensive":[215],"experiments":[216],"benchmarks":[219],"demonstrate":[220],"accurate":[222],"robust":[224],"performance":[225],"our":[227],"approach":[228],"compared":[229],"state-of-the-arts.":[231],"Code":[232],"available":[234],"https://github.com/Feliciaxyao/MM2023-SACCN.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}