{"id":"https://openalex.org/W4387827795","doi":"https://doi.org/10.1145/3615522.3615547","title":"Visual Analysis of Scene-Graph-Based Visual Question Answering","display_name":"Visual Analysis of Scene-Graph-Based Visual Question Answering","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4387827795","doi":"https://doi.org/10.1145/3615522.3615547"},"language":"en","primary_location":{"id":"doi:10.1145/3615522.3615547","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3615522.3615547","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3615522.3615547","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Symposium on Visual Information Communication and Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3615522.3615547","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015204353","display_name":"Noel Sch\u00e4fer","orcid":"https://orcid.org/0009-0007-4034-3453"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Noel Sch\u00e4fer","raw_affiliation_strings":["VISUS, University of Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0009-0007-4034-3453","affiliations":[{"raw_affiliation_string":"VISUS, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062353537","display_name":"Sebastian K\u00fcnzel","orcid":"https://orcid.org/0009-0001-0799-4293"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian K\u00fcnzel","raw_affiliation_strings":["VISUS, University of Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0009-0001-0799-4293","affiliations":[{"raw_affiliation_string":"VISUS, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057232508","display_name":"Tanja Munz","orcid":"https://orcid.org/0000-0003-3960-3290"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tanja Munz-K\u00f6rner","raw_affiliation_strings":["VISUS, University of Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3960-3290","affiliations":[{"raw_affiliation_string":"VISUS, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091791731","display_name":"Pascal Tilli","orcid":"https://orcid.org/0009-0001-7503-1413"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pascal Tilli","raw_affiliation_strings":["IMS, University of Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0009-0001-7503-1413","affiliations":[{"raw_affiliation_string":"IMS, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026359143","display_name":"Sandeep Vidyapu","orcid":"https://orcid.org/0000-0003-3595-5221"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sandeep Vidyapu","raw_affiliation_strings":["VISUS, University of Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3595-5221","affiliations":[{"raw_affiliation_string":"VISUS, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["IMS, University of Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7893-9147","affiliations":[{"raw_affiliation_string":"IMS, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073619125","display_name":"Daniel Weiskopf","orcid":"https://orcid.org/0000-0003-1174-1026"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Weiskopf","raw_affiliation_strings":["VISUS, University of Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1174-1026","affiliations":[{"raw_affiliation_string":"VISUS, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5015204353"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":0.2355,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53116598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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":0.9970999956130981,"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":0.8400872945785522},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.7549734115600586},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7135452628135681},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5720453858375549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5330981612205505},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4578595757484436},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.4575246572494507},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44854068756103516},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4356907308101654},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4304487109184265},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3762396574020386},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3293289542198181},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3256719708442688},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1458827555179596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8400872945785522},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.7549734115600586},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7135452628135681},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5720453858375549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5330981612205505},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4578595757484436},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.4575246572494507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44854068756103516},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4356907308101654},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4304487109184265},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3762396574020386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3293289542198181},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3256719708442688},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1458827555179596},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3615522.3615547","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3615522.3615547","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3615522.3615547","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Symposium on Visual Information Communication and Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3615522.3615547","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3615522.3615547","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3615522.3615547","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Symposium on Visual Information Communication and Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G8784604414","display_name":null,"funder_award_id":"390740016","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387827795.pdf","grobid_xml":"https://content.openalex.org/works/W4387827795.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W380705384","https://openalex.org/W2097481508","https://openalex.org/W2587299461","https://openalex.org/W2607223307","https://openalex.org/W2752194699","https://openalex.org/W2895658904","https://openalex.org/W2963214037","https://openalex.org/W2963518342","https://openalex.org/W2963707011","https://openalex.org/W2975495759","https://openalex.org/W3011797839","https://openalex.org/W3108010663","https://openalex.org/W3202031328","https://openalex.org/W3209226499","https://openalex.org/W4200335458","https://openalex.org/W4200475213","https://openalex.org/W4200498145","https://openalex.org/W4301409532","https://openalex.org/W6906755507"],"related_works":["https://openalex.org/W2013728941","https://openalex.org/W4225274103","https://openalex.org/W2579659702","https://openalex.org/W2154046714","https://openalex.org/W1965329638","https://openalex.org/W2189613078","https://openalex.org/W1574055964","https://openalex.org/W2923661510","https://openalex.org/W2542318691","https://openalex.org/W3160708108"],"abstract_inverted_index":{"Scene-graph-based":[0],"Visual":[1],"Question":[2],"Answering":[3],"(VQA)":[4],"has":[5],"emerged":[6],"as":[7],"a":[8,16,30,131,140],"burgeoning":[9],"field":[10],"in":[11,40],"Deep":[12],"Learning":[13],"research,":[14],"with":[15,92],"growing":[17],"demand":[18],"for":[19,117],"robust":[20],"and":[21,43,47,76,103,114,123,137,151],"interpretable":[22],"VQA":[23],"systems.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,109,143],"present":[29],"novel":[31],"visual":[32],"analysis":[33,86,102,149],"approach":[34,59],"that":[35],"addresses":[36],"two":[37],"critical":[38],"objectives":[39],"VQA:":[41],"identifying":[42],"correcting":[44],"prediction":[45],"issues":[46],"providing":[48],"insights":[49],"into":[50],"model":[51,121,152],"decision-making":[52],"processes":[53],"through":[54],"visualizing":[55],"internal":[56,107,128],"information.":[57],"Our":[58,85],"builds":[60],"on":[61,80],"the":[62,81,93,145],"GraphVQA":[63],"framework,":[64],"which":[65,77],"uses":[66],"graph":[67],"neural":[68],"networks":[69],"to":[70,112],"process":[71],"scene":[72,101],"graphs":[73],"representing":[74],"images":[75],"was":[78],"trained":[79],"widely-used":[82],"GQA":[83],"dataset.":[84],"tool":[87,150],"aims":[88],"at":[89],"users":[90],"familiar":[91],"basics":[94],"of":[95,105,139,147],"graph-based":[96],"VQA.":[97],"By":[98],"leveraging":[99],"query-based":[100],"visualization":[104],"crucial":[106],"states,":[108],"are":[110],"able":[111],"detect":[113],"pinpoint":[115],"reasons":[116],"inaccurate":[118],"predictions,":[119],"facilitating":[120],"refinement":[122],"dataset":[124],"curation.":[125],"Identifying":[126],"expressive":[127],"states":[129],"is":[130],"challenge.":[132],"Through":[133],"rigorous":[134],"computer-based":[135],"evaluations":[136],"presentation":[138],"use":[141],"case,":[142],"demonstrate":[144],"effectiveness":[146],"our":[148],"state":[153],"visualization.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}