{"id":"https://openalex.org/W4402979270","doi":"https://doi.org/10.1109/icme57554.2024.10687523","title":"Semantic-Visual Graph Reasoning for Visual Dialog","display_name":"Semantic-Visual Graph Reasoning for Visual Dialog","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979270","doi":"https://doi.org/10.1109/icme57554.2024.10687523"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687523","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5019338727","display_name":"Dongze Hao","orcid":"https://orcid.org/0000-0001-5504-1799"},"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":"Dongze Hao","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Science"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Science","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043193778","display_name":"Qunbo Wang","orcid":"https://orcid.org/0000-0002-5607-7854"},"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":"Qunbo Wang","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Science"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Science","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100374998","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0002-3588-2969"},"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":"Jing Liu","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Science"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Science","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019338727"],"corresponding_institution_ids":["https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16463992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9805999994277954,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9805999994277954,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9772999882698059,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9710999727249146,"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":0.7999261617660522},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7381601333618164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5076116323471069},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5066038370132446},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48929688334465027},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32064056396484375},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14758142828941345},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10944575071334839}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999261617660522},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7381601333618164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076116323471069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5066038370132446},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48929688334465027},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32064056396484375},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14758142828941345},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10944575071334839}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687523","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W4233992201","https://openalex.org/W337810568","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Visual":[0],"dialog":[1,12,37,94],"(VisDial)":[2],"requires":[3],"models":[4,139],"to":[5,52,80,103,136],"answer":[6,55],"questions":[7,57],"based":[8],"on":[9,121],"both":[10],"the":[11,30,33,36,39,42,45,56,82,89,93,112,122,137],"history":[13],"and":[14,23,38,92,114,125],"image":[15,113],"contents.":[16],"Traditional":[17],"approaches":[18],"simply":[19],"extract":[20],"relevant":[21],"visual":[22,101,106,116],"textual":[24],"information":[25,49],"for":[26,71],"answering":[27],"questions,":[28],"ignoring":[29],"relationships":[31,40,84],"between":[32,41,85],"entities":[34,87],"in":[35,44,58,88],"objects":[43,110],"image.":[46],"These":[47],"fine-grained":[48],"is":[50],"crucial":[51],"help":[53],"correctly":[54],"VisDial.":[59,72],"In":[60],"this":[61],"work,":[62],"we":[63,74,97],"propose":[64],"a":[65,77,99],"Semantic-Visual":[66],"Graph":[67],"Reasoning":[68],"framework":[69],"(SVG)":[70],"Specifically,":[73],"first":[75],"construct":[76,98],"semantic":[78,83],"graph":[79,102],"capture":[81,104],"different":[86],"current":[90],"question":[91],"history.":[95],"Secondly,":[96],"semantics-aware":[100],"high-level":[105],"semantics":[107],"including":[108],"key":[109],"of":[111],"their":[115],"relationships.":[117],"Extensive":[118],"experimental":[119],"results":[120],"VisDial":[123],"v0.9":[124],"v1.0":[126],"show":[127],"that":[128],"our":[129],"method":[130],"has":[131],"shown":[132],"superior":[133],"performance":[134],"compared":[135],"state-of-the-art":[138],"across":[140],"most":[141],"evaluation":[142],"metrics.":[143]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
