{"id":"https://openalex.org/W4379806366","doi":"https://doi.org/10.1145/3591106.3592272","title":"Knowledge-Aware Causal Inference Network for Visual Dialog","display_name":"Knowledge-Aware Causal Inference Network for Visual Dialog","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806366","doi":"https://doi.org/10.1145/3591106.3592272"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592272","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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/A5012016681","display_name":"Zefan Zhang","orcid":"https://orcid.org/0000-0001-5627-050X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zefan Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, China"],"raw_orcid":"https://orcid.org/0000-0001-5627-050X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029104204","display_name":"Yi Ji","orcid":"https://orcid.org/0000-0001-6965-4158"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ji","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, China"],"raw_orcid":"https://orcid.org/0000-0001-6965-4158","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058448163","display_name":"Chunping Liu","orcid":"https://orcid.org/0009-0008-1495-5138"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunping Liu","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, China"],"raw_orcid":"https://orcid.org/0009-0008-1495-5138","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012016681"],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":0.8242,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74327217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"261"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9959999918937683,"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":0.9957000017166138,"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":0.8139687776565552},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7482608556747437},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7295805215835571},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.6993274092674255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6121249198913574},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.6029966473579407},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.579406201839447},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5606163144111633},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.54776930809021},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4767687916755676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4750502109527588},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4460830092430115},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.32573816180229187},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25802701711654663}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8139687776565552},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7482608556747437},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7295805215835571},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.6993274092674255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121249198913574},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.6029966473579407},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.579406201839447},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5606163144111633},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.54776930809021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4767687916755676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4750502109527588},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4460830092430115},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.32573816180229187},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25802701711654663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592272","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G875684265","display_name":null,"funder_award_id":"1972059, 61773272, 6160233","funder_id":"https://openalex.org/F4320336806","funder_display_name":"National Natural Science Foundation of China - State Grid Corporation Joint Fund for Smart Grid"}],"funders":[{"id":"https://openalex.org/F4320336806","display_name":"National Natural Science Foundation of China - State Grid Corporation Joint Fund for Smart Grid","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1552847225","https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2561529111","https://openalex.org/W2745461083","https://openalex.org/W2912814679","https://openalex.org/W2963101081","https://openalex.org/W2966158321","https://openalex.org/W2981902456","https://openalex.org/W2988023442","https://openalex.org/W3035103424","https://openalex.org/W3099143471","https://openalex.org/W3107092117","https://openalex.org/W3115747660","https://openalex.org/W3139565899","https://openalex.org/W3166513553","https://openalex.org/W3175445769","https://openalex.org/W3177934633","https://openalex.org/W3202473058","https://openalex.org/W4206715653","https://openalex.org/W4211071949","https://openalex.org/W4223451840","https://openalex.org/W4224003584","https://openalex.org/W4224920289","https://openalex.org/W4229019825","https://openalex.org/W4249013746","https://openalex.org/W4293519344","https://openalex.org/W6640773114"],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W4385488510","https://openalex.org/W2196562041","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4378501473"],"abstract_inverted_index":{"The":[0],"effective":[1],"knowledge":[2,70,88,143],"and":[3,22,34,83,100,104,119,134,154,163],"interaction":[4],"within":[5],"multi-modalities":[6],"are":[7],"key":[8],"to":[9,25,78,93,110],"Visual":[10,149],"Dialog.":[11,150],"Classic":[12],"graph-based":[13,120],"framework":[14,44,77,118,122,133],"with":[15,102,107,116],"the":[16,27,31,50,68,74,86,94,98,108,112,128,136,138,141],"direct":[17,47],"connection":[18,48],"between":[19,161],"history":[20,39],"dialog":[21],"answer":[23,29],"fails":[24],"give":[26],"right":[28],"for":[30,144],"spurious":[32],"guidance":[33],"strong":[35],"bias":[36],"induced":[37],"from":[38,97],"dialog.":[40],"Recent":[41],"causal":[42,75],"inference":[43,76],"without":[45],"this":[46,56],"improves":[49],"generalization":[51],"while":[52],"worse":[53],"accuracy.":[54],"In":[55],"work,":[57],"we":[58],"propose":[59],"a":[60,145,158],"novel":[61],"Knowledge-Aware":[62],"Causal":[63],"Inference":[64],"framework(KACI-Net)":[65],"in":[66,148],"which":[67],"commonsense":[69,87,142],"is":[71,89],"introduced":[72],"into":[73],"achieve":[79],"both":[80],"high":[81,152],"accuracy":[82,162],"generalization.":[84,164],"Specifically,":[85],"first":[90],"generated":[91],"according":[92],"entities":[95],"extracted":[96],"question":[99],"fused":[101],"language":[103],"visual":[105],"features":[106],"co-attention":[109],"get":[111],"final":[113],"answer.":[114],"Comparisons":[115],"knowledge-unaware":[117],"knowledge-aware":[121],"on":[123],"VisDial":[124],"v1.0":[125],"dataset":[126],"show":[127],"superiority":[129],"of":[130,140],"our":[131],"proposed":[132],"verify":[135],"effectiveness":[137],"usage":[139],"good":[146,159],"reasoning":[147],"Both":[151],"NDCG":[153],"MRR":[155],"metrics":[156],"indicate":[157],"trade-off":[160]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}