{"id":"https://openalex.org/W4415707982","doi":"https://doi.org/10.1109/icme59968.2025.11209313","title":"MP-FIRE: An End-to-End Cross-Modal Framework for Complex Multi-Page Document Question Answering","display_name":"MP-FIRE: An End-to-End Cross-Modal Framework for Complex Multi-Page Document Question Answering","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707982","doi":"https://doi.org/10.1109/icme59968.2025.11209313"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209313","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101188257","display_name":"Yongqi Yu","orcid":"https://orcid.org/0009-0005-0674-788X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqi Yu","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102878671","display_name":"Jinxu Zhang","orcid":"https://orcid.org/0009-0000-9876-1454"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxu Zhang","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433723","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-3090-7431"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34182274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9656000137329102,"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":0.9656000137329102,"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/T10028","display_name":"Topic Modeling","score":0.01590000092983246,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.004800000227987766,"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":0.6394000053405762},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.544700026512146},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5099999904632568},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5009999871253967},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.48730000853538513},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4115000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627000212669373},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6394000053405762},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.544700026512146},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4083999991416931},{"id":"https://openalex.org/C2780841128","wikidata":"https://www.wikidata.org/wiki/Q5073781","display_name":"Characterization (materials science)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209313","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2988326850","https://openalex.org/W3120043490","https://openalex.org/W4285255856","https://openalex.org/W4304013646","https://openalex.org/W4385237494","https://openalex.org/W4389519972","https://openalex.org/W4390873989","https://openalex.org/W4393154852","https://openalex.org/W4404782234"],"related_works":[],"abstract_inverted_index":{"Most":[0],"existing":[1],"document":[2,53,67,78],"visual":[3],"question":[4],"answering":[5],"(DocVQA)":[6],"methods":[7],"are":[8],"restricted":[9],"to":[10,16,65,75,87],"single-page":[11],"documents,":[12],"limiting":[13],"their":[14],"applicability":[15],"more":[17],"common":[18],"multi-page":[19,25],"scenarios.":[20],"We":[21],"introduce":[22],"MP-FIRE,":[23],"a":[24,56,62,71,89],"DocVQA":[26],"framework":[27],"that":[28],"integrates":[29],"graph":[30,64],"pruning-based":[31],"reinforcement":[32],"and":[33,69,97,105,115],"cross-modal":[34,90],"agent":[35,91],"ensemble.":[36],"MP-FIRE":[37,60],"overcomes":[38],"the":[39,46,82],"Transformer\u2019s":[40],"inherent":[41],"input":[42],"length":[43],"limitation,":[44],"enabling":[45],"processing":[47],"of":[48,52],"an":[49],"unlimited":[50],"number":[51],"pages":[54],"in":[55],"single":[57],"pass.":[58],"Specifically,":[59],"employs":[61],"topology":[63],"extract":[66],"features":[68],"applies":[70],"two-stage":[72],"pruning":[73],"process":[74],"eliminate":[76],"irrelevant":[77],"elements.":[79],"It":[80],"leverages":[81],"Performance":[83],"Characterization":[84],"Spectrum":[85],"(PCS)":[86],"form":[88],"ensemble,":[92],"thereby":[93],"enhancing":[94],"complementary":[95],"strengths":[96],"improving":[98],"overall":[99],"performance.":[100],"Experimental":[101],"results":[102],"on":[103],"DUDE":[104],"MP-DocVQA":[106],"demonstrate":[107],"MP-FIRE\u2019s":[108],"state-of-the-art":[109],"performance,":[110],"while":[111],"ensuring":[112],"strong":[113],"generalization":[114],"fault":[116],"tolerance.":[117]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}