{"id":"https://openalex.org/W4387968236","doi":"https://doi.org/10.1145/3581783.3614244","title":"VTQA2023: ACM Multimedia 2023 Visual Text Question Answering Challenge","display_name":"VTQA2023: ACM Multimedia 2023 Visual Text Question Answering Challenge","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968236","doi":"https://doi.org/10.1145/3581783.3614244"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3614244","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3614244","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3614244","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3614244","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102011904","display_name":"Kang Chen","orcid":"https://orcid.org/0009-0008-2667-3373"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Chen","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0008-2667-3373","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534704","display_name":"Tianli Zhao","orcid":"https://orcid.org/0009-0004-0938-3690"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianli Zhao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0004-0938-3690","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030966569","display_name":"Xiangqian Wu","orcid":"https://orcid.org/0000-0002-0956-8757"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangqian Wu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-0956-8757","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16587903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9646","last_page":"9650"},"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":0.9972000122070312,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9884999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8646414279937744},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8539525866508484},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5482627749443054},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5330193042755127},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4978039264678955},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46862155199050903},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45926347374916077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4435601830482483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4110180735588074},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34388917684555054},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0881853699684143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8646414279937744},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8539525866508484},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5482627749443054},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5330193042755127},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4978039264678955},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46862155199050903},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45926347374916077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4435601830482483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4110180735588074},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34388917684555054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0881853699684143},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3614244","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3614244","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3614244","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3614244","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3614244","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3614244","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5035196547","display_name":null,"funder_award_id":"ZD2022F002","funder_id":"https://openalex.org/F4320323085","funder_display_name":"Natural Science Foundation of Heilongjiang Province"},{"id":"https://openalex.org/G6060587251","display_name":null,"funder_award_id":"2020AAA0106502","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G711209656","display_name":null,"funder_award_id":"62073105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968236.pdf","grobid_xml":"https://content.openalex.org/works/W4387968236.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2747329762","https://openalex.org/W2964303913","https://openalex.org/W2981852735","https://openalex.org/W4226278471","https://openalex.org/W4288089799"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W2147241511","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952"],"abstract_inverted_index":{"The":[0,103],"ideal":[1],"form":[2],"of":[3,16,29,48,82,105,117],"Visual":[4],"Question":[5],"Answering":[6],"requires":[7,75],"understanding,":[8],"grounding":[9],"and":[10,18,20,50,92,94,111,123],"reasoning":[11,89,122],"in":[12],"the":[13,26,42,73,76,83,101],"joint":[14],"space":[15],"vision":[17],"language":[19,98],"serves":[21],"as":[22],"a":[23,45,57,61],"proxy":[24],"for":[25],"AI":[27],"task":[28,74],"scene":[30],"understanding.":[31],"However,":[32],"most":[33],"existing":[34],"VQA":[35],"benchmarks":[36],"are":[37,115],"limited":[38],"to":[39,53,78,86,99,109],"just":[40],"picking":[41],"answer":[43,100,125],"from":[44],"pre-defined":[46],"set":[47],"options":[49],"lack":[51],"attention":[52],"text.":[54],"We":[55],"present":[56],"new":[58],"challenge":[59,107],"with":[60],"dataset":[62],"that":[63,114],"contains":[64],"23,781":[65],"questions":[66],"based":[67],"on":[68],"10124":[69],"image-text":[70],"pairs.":[71],"Specifically,":[72],"model":[77],"align":[79],"multimedia":[80,118],"representations":[81],"same":[84],"entity":[85,119],"implement":[87],"multi-hop":[88],"between":[90],"image":[91],"text":[93],"finally":[95],"use":[96],"natural":[97],"question.":[102],"aim":[104],"this":[106],"is":[108],"develop":[110],"benchmark":[112],"models":[113],"capable":[116],"alignment,":[120],"multi-step":[121],"open-ended":[124],"generation.":[126]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}