{"id":"https://openalex.org/W4412200577","doi":"https://doi.org/10.1007/s41060-025-00835-7","title":"GViG: low-resource generative visual grounding using prompt-based language modeling for visual question answering","display_name":"GViG: low-resource generative visual grounding using prompt-based language modeling for visual question answering","publication_year":2025,"publication_date":"2025-07-11","ids":{"openalex":"https://openalex.org/W4412200577","doi":"https://doi.org/10.1007/s41060-025-00835-7"},"language":"en","primary_location":{"id":"doi:10.1007/s41060-025-00835-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-025-00835-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-025-00835-7.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s41060-025-00835-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100670477","display_name":"Yiting Li","orcid":"https://orcid.org/0000-0003-4153-8299"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yi-Ting Li","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu City, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu City, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040237383","display_name":"Ying-Jia Lin","orcid":"https://orcid.org/0000-0003-4347-0232"},"institutions":[{"id":"https://openalex.org/I173093425","display_name":"Chang Gung University","ror":"https://ror.org/00d80zx46","country_code":"TW","type":"education","lineage":["https://openalex.org/I173093425"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Jia Lin","raw_affiliation_strings":["Department of Artificial Intelligence, Chang Gung University, Taoyuan City, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Chang Gung University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I173093425"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101898313","display_name":"Hung\u2010Yu Kao","orcid":"https://orcid.org/0000-0002-8890-8544"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yu Kao","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu City, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu City, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100670477"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15475232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"7","first_page":"6489","last_page":"6505"},"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":0.9923999905586243,"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":0.9901000261306763,"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/question-answering","display_name":"Question answering","score":0.7597395181655884},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6862871050834656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6332361698150635},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5152440667152405},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49334779381752014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4597703218460083}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7597395181655884},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6862871050834656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6332361698150635},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5152440667152405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49334779381752014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4597703218460083},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s41060-025-00835-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-025-00835-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-025-00835-7.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s41060-025-00835-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-025-00835-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-025-00835-7.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323092","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412200577.pdf","grobid_xml":"https://content.openalex.org/works/W4412200577.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2597425697","https://openalex.org/W2606473278","https://openalex.org/W2907143950","https://openalex.org/W2947312908","https://openalex.org/W2962766617","https://openalex.org/W2962784628","https://openalex.org/W2964284374","https://openalex.org/W2987734933","https://openalex.org/W3034325957","https://openalex.org/W3034772468","https://openalex.org/W3090449556","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3153427360","https://openalex.org/W3159619744","https://openalex.org/W3173777717","https://openalex.org/W3192448690","https://openalex.org/W3207493267","https://openalex.org/W4214490042","https://openalex.org/W4309181071","https://openalex.org/W4312480274","https://openalex.org/W4385574358","https://openalex.org/W4386075493","https://openalex.org/W6600007113","https://openalex.org/W6600018615","https://openalex.org/W6600178739","https://openalex.org/W6600424091","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"WSDM":[1],"2023":[2],"Toloka":[3],"VQA":[4,24,80],"challenge":[5,20],"introduces":[6],"a":[7,30,70],"new":[8],"grounding-based":[9],"visual":[10,41,117],"question":[11],"answering":[12],"(GVQA)":[13],"dataset,":[14],"elevating":[15],"multimodal":[16],"task":[17],"complexity.":[18],"This":[19,129],"diverges":[21],"from":[22],"traditional":[23],"by":[25],"requiring":[26],"models":[27,57],"to":[28,35,49,62],"identify":[29],"bounding":[31],"box":[32],"in":[33,98,135],"response":[34],"an":[36,87,102],"image\u2013question":[37],"pair,":[38],"aligning":[39],"with":[40,77,140],"grounding":[42],"tasks.":[43],"Existing":[44],"VG":[45],"approaches,":[46],"when":[47],"applied":[48],"GVQA,":[50],"often":[51],"necessitate":[52],"external":[53,93],"data":[54,118],"or":[55],"larger":[56],"for":[58,152],"satisfactory":[59],"results,":[60],"leading":[61],"high":[63,133],"computational":[64],"demands.":[65],"We":[66],"approach":[67],"this":[68],"as":[69],"language":[71],"modeling":[72],"problem,":[73],"utilizing":[74],"prompt":[75],"tuning":[76],"multiple":[78],"state-of-the-art":[79],"models.":[81],"Our":[82,109],"method,":[83],"operating":[84],"solely":[85],"on":[86],"NVIDIA":[88],"RTX":[89],"3090":[90],"GPU":[91],"without":[92],"data,":[94],"secured":[95],"third":[96],"place":[97],"the":[99,150],"challenge,":[100],"achieving":[101],"Intersection":[103],"over":[104],"Union":[105],"(IoU)":[106],"of":[107,145],"75.658.":[108],"model":[110,146],"notably":[111],"provides":[112],"explainability":[113],"between":[114],"textual":[115],"and":[116,148,155],"through":[119],"its":[120,126],"attention":[121],"mechanism,":[122],"offering":[123],"insights":[124],"into":[125],"decision-making":[127],"process.":[128],"research":[130],"demonstrates":[131],"that":[132],"performance":[134],"GVQA":[136],"can":[137],"be":[138],"achieved":[139],"minimal":[141],"resources,":[142],"enhancing":[143],"understanding":[144],"dynamics":[147],"paving":[149],"way":[151],"improved":[153],"interpretability":[154],"efficiency.":[156]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}