{"id":"https://openalex.org/W4408351862","doi":"https://doi.org/10.1109/icassp49660.2025.10888359","title":"SiQA: A Large Multi-Modal Question Answering Model for Structured Images Based on RAG","display_name":"SiQA: A Large Multi-Modal Question Answering Model for Structured Images Based on RAG","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351862","doi":"https://doi.org/10.1109/icassp49660.2025.10888359"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5070619167","display_name":"Jiawang Liu","orcid":"https://orcid.org/0000-0003-3264-6271"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawang Liu","raw_affiliation_strings":["Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045354938","display_name":"Ye Tao","orcid":"https://orcid.org/0009-0000-9789-3826"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Tao","raw_affiliation_strings":["Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455958","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0003-3462-8472"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627145","display_name":"Hui Li","orcid":"https://orcid.org/0000-0003-1330-4401"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qingdao University of Science and Technology,School of Information Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018911894","display_name":"Xiugong Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136225","display_name":"Beijing Research Institute of Automation for Machinery Industry (China)","ror":"https://ror.org/03rbc9d50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiugong Qin","raw_affiliation_strings":["Beijing Research Institute of Automation for Machinery Industry Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Research Institute of Automation for Machinery Industry Co., Ltd.,Beijing,China","institution_ids":["https://openalex.org/I4210136225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8699,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84136481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval 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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval 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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9887999892234802,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9818999767303467,"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/computer-science","display_name":"Computer science","score":0.7458771467208862},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6463542580604553},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6286906003952026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4747738540172577},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45281121134757996},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38337525725364685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458771467208862},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6463542580604553},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6286906003952026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4747738540172577},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45281121134757996},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38337525725364685},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2970641574","https://openalex.org/W2998702515","https://openalex.org/W3128272199","https://openalex.org/W3197016550","https://openalex.org/W4285279070","https://openalex.org/W4285294723","https://openalex.org/W4385991121","https://openalex.org/W4386065512","https://openalex.org/W4386597256","https://openalex.org/W4389520282","https://openalex.org/W4390873637","https://openalex.org/W4392904203","https://openalex.org/W4393149524","https://openalex.org/W4393160302","https://openalex.org/W4400231894","https://openalex.org/W4402753519","https://openalex.org/W4402753862","https://openalex.org/W4402754006","https://openalex.org/W4402780269","https://openalex.org/W4403791441","https://openalex.org/W4404783754","https://openalex.org/W6726873649","https://openalex.org/W6784333009","https://openalex.org/W6795140394","https://openalex.org/W6809646742","https://openalex.org/W6839401645","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6855350031","https://openalex.org/W6856800273","https://openalex.org/W6864288807"],"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":{"Existing":[0],"Large":[1],"Multimodal":[2],"Models":[3],"(LMMs)":[4],"demonstrate":[5],"excellent":[6],"performance":[7],"in":[8,12,20,60],"handling":[9],"visual":[10],"tasks":[11],"everyday":[13],"scenarios.":[14],"However,":[15],"they":[16],"still":[17],"face":[18],"challenges":[19],"understanding":[21],"structured":[22,79,147],"images,":[23],"such":[24],"as":[25],"flowcharts":[26],"and":[27,35,48,68,94,150,159,161,165],"organizational":[28],"charts,":[29],"which":[30,135],"are":[31],"characterized":[32],"by":[33],"text-rich":[34],"complex":[36],"hierarchical":[37],"components.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,127],"propose":[43],"SiQA,":[44],"a":[45,72,97,129],"knowledge":[46],"construction":[47],"Retrieval-Augmented":[49],"Generation(RAG)-based":[50],"multimodal":[51,114],"Question-Answering":[52],"model":[53],"designed":[54],"for":[55],"Structured":[56],"Images.":[57],"SiQA":[58],"operates":[59],"three":[61],"stages:":[62],"Knowledge":[63],"Graph":[64],"(KG)":[65],"generation,":[66],"retrieval-augmented,":[67],"answer":[69],"generation.":[70],"First,":[71],"KG":[73,93],"representing":[74],"the":[75,78,92,102,113,120,124,154],"semantics":[76],"of":[77],"images":[80],"is":[81,117],"generated":[82],"through":[83,169],"component":[84],"analysis.":[85],"We":[86,144],"then":[87],"performed":[88],"similarity":[89],"retrieval":[90],"between":[91],"queries,":[95],"using":[96],"node-first":[98],"algorithm":[99],"to":[100,122],"construct":[101],"most":[103],"relevant":[104],"subgraph.":[105],"Finally,":[106],"after":[107],"performing":[108],"an":[109],"encoding":[110],"alignment":[111],"on":[112,153],"information,":[115],"it":[116],"fed":[118],"into":[119],"LLM":[121],"generate":[123],"answer.":[125],"Additionally,":[126],"introduce":[128],"new":[130],"dataset,":[131],"OCQA<sup":[132],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[133],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[134],"includes":[136],"5,112":[137],"questions":[138],"derived":[139],"from":[140],"1,000":[141],"Organizational":[142],"Charts.":[143],"evaluated":[145],"SiQA\u2019s":[146],"image":[148],"detection":[149],"question-answering":[151],"capabilities":[152],"FD-DETR":[155],"(a":[156],"flowchart":[157],"dataset)":[158],"SCQA,":[160],"verified":[162],"its":[163],"effectiveness":[164],"strong":[166],"generalization":[167],"ability":[168],"comparisons":[170],"with":[171],"existing":[172],"state-of-the-art":[173],"(SOTA)":[174],"methods.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}