{"id":"https://openalex.org/W4385488739","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191548","title":"Variational Disentangled Attention and Regularization for Visual Dialog","display_name":"Variational Disentangled Attention and Regularization for Visual Dialog","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488739","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191548"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan","Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109627611","display_name":"Hsiu-Wei Tien","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiu-Wei Tien","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan","Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061908942"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.4913,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64779249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"09"},"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":0.9973000288009644,"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":0.9901999831199646,"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/dialog-box","display_name":"Dialog box","score":0.8889156579971313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7692567110061646},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7390806674957275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5914930105209351},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.5195013284683228},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5070211887359619},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4487074613571167},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43611961603164673},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41921812295913696},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3704375624656677},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11781671643257141},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08782497048377991},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.08288809657096863}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8889156579971313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692567110061646},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7390806674957275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914930105209351},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.5195013284683228},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5070211887359619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4487074613571167},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43611961603164673},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41921812295913696},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3704375624656677},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11781671643257141},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08782497048377991},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.08288809657096863},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/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:10.1109/ijcnn54540.2023.10191548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W115285041","https://openalex.org/W1786904711","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2133564696","https://openalex.org/W2187089797","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2803832867","https://openalex.org/W2887997457","https://openalex.org/W2888466235","https://openalex.org/W2890984855","https://openalex.org/W2952576443","https://openalex.org/W2955124656","https://openalex.org/W2962706989","https://openalex.org/W2963226019","https://openalex.org/W2963644680","https://openalex.org/W2969686176","https://openalex.org/W2970355596","https://openalex.org/W2981902456","https://openalex.org/W3034303964","https://openalex.org/W3035052826","https://openalex.org/W3036928441","https://openalex.org/W3045190332","https://openalex.org/W3091387572","https://openalex.org/W3106176216","https://openalex.org/W3112919685","https://openalex.org/W3116651605","https://openalex.org/W3130297547","https://openalex.org/W3138043709","https://openalex.org/W3147630004","https://openalex.org/W4210790685","https://openalex.org/W4220758154","https://openalex.org/W4225810142","https://openalex.org/W4243316134","https://openalex.org/W4249013746","https://openalex.org/W4285505540","https://openalex.org/W4289129346","https://openalex.org/W4289421997","https://openalex.org/W4293469690","https://openalex.org/W4294562888","https://openalex.org/W4296068966","https://openalex.org/W4297671192","https://openalex.org/W4312554247","https://openalex.org/W4313887415","https://openalex.org/W4321768969","https://openalex.org/W4391602018","https://openalex.org/W4404752311","https://openalex.org/W6638150201","https://openalex.org/W6639102338","https://openalex.org/W6640963894","https://openalex.org/W6679434410","https://openalex.org/W6684578138","https://openalex.org/W6718140377","https://openalex.org/W6729906282","https://openalex.org/W6745749135","https://openalex.org/W6746923139","https://openalex.org/W6753516544","https://openalex.org/W6754521712","https://openalex.org/W6754733129","https://openalex.org/W6757445682","https://openalex.org/W6764756247","https://openalex.org/W6779459370","https://openalex.org/W6781534913","https://openalex.org/W6784077869","https://openalex.org/W6785876359","https://openalex.org/W6790494085","https://openalex.org/W6840822198","https://openalex.org/W6874449412"],"related_works":["https://openalex.org/W2889286961","https://openalex.org/W3174836468","https://openalex.org/W1862650538","https://openalex.org/W2665731731","https://openalex.org/W3200236585","https://openalex.org/W2129798996","https://openalex.org/W4312268805","https://openalex.org/W4286980818","https://openalex.org/W3011779917","https://openalex.org/W1872130062"],"abstract_inverted_index":{"One":[0],"of":[1,48,52,72,157,165],"the":[2,14,28,34,107,116,148,163,166],"most":[3],"important":[4],"challenges":[5],"in":[6,38,57,95,151],"a":[7,17,58,79,126,136,143,152],"visual":[8,53,89,117,123,153,173],"dialog":[9],"is":[10,65,93,103,131],"to":[11,27,43,82,85,105,122,146,161],"effectively":[12],"extract":[13],"information":[15,40],"from":[16],"given":[18],"image":[19],"and":[20,46,74,111,133,169],"its":[21,44],"historical":[22],"conversation":[23],"which":[24,140],"are":[25,55,159],"related":[26],"current":[29],"question.":[30],"Many":[31],"studies":[32],"adopt":[33],"soft":[35],"attention":[36,84,129,145,168],"mechanism":[37,130],"different":[39],"sources":[41],"due":[42],"simplicity":[45],"ease":[47],"optimization.":[49],"However,":[50],"some":[51],"dialogs":[54],"observed":[56],"single":[59],"round.":[60],"This":[61,76],"implies":[62],"that":[63],"there":[64],"no":[66],"substantial":[67],"correlation":[68],"between":[69,109],"individual":[70],"rounds":[71],"questions":[73],"answers.":[75],"paper":[77],"presents":[78],"unified":[80],"approach":[81],"disentangled":[83,94],"deal":[86],"with":[87],"context-free":[88],"dialogs.":[90,174],"The":[91],"question":[92,118],"latent":[96],"representation.":[97],"In":[98],"particular,":[99],"an":[100],"informative":[101],"regularization":[102,170],"imposed":[104],"strengthen":[106],"dependence":[108],"vision":[110],"language":[112],"by":[113,135],"pretraining":[114],"on":[115],"answering":[119],"before":[120],"transferring":[121],"dialog.":[124,154],"Importantly,":[125],"novel":[127],"variational":[128],"developed":[132],"implemented":[134],"local":[137],"reparameterization":[138],"trick":[139],"carries":[141],"out":[142],"discrete":[144],"identify":[147],"relevant":[149],"conversations":[150],"A":[155],"set":[156],"experiments":[158],"evaluated":[160],"illustrate":[162],"merits":[164],"proposed":[167],"schemes":[171],"for":[172]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}