{"id":"https://openalex.org/W4362655662","doi":"https://doi.org/10.48550/arxiv.2304.01603","title":"Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA","display_name":"Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA","publication_year":2023,"publication_date":"2023-04-04","ids":{"openalex":"https://openalex.org/W4362655662","doi":"https://doi.org/10.48550/arxiv.2304.01603"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2304.01603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.01603","pdf_url":"https://arxiv.org/pdf/2304.01603","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.01603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100768238","display_name":"Yongxin Zhu","orcid":"https://orcid.org/0000-0002-4757-543X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhu, Yongxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412017","display_name":"Zhen Liu","orcid":"https://orcid.org/0000-0001-9360-269X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004383790","display_name":"Yukang Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Yukang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353783","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-0144-9489"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458820","display_name":"Hao L\u00edu","orcid":"https://orcid.org/0000-0002-5336-273X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091200100","display_name":"Changcun Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Changcun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101859765","display_name":"Linli Xu","orcid":"https://orcid.org/0000-0001-6004-4425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Linli","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100768238"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":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":0.993399977684021,"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":0.9830999970436096,"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/minimum-bounding-box","display_name":"Minimum bounding box","score":0.7949608564376831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596261501312256},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6470229625701904},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6267744898796082},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6035786271095276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5946261882781982},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.51832115650177},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.49484676122665405},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4392591714859009},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43073350191116333},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4110386371612549},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0829378068447113}],"concepts":[{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.7949608564376831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596261501312256},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6470229625701904},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6267744898796082},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6035786271095276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946261882781982},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.51832115650177},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.49484676122665405},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4392591714859009},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43073350191116333},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4110386371612549},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0829378068447113},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2304.01603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.01603","pdf_url":"https://arxiv.org/pdf/2304.01603","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2304.01603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.01603","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.01603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.01603","pdf_url":"https://arxiv.org/pdf/2304.01603","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G544562989","display_name":null,"funder_award_id":"62276245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6481167376","display_name":null,"funder_award_id":"2008085J31","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4362655662.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"In":[0],"this":[1,81,95],"paper,":[2,82],"we":[3,83],"propose":[4,84],"a":[5,53,85,104,132,137,168,180,185,226],"novel":[6],"multi-modal":[7],"framework":[8],"for":[9,25],"Scene":[10],"Text":[11],"Visual":[12],"Question":[13],"Answering":[14],"(STVQA),":[15],"which":[16,34,65,92,143,246],"requires":[17],"models":[18,64],"to":[19,61,146],"read":[20],"scene":[21,38,74,154,200],"text":[22,30,39,42,75,155,201,238],"in":[23,56,73,80,115,249],"images":[24],"question":[26],"answering.":[27],"Apart":[28],"from":[29],"or":[31],"visual":[32,44,54,71,193,236],"objects,":[33],"could":[35],"exist":[36],"independently,":[37],"naturally":[40],"links":[41],"and":[43,70,136,194,213,219,237],"modalities":[45,239],"together":[46],"by":[47,164,211],"conveying":[48],"linguistic":[49,68,195],"semantics":[50,69,72,97],"while":[51],"being":[52],"object":[55],"an":[57,116,125,173],"image":[58,117],"simultaneously.":[59],"Different":[60],"conventional":[62],"STVQA":[63],"take":[66],"the":[67,99,113,121,153,160,188,192,208,216,220,241],"as":[76,103],"two":[77,96],"separate":[78],"features,":[79],"paradigm":[86],"of":[87,131,142,187,191],"\"Locate":[88],"Then":[89],"Generate\"":[90],"(LTG),":[91],"explicitly":[93],"unifies":[94,235],"with":[98,124,149,172,225],"spatial":[100,242],"bounding":[101,156,243],"box":[102,244],"bridge":[105],"connecting":[106],"them.":[107],"Specifically,":[108],"at":[109],"first,":[110],"LTG":[111,166,205,233],"locates":[112],"region":[114,133],"that":[118,232],"may":[119],"contain":[120],"answer":[122,126,161,170,174],"words":[123,162],"location":[127],"module":[128,176],"(ALM)":[129],"consisting":[130],"proposal":[134],"network":[135],"language":[138,182],"refinement":[139],"network,":[140],"both":[141],"can":[144,206],"transform":[145],"each":[147],"other":[148],"one-to-one":[150],"mapping":[151],"via":[152],"box.":[157],"Next,":[158],"given":[159],"selected":[163],"ALM,":[165],"generates":[167],"readable":[169],"sequence":[171],"generation":[175],"(AGM)":[177],"based":[178,202],"on":[179,215],"pre-trained":[181],"model.":[183],"As":[184],"benefit":[186],"explicit":[189],"alignment":[190],"semantics,":[196],"even":[197],"without":[198],"any":[199],"pre-training":[203],"tasks,":[204],"boost":[207],"absolute":[209],"accuracy":[210],"+6.06%":[212],"+6.92%":[214],"TextVQA":[217],"dataset":[218,222],"ST-VQA":[221],"respectively,":[223],"compared":[224],"non-pre-training":[227],"baseline.":[228],"We":[229],"further":[230],"demonstrate":[231],"effectively":[234],"through":[240],"connection,":[245],"is":[247],"underappreciated":[248],"previous":[250],"methods.":[251]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2023-04-07T00:00:00"}