{"id":"https://openalex.org/W7134889549","doi":"https://doi.org/10.1109/icdmw69685.2025.00167","title":"TALENT: Table VQA via Augmented Language-Enhanced Natural-Text Transcription","display_name":"TALENT: Table VQA via Augmented Language-Enhanced Natural-Text Transcription","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7134889549","doi":"https://doi.org/10.1109/icdmw69685.2025.00167"},"language":null,"primary_location":{"id":"doi:10.1109/icdmw69685.2025.00167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128759217","display_name":"Yutong Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yutong Guo","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128790012","display_name":"Wanying Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanying Wang","raw_affiliation_strings":["Independent Researcher"],"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128788669","display_name":"Yue Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":["Independent Researcher"],"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063383026","display_name":"Zichen Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zichen Miao","raw_affiliation_strings":["Purdue University"],"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018990800","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0001-7485-6213"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["University at Albany"],"affiliations":[{"raw_affiliation_string":"University at Albany","institution_ids":["https://openalex.org/I392282"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5128759217"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8829835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1404","last_page":"1410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2922999858856201,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2922999858856201,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.23739999532699585,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1266999989748001,"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/transcription","display_name":"Transcription (linguistics)","score":0.5522000193595886},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.41589999198913574},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.2345000058412552},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.22849999368190765}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4787999987602234},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28200000524520874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23469999432563782},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2345000058412552},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2337999939918518},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.22849999368190765},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.22290000319480896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw69685.2025.00167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.631393313407898,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3109870706","https://openalex.org/W4284892042","https://openalex.org/W4304098321","https://openalex.org/W4402727764","https://openalex.org/W4409269797"],"related_works":[],"abstract_inverted_index":{"Table":[0,183],"Visual":[1],"Question":[2],"Answering":[3],"(Table":[4,79],"VQA)":[5],"is":[6,43],"typically":[7],"addressed":[8],"by":[9,121],"large":[10,31,167],"vision-language":[11],"models":[12,16,69],"(VLMs).":[13],"While":[14],"such":[15,56,61],"can":[17],"answer":[18],"directly":[19],"from":[20],"images,":[21],"they":[22],"often":[23],"miss":[24],"fine-grained":[25],"details":[26],"unless":[27],"scaled":[28],"to":[29,44,100,160],"very":[30],"sizes,":[32],"which":[33],"are":[34,63],"computationally":[35],"prohibitive-especially":[36],"for":[37,67,119,182],"mobile":[38],"deployment.":[39],"A":[40],"lighter":[41],"alternative":[42],"have":[45],"the":[46,111,117,127,134],"VLM":[47,99,135,155],"perform":[48],"OCR":[49,103],"and":[50,70,105,156,179],"then":[51,113],"reason":[52],"over":[53],"structured":[54],"outputs":[55],"as":[57,129,137],"Markdown":[58],"tables.":[59,94],"However,":[60],"representations":[62,92],"not":[64],"naturally":[65],"optimized":[66],"language":[68,108],"still":[71],"result":[72],"in":[73],"frequent":[74],"errors.":[75],"We":[76],"introduce":[77],"TALENT":[78,95,149],"VQA":[80],"via":[81],"Augmented":[82],"Language-Enhanced":[83],"Natural-text":[84],"Transcription),":[85],"a":[86,97,106,138,143,153,157,165],"lightweight":[87],"framework":[88],"that":[89,148],"leverages":[90],"dual":[91],"of":[93,110],"prompts":[96],"small":[98,154,158],"produce":[101],"both":[102],"text":[104],"natural":[107],"narration":[109],"table,":[112],"combines":[114],"them":[115],"with":[116,169],"question":[118],"reasoning":[120],"an":[122,177],"LLM.":[123],"This":[124],"design":[125],"reframes":[126],"task":[128],"LLM-centric":[130],"multimodal":[131],"reasoning,":[132],"where":[133],"serves":[136],"perception-narration":[139],"module":[140],"rather":[141],"than":[142],"monolithic":[144],"solver.":[145],"Experiments":[146],"show":[147],"enables":[150],"collaboration":[151],"between":[152],"LLM":[159],"rival":[161],"or":[162],"even":[163],"surpass":[164],"single":[166],"VLM,":[168],"much":[170],"lower":[171],"computational":[172],"cost.":[173],"Our":[174],"results":[175],"highlight":[176],"efficient":[178],"deployable":[180],"paradigm":[181],"VQA.":[184]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2026-03-12T00:00:00"}