{"id":"https://openalex.org/W4412394899","doi":"https://doi.org/10.1145/3726302.3729990","title":"GlFoMR: A Glance-then-Focus Multimodal Reasoning Framework for Diagram Question Answering","display_name":"GlFoMR: A Glance-then-Focus Multimodal Reasoning Framework for Diagram Question Answering","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412394899","doi":"https://doi.org/10.1145/3726302.3729990"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3729990","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729990","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729990","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/10.1145/3726302.3729990","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101851808","display_name":"Yaxian Wang","orcid":"https://orcid.org/0000-0003-3193-3658"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxian Wang","raw_affiliation_strings":["School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-3193-3658","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070094915","display_name":"Bifan Wei","orcid":"https://orcid.org/0000-0002-9732-3011"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bifan Wei","raw_affiliation_strings":["School of Continuing Education, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-9732-3011","affiliations":[{"raw_affiliation_string":"School of Continuing Education, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361891","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-6004-0675"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6004-0675","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384144","display_name":"Lingling Zhang","orcid":"https://orcid.org/0000-0001-8136-8795"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8136-8795","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085200012","display_name":"Shuting He","orcid":"https://orcid.org/0000-0002-1582-5684"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuting He","raw_affiliation_strings":["Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1582-5684","affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112086045","display_name":"Jun Li","orcid":"https://orcid.org/0009-0006-3176-8030"},"institutions":[{"id":"https://openalex.org/I4210121144","display_name":"China Machine Press","ror":"https://ror.org/02t1dzr71","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210121144"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3176-8030","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China","institution_ids":["https://openalex.org/I4210121144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086407377","display_name":"Qika Lin","orcid":"https://orcid.org/0000-0001-5650-0600"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qika Lin","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5650-0600","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1130","last_page":"1140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9991000294685364,"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":0.9958000183105469,"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/focus","display_name":"Focus (optics)","score":0.7559592723846436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7364107966423035},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6911568641662598},{"id":"https://openalex.org/keywords/diagram","display_name":"Diagram","score":0.4377681016921997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.357910692691803},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33175498247146606},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12934482097625732},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05257806181907654}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7559592723846436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7364107966423035},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6911568641662598},{"id":"https://openalex.org/C186399060","wikidata":"https://www.wikidata.org/wiki/Q959962","display_name":"Diagram","level":2,"score":0.4377681016921997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.357910692691803},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33175498247146606},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12934482097625732},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05257806181907654},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3729990","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729990","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729990","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3729990","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729990","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729990","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1519579974","display_name":null,"funder_award_id":"62306229","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1661763918","display_name":null,"funder_award_id":"62293554","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2369050462","display_name":null,"funder_award_id":"2022YFC3303600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2481529711","display_name":null,"funder_award_id":"62137002, 62293550, 62293553, 62293554, 62450005, 62437002, 62477036, 62477037, 62176209, 