{"id":"https://openalex.org/W3200205971","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533312","title":"Attribute Centered Multimodal Response Generation in a Dialogue System","display_name":"Attribute Centered Multimodal Response Generation in a Dialogue System","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200205971","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533312","mag":"3200205971"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5089625578","display_name":"Mauajama Firdaus","orcid":"https://orcid.org/0000-0001-7485-5974"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mauajama Firdaus","raw_affiliation_strings":["Indian Institute of Technology, Patna, Bihar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Patna, Bihar, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086094867","display_name":"Arunav Pratap Shandilya","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arunav Pratap Shandilya","raw_affiliation_strings":["Indian Institute of Technology, Patna, Bihar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Patna, Bihar, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063673819","display_name":"Sthita Pragyan Pujari","orcid":"https://orcid.org/0009-0009-0191-3059"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sthita Pragyan Pujari","raw_affiliation_strings":["Indian Institute of Technology, Patna, Bihar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Patna, Bihar, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085370631","display_name":"Asif Ekbal","orcid":"https://orcid.org/0000-0003-3612-8834"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Asif Ekbal","raw_affiliation_strings":["Indian Institute of Technology, Patna, Bihar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Patna, Bihar, India","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.0955,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3619291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"8"},"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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9962999820709229,"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":0.8448168039321899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5460436940193176},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5144055485725403},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5084125399589539},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5067065358161926},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4649457037448883},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4634224474430084},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.445695161819458},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43942689895629883},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.434036523103714},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.41960012912750244},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4127446413040161},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39056843519210815},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10609081387519836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8448168039321899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5460436940193176},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5144055485725403},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5084125399589539},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5067065358161926},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4649457037448883},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4634224474430084},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.445695161819458},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43942689895629883},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.434036523103714},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.41960012912750244},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4127446413040161},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39056843519210815},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10609081387519836},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G6347276998","display_name":null,"funder_award_id":"IMP/2018/002072","funder_id":"https://openalex.org/F4320334771","funder_display_name":"Science and Engineering Research Board"}],"funders":[{"id":"https://openalex.org/F4320334771","display_name":"Science and Engineering Research Board","ror":"https://ror.org/03ffdsr55"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1975879668","https://openalex.org/W2062989416","https://openalex.org/W2099471712","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2729046720","https://openalex.org/W2768661419","https://openalex.org/W2896632102","https://openalex.org/W2897182555","https://openalex.org/W2951450739","https://openalex.org/W2956125353","https://openalex.org/W2962764403","https://openalex.org/W2962785568","https://openalex.org/W2962835968","https://openalex.org/W2963403868","https://openalex.org/W2963626105","https://openalex.org/W2963748384","https://openalex.org/W2964011461","https://openalex.org/W2964318046","https://openalex.org/W2984809863","https://openalex.org/W3017328214","https://openalex.org/W3083690138","https://openalex.org/W4249013746","https://openalex.org/W4251742697","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6740021858","https://openalex.org/W6767907118","https://openalex.org/W6779669310","https://openalex.org/W6833387226","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W150615748","https://openalex.org/W3185756568","https://openalex.org/W4287761641","https://openalex.org/W3034009428","https://openalex.org/W2091812581","https://openalex.org/W2160505327","https://openalex.org/W88822752","https://openalex.org/W2141383153","https://openalex.org/W2617385383","https://openalex.org/W2146319278"],"abstract_inverted_index":{"Dialogue":[0],"system":[1,97],"has":[2,17,64],"become":[3],"a":[4,71,95],"prominent":[5],"platform":[6],"for":[7,21,59,133],"human-machine":[8],"interactions.":[9],"The":[10,117,149],"ongoing":[11],"research":[12,63],"in":[13,46,70,82,94,195],"vision":[14],"and":[15,39],"language":[16],"opened":[18],"new":[19],"frontiers":[20],"building":[22],"multimodal":[23,44,72,96,138],"dialogue":[24,198],"systems":[25],"that":[26,98,158,188],"incorporate":[27],"information":[28,77],"from":[29],"the":[30,47,57,79,106,110,113,137,146,153,163,171,181,189,197,202],"various":[31],"complementary":[32],"sources":[33],"such":[34],"as":[35],"text,":[36],"images,":[37,103],"audios,":[38],"videos.":[40],"For":[41],"interactive":[42],"systems,":[43],"knowledge":[45],"form":[48],"of":[49,101,112],"different":[50],"modalities":[51],"need":[52],"to":[53,56,78,142,155,162,176,201],"be":[54],"presented":[55],"user":[58],"effective":[60],"communication.":[61],"Recent":[62],"mainly":[65],"focused":[66],"upon":[67,105],"textual":[68,107,124],"generation":[69,92],"setting,":[73],"thereby":[74],"providing":[75],"incomplete":[76],"users.":[80,203],"Hence,":[81],"our":[83,168],"current":[84],"work,":[85],"we":[86],"present":[87],"an":[88],"attribute":[89,183,191],"centered":[90,192],"image":[91],"framework":[93],"is":[99,140],"capable":[100],"generating":[102],"conditioned":[104],"features":[108,119,125],"with":[109,121],"help":[111,194],"taxonomy-attribute":[114],"combined":[115],"tree.":[116],"visual":[118],"interact":[120],"multi-head":[122],"attended":[123],"through":[126],"attention":[127],"based":[128],"factorized":[129],"bilinear":[130],"pooling":[131],"approach":[132],"fine-grained":[134],"representation.":[135],"Further,":[136],"representation":[139],"extended":[141],"generate":[143,156],"images":[144,157,179,193],"using":[145,180],"adversarial":[147],"network.":[148],"loss":[150],"functions":[151],"encourage":[152],"network":[154],"are":[159],"very":[160],"similar":[161],"natural":[164],"image.":[165],"We":[166],"perform":[167],"experiments":[169],"on":[170],"Multimodal":[172],"Dialog":[173],"Dataset":[174],"(MMD)":[175],"create":[177],"contextualized":[178],"fashion":[182],"features.":[184],"Empirical":[185],"studies":[186],"show":[187],"generated":[190],"making":[196],"more":[199],"engaging":[200]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
