{"id":"https://openalex.org/W4415537808","doi":"https://doi.org/10.1145/3746027.3755357","title":"DREAM: Integrating Hierarchical Multimodal Retrieval with Multi-page Multimodal Language Model for Documents VQA","display_name":"DREAM: Integrating Hierarchical Multimodal Retrieval with Multi-page Multimodal Language Model for Documents VQA","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537808","doi":"https://doi.org/10.1145/3746027.3755357"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755357","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"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/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":true,"raw_author_name":"Jinxu Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiyuan Fan","orcid":"https://orcid.org/0009-0008-7107-9795"},"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":"Qiyuan Fan","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","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"],"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"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102878671"],"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":0.15999491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4213","last_page":"4221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5672000050544739},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.557200014591217},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.512499988079071},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4731000065803528},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.42730000615119934},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4185999929904938},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4047999978065491}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384000062942505},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6029999852180481},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5672000050544739},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5284000039100647},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5164999961853027},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4047999978065491},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755357","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5843395088","display_name":null,"funder_award_id":"62476066, 62277002","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2144211451","https://openalex.org/W2997154779","https://openalex.org/W3120043490","https://openalex.org/W4304013646","https://openalex.org/W4312233877","https://openalex.org/W4385237494","https://openalex.org/W4390873989","https://openalex.org/W4403791048","https://openalex.org/W4405595839","https://openalex.org/W6931636349"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"the":[1,30,69,81,108,114,117,121,126,130],"content":[2],"of":[3,32,71,85,116,129],"multi-page":[4,33,99,134,144],"documents":[5,34,100],"with":[6],"rich":[7],"layout":[8],"information":[9],"is":[10],"a":[11,41,53,63,91,140],"challenging":[12],"task.":[13],"Recent":[14],"multimodal":[15,57,75,95,131],"large":[16],"language":[17,96],"models":[18],"(MLLMs)":[19],"have":[20],"made":[21],"remarkable":[22],"progress":[23],"in":[24,133],"understanding":[25,31],"single-page":[26],"document":[27,86,135,145,149],"images.":[28,87],"However,":[29],"remains":[35],"insufficiently":[36],"explored.":[37],"This":[38],"work":[39],"proposes":[40],"Document":[42],"Retrieval-enhanced,":[43],"Expert-guided,":[44],"Attention-aware":[45],"Multimodal":[46],"Framework,":[47],"dubbed":[48],"DREAM.":[49],"Specifically,":[50],"we":[51,61,89],"propose":[52,62],"confidence-based,":[54],"high-level":[55],"semantic,":[56],"retrieval":[58,73,78,118],"method.":[59],"Then,":[60],"machine":[64],"learning":[65],"algorithm":[66],"to":[67,79,101],"complement":[68],"result":[70],"confidence-based":[72],"and":[74,106,147],"embedding":[76],"similarity":[77],"obtain":[80],"most":[82],"query-relevant":[83],"set":[84],"Subsequently,":[88],"designed":[90],"decoupled":[92],"cross-page":[93,148],"attention-aware":[94],"model":[97,132],"for":[98,143],"interpret":[102],"these":[103],"retrieved":[104],"images":[105],"produce":[107],"final":[109],"answer.":[110],"Experimental":[111],"results":[112],"demonstrate":[113],"effectiveness":[115],"module":[119],"within":[120],"framework,":[122],"as":[123,125],"well":[124],"robust":[127],"performance":[128],"comprehension.":[136],"These":[137],"findings":[138],"offer":[139],"compelling":[141],"solution":[142],"comprehension":[146],"visual":[150],"question":[151],"answering.":[152]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}