{"id":"https://openalex.org/W3166513553","doi":"https://doi.org/10.1109/icme51207.2021.9428279","title":"SKANet: Structured Knowledge-Aware Network for Visual Dialog","display_name":"SKANet: Structured Knowledge-Aware Network for Visual Dialog","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3166513553","doi":"https://doi.org/10.1109/icme51207.2021.9428279","mag":"3166513553"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101749819","display_name":"Lei Zhao","orcid":"https://orcid.org/0000-0002-8838-164X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhao","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103213404","display_name":"Yuyu Guo","orcid":"https://orcid.org/0000-0003-4376-6922"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyu Guo","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengtao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"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/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":0.9940000176429749,"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":0.9876999855041504,"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/dialog-box","display_name":"Dialog box","score":0.9379545450210571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8557496070861816},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6696876883506775},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5951387286186218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5791751742362976},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5248755812644958},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5051000714302063},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.481989324092865},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46886566281318665},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4488081932067871},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42877382040023804},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10897290706634521},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10162502527236938}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9379545450210571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8557496070861816},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6696876883506775},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5951387286186218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5791751742362976},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5248755812644958},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5051000714302063},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.481989324092865},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46886566281318665},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4488081932067871},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42877382040023804},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10897290706634521},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10162502527236938},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W2283196293","https://openalex.org/W2558809543","https://openalex.org/W2561529111","https://openalex.org/W2603266952","https://openalex.org/W2745461083","https://openalex.org/W2892245540","https://openalex.org/W2904452845","https://openalex.org/W2962958773","https://openalex.org/W2963187678","https://openalex.org/W2963791035","https://openalex.org/W2964015378","https://openalex.org/W2964218959","https://openalex.org/W2965287587","https://openalex.org/W2966730259","https://openalex.org/W2967045987","https://openalex.org/W2970355596","https://openalex.org/W2981902456","https://openalex.org/W2983995706","https://openalex.org/W3034291519","https://openalex.org/W3035243232","https://openalex.org/W4249013746","https://openalex.org/W6695596964","https://openalex.org/W6726873649","https://openalex.org/W6730529904","https://openalex.org/W6748686444"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047","https://openalex.org/W1977846844","https://openalex.org/W2901575119"],"abstract_inverted_index":{"Visual":[0],"dialog":[1,15,51,83],"aims":[2],"to":[3,7],"generate":[4],"an":[5,12,64],"answer":[6],"each":[8],"question":[9],"based":[10],"on":[11,25,35,109],"image":[13],"and":[14,68,85,96],"history.":[16],"Despite":[17],"recent":[18],"progress,":[19],"existing":[20],"methods":[21],"still":[22],"undergo":[23],"degradation":[24],"the":[26,78,82,91,94,110],"condition":[27],"of":[28,59],"complex":[29,92],"scenarios.":[30],"Handling":[31],"these":[32],"scenarios":[33],"depends":[34],"logical":[36],"reasoning":[37],"that":[38,115],"requires":[39],"common":[40,101],"sense":[41,102],"priors.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"a":[48,60,69],"novel":[49],"visual":[50,86],"pipeline,":[52],"named":[53],"Structured":[54],"Knowledge-Aware":[55,66,71,98],"Network":[56],"(SKANet),":[57],"consisting":[58],"Multi-Modality":[61,74],"Fusion":[62,75],"Module,":[63,67],"Image":[65,95],"Caption":[70,97],"Module.":[72],"The":[73],"Module":[76],"explores":[77],"textual":[79],"context":[80],"about":[81],"history":[84],"content.":[87],"To":[88],"deal":[89],"with":[90],"scenarios,":[93],"Modules":[99],"construct":[100],"knowledge":[103],"graphs":[104],"from":[105],"ConceptNet.":[106],"Experimental":[107],"results":[108],"VisDial":[111],"v1.0":[112],"dataset":[113],"show":[114],"our":[116],"proposed":[117],"method":[118],"effectively":[119],"outperforms":[120],"comparative":[121],"methods.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
