{"id":"https://openalex.org/W4415540651","doi":"https://doi.org/10.1145/3746027.3761996","title":"AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings","display_name":"AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540651","doi":"https://doi.org/10.1145/3746027.3761996"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3761996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3761996","pdf_url":null,"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 33rd 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://doi.org/10.1145/3746027.3761996","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Haoxuan Li","orcid":"https://orcid.org/0009-0008-3775-0688"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxuan Li","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-3775-0688","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111043554","display_name":"Wei Song","orcid":"https://orcid.org/0009-0006-8868-3134"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Song","raw_affiliation_strings":["School of Automation, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-8868-3134","affiliations":[{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051022943","display_name":"Aofan Liu","orcid":"https://orcid.org/0000-0002-6377-1633"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aofan Liu","raw_affiliation_strings":["School of Information Engineering, Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6377-1633","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014040365","display_name":"Peiwu Qin","orcid":"https://orcid.org/0000-0002-7829-8973"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiwu Qin","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7829-8973","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33171446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13777","last_page":"13783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9959999918937683,"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":0.7537000179290771},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5932000279426575},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5404000282287598},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5397999882698059},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4595000147819519},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4514000117778778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299999833106995},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7537000179290771},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5932000279426575},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5404000282287598},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5397999882698059},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5097000002861023},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45489999651908875},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3538999855518341},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3343000113964081},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3761996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3761996","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3761996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3761996","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2970641574","https://openalex.org/W3004268082","https://openalex.org/W3100806282","https://openalex.org/W3120043490","https://openalex.org/W4382202558","https://openalex.org/W4385237494","https://openalex.org/W4402727764"],"related_works":[],"abstract_inverted_index":{"Document":[0],"Visual":[1],"Question":[2],"Answering":[3],"(Document":[4],"VQA)":[5],"faces":[6],"significant":[7],"challenges":[8,34],"when":[9],"processing":[10],"long":[11],"documents":[12],"in":[13,99],"low-resource":[14,133],"environments":[15],"due":[16],"to":[17],"context":[18],"limitations":[19],"and":[20,63,71,94,101,115,135],"insufficient":[21],"training":[22],"data.":[23],"This":[24],"paper":[25],"presents":[26],"AdaDocVQA,":[27],"a":[28,39,128],"unified":[29],"adaptive":[30,64],"framework":[31,117],"addressing":[32],"these":[33],"through":[35],"three":[36],"core":[37],"innovations:":[38],"hybrid":[40],"text":[41],"retrieval":[42],"architecture":[43],"for":[44,122,131],"effective":[45],"document":[46,78,124],"segmentation,":[47],"an":[48],"intelligent":[49],"data":[50],"augmentation":[51],"pipeline":[52],"that":[53],"automatically":[54],"generates":[55],"high-quality":[56],"reasoning":[57],"question-answer":[58],"pairs":[59],"with":[60,67,84],"multi-level":[61],"verification,":[62],"ensemble":[65],"inference":[66],"dynamic":[68],"configuration":[69],"generation":[70],"early":[72],"stopping":[73],"mechanisms.":[74],"Experiments":[75],"on":[76,87,91,96,104],"Japanese":[77,123],"VQA":[79,125],"benchmarks":[80],"demonstrate":[81],"substantial":[82],"improvements":[83],"83.04%":[85],"accuracy":[86,103],"Yes/No":[88],"questions,":[89,93],"52.66%":[90],"factual":[92],"44.12%":[95],"numerical":[97],"questions":[98],"JDocQA,":[100],"59%":[102],"LAVA":[105],"dataset.":[106],"Ablation":[107],"studies":[108],"confirm":[109],"meaningful":[110],"contributions":[111],"from":[112],"each":[113],"component,":[114],"our":[116],"establishes":[118],"new":[119],"state-of-the-art":[120],"results":[121],"while":[126],"providing":[127],"scalable":[129],"foundation":[130],"other":[132],"languages":[134],"specialized":[136],"domains.":[137],"Our":[138],"code":[139],"available":[140],"at:":[141],"https://github.com/Haoxuanli-Thu/AdaDocVQA.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}