62192781, and 62306229","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G2496375212","display_name":null,"funder_award_id":"62293550","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4303215675","display_name":null,"funder_award_id":"62192781","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4712315907","display_name":null,"funder_award_id":"62437002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4896784468","display_name":null,"funder_award_id":"62137002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6311837223","display_name":null,"funder_award_id":"62293553","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6939427173","display_name":null,"funder_award_id":"2022YFC3303600","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G7339645210","display_name":null,"funder_award_id":"62176209","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/F4320321169","display_name":"Xi\u2019an Jiaotong University","ror":"https://ror.org/017zhmm22"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412394899.pdf","grobid_xml":"https://content.openalex.org/works/W4412394899.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2153110463","https://openalex.org/W2307512708","https://openalex.org/W2746097825","https://openalex.org/W2970919161","https://openalex.org/W2990138404","https://openalex.org/W3126713371","https://openalex.org/W4282936652","https://openalex.org/W4296605665","https://openalex.org/W4313013044","https://openalex.org/W4320914959","https://openalex.org/W4385570088","https://openalex.org/W4386116948","https://openalex.org/W4387994822","https://openalex.org/W4389154210","https://openalex.org/W4389520252","https://openalex.org/W4390874575","https://openalex.org/W4393146968","https://openalex.org/W4393160064","https://openalex.org/W4393161084","https://openalex.org/W4394009537","https://openalex.org/W4394625850","https://openalex.org/W4402672053","https://openalex.org/W4402715874","https://openalex.org/W4402727624","https://openalex.org/W4402727764","https://openalex.org/W4402753910","https://openalex.org/W4406354624","https://openalex.org/W4410992944","https://openalex.org/W6600459194","https://openalex.org/W6600493712","https://openalex.org/W6600577311","https://openalex.org/W6818723395","https://openalex.org/W7035904466"],"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/W2115758952"],"abstract_inverted_index":{"Diagram":[0],"question":[1],"answering":[2],"(DQA)":[3],"is":[4,79,113,186],"a":[5,42,90,101,116,144],"challenging":[6],"task":[7],"that":[8,215],"requires":[9],"models":[10],"to":[11,21,82,135,156,176,223],"combine":[12],"with":[13],"domain-specific":[14,171],"knowledge":[15,157,172],"and":[16,37,66,74,107,126,131,161,173,198],"reason":[17],"over":[18,59],"the":[19,47,60,111,129,137,150,190,196,225],"diagrams":[20],"answer":[22],"questions.":[23],"Multimodal":[24,92],"Large":[25],"Language":[26],"Models":[27],"(MLLMs)":[28],"have":[29],"recently":[30],"made":[31],"notable":[32],"strides":[33],"in":[34,55],"combining":[35],"textual":[36,75],"visual":[38,62,73,106,159,162,174],"information,":[39],"emerging":[40],"as":[41],"promising":[43],"solution":[44],"for":[45,77,97,104,203],"addressing":[46],"DQA":[48,205,212],"task.":[49],"However,":[50],"they":[51],"still":[52],"encounter":[53],"challenges":[54],"deliberate":[56,179],"multimodal":[57,151,228],"reasoning":[58,76,139,199],"fine-grained":[61],"details":[63,175],"of":[64,72,201,227],"content-rich":[65],"knowledge-grounded":[67],"diagrams.":[68],"The":[69,181],"tight":[70],"interweaving":[71],"MLLMs":[78,202],"also":[80],"susceptible":[81],"hallucinations.":[83],"To":[84],"overcome":[85],"these":[86,166],"limitations,":[87],"we":[88],"propose":[89],"Glance-then-Focus":[91],"Reasoning":[93],"framework":[94],"named":[95],"GlFoMR":[96,216],"DQA,":[98],"which":[99],"features":[100],"flexible":[102],"architecture":[103],"comprehensive":[105],"text":[108],"interaction.":[109],"Firstly,":[110],"diagram":[112,184],"parsed":[114,182],"into":[115,189],"hierarchical":[117],"structure":[118],"spanning":[119],"different":[120],"granularities":[121],"including":[122],"isolated":[123],"single-object,":[124],"object-group,":[125],"whole-diagram.":[127],"Subsequently,":[128],"Glance-Plan":[130,141],"Focus-Reason":[132,168],"stages":[133],"collaborate":[134],"decouple":[136],"complex":[138],"process.":[140],"first":[142],"generates":[143],"preliminary":[145],"plan":[146],"by":[147],"glancing":[148],"at":[149],"context,":[152],"specifying":[153],"sub-goals":[154],"related":[155],"extraction,":[158],"perception,":[160],"reasoning.":[163,180,229],"Based":[164],"on":[165,210],"sub-goals,":[167],"further":[169],"integrates":[170],"enable":[177],"more":[178],"multi-granularity":[183],"information":[185],"seamlessly":[187],"incorporated":[188],"corresponding":[191],"sub-goal":[192],"achievement":[193],"process,":[194],"enhancing":[195],"perception":[197],"capabilities":[200],"better":[204],"performance.":[206],"Extensive":[207],"experimental":[208],"results":[209],"four":[211],"datasets":[213],"demonstrate":[214],"achieves":[217],"substantial":[218],"improvements,":[219],"showcasing":[220],"its":[221],"potential":[222],"advance":[224],"development":[226]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}