{"id":"https://openalex.org/W3211539296","doi":"https://doi.org/10.48550/arxiv.2004.06698","title":"Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer","display_name":"Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer","publication_year":2020,"publication_date":"2020-04-14","ids":{"openalex":"https://openalex.org/W3211539296","doi":"https://doi.org/10.48550/arxiv.2004.06698","mag":"3211539296"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2004.06698","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06698","pdf_url":"https://arxiv.org/pdf/2004.06698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.06698","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022061514","display_name":"Gi-Cheon Kang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kang, Gi-Cheon","raw_affiliation_strings":["Seoul National University, AIIS","Junseok Park","NAVER AI Lab","Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, AIIS","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Junseok Park","institution_ids":[]},{"raw_affiliation_string":"NAVER AI Lab","institution_ids":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101980171","display_name":"Junseok Park","orcid":"https://orcid.org/0009-0004-0347-5842","observed_orcids":["https://orcid.org/0009-0004-0347-5842"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Junseok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054334046","display_name":"Hwaran Lee","orcid":"https://orcid.org/0000-0002-3773-4871","observed_orcids":["https://orcid.org/0000-0002-3773-4871"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lee, Hwaran","raw_affiliation_strings":["NAVER AI Lab","Junseok Park","Seoul National University","Seoul National University, AIIS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER AI Lab","institution_ids":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"raw_affiliation_string":"Junseok Park","institution_ids":[]},{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University, AIIS","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050928023","display_name":"Byoung\u2010Tak Zhang","orcid":"https://orcid.org/0000-0001-9890-0389","observed_orcids":["https://orcid.org/0000-0001-9890-0389"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zhang, Byoung-Tak","raw_affiliation_strings":["Junseok Park","Seoul National University, AIIS","NAVER AI Lab","Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Junseok Park","institution_ids":[]},{"raw_affiliation_string":"Seoul National University, AIIS","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"NAVER AI Lab","institution_ids":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101954750","display_name":"Jin-Hwa Kim","orcid":"https://orcid.org/0000-0002-0423-0415","observed_orcids":["https://orcid.org/0000-0002-0423-0415"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Jin-Hwa","raw_affiliation_strings":["NAVER AI Lab","Junseok Park","Seoul National University","Seoul National University, AIIS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER AI Lab","institution_ids":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"raw_affiliation_string":"Junseok Park","institution_ids":[]},{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University, AIIS","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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":0.9980000257492065,"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/T12031","display_name":"Speech and dialogue systems","score":0.0008999999845400453,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.00019999999494757503,"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/visual-dialogue","display_name":"visual dialogue","score":0.9670000076293945},{"id":"https://openalex.org/keywords/sparse-graph-learning","display_name":"sparse graph learning","score":0.828000009059906},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"knowledge transfer","score":0.9359999895095825},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.6100000143051147},{"id":"https://openalex.org/keywords/graph-structure-learning","display_name":"graph structure learning","score":0.7390000224113464}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9481790661811829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8117364645004272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6356478929519653},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.548244833946228},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5447240471839905},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5174953937530518},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5131550431251526},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.47241535782814026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4665773808956146},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.42355024814605713},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4106263518333435},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2685868442058563},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2004.06698","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06698","pdf_url":"https://arxiv.org/pdf/2004.06698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2004.06698","doi":"https://doi.org/10.48550/arxiv.2004.06698","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.06698","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.06698","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06698","pdf_url":"https://arxiv.org/pdf/2004.06698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3211539296.pdf","grobid_xml":"https://content.openalex.org/works/W3211539296.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2912323206","https://openalex.org/W3099143471"],"related_works":["https://openalex.org/W3016271098","https://openalex.org/W4402979270","https://openalex.org/W4281997825","https://openalex.org/W2967045987","https://openalex.org/W4394564345","https://openalex.org/W3205857725","https://openalex.org/W3166513553","https://openalex.org/W2963287297","https://openalex.org/W4223451840","https://openalex.org/W4296079526"],"abstract_inverted_index":{"Visual":[0],"dialog":[1,18,43,70,81],"is":[2,170],"a":[3,7,61,72,91,99,136,144],"task":[4],"of":[5,9,126,135],"answering":[6],"sequence":[8],"questions":[10],"grounded":[11],"in":[12],"an":[13],"image":[14],"using":[15],"the":[16,52,106,110,124,133,159,163],"previous":[17],"history":[19],"as":[20,71,116],"context.":[21],"In":[22],"this":[23,34],"paper,":[24],"we":[25,59,97],"study":[26],"how":[27],"to":[28,51,67,122,138,154],"address":[29,56],"two":[30],"fundamental":[31],"challenges":[32],"for":[33],"task:":[35],"(1)":[36],"reasoning":[37,151],"over":[38],"underlying":[39],"semantic":[40],"structures":[41,82],"among":[42],"rounds":[44],"and":[45,86,89,113,157],"(2)":[46],"identifying":[47],"several":[48],"appropriate":[49],"answers":[50],"given":[53],"question.":[54],"To":[55],"these":[57],"challenges,":[58],"propose":[60,120],"Sparse":[62],"Graph":[63],"Learning":[64],"(SGL)":[65],"method":[66,103],"formulate":[68],"visual":[69],"graph":[73],"structure":[74],"learning":[75],"task.":[76],"SGL":[77],"infers":[78],"inherently":[79],"sparse":[80],"by":[83],"incorporating":[84],"binary":[85],"score":[87],"edges":[88],"leveraging":[90],"new":[92],"structural":[93],"loss":[94],"function.":[95],"Next,":[96],"introduce":[98],"Knowledge":[100],"Transfer":[101],"(KT)":[102],"that":[104],"extracts":[105],"answer":[107],"predictions":[108],"from":[109],"teacher":[111],"model":[112,137,148],"uses":[114],"them":[115],"pseudo":[117],"labels.":[118],"We":[119],"KT":[121],"remedy":[123],"shortcomings":[125],"single":[127],"ground-truth":[128],"labels,":[129],"which":[130],"severely":[131],"limit":[132],"ability":[134],"obtain":[139],"multiple":[140],"reasonable":[141],"answers.":[142],"As":[143],"result,":[145],"our":[146],"proposed":[147],"significantly":[149],"improves":[150],"capability":[152],"compared":[153],"baseline":[155],"methods":[156],"outperforms":[158],"state-of-the-art":[160],"approaches":[161],"on":[162],"VisDial":[164],"v1.0":[165],"dataset.":[166],"The":[167],"source":[168],"code":[169],"available":[171],"at":[172],"https://github.com/gicheonkang/SGLKT-VisDial.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-22T00:00:00"}
