{"id":"https://openalex.org/W7164855712","doi":"https://doi.org/10.1145/3805622.3810864","title":"MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval","display_name":"MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164855712","doi":"https://doi.org/10.1145/3805622.3810864"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810864","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810864","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810864","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029052244","display_name":"Fengbin Zhu","orcid":"https://orcid.org/0000-0001-6776-2040"},"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":"Fengbin Zhu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6776-2040","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107771839","display_name":"Zijing Cai","orcid":"https://orcid.org/0009-0005-6691-7908"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijing Cai","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-6691-7908","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780553","display_name":"Yuzhe Wang","orcid":"https://orcid.org/0009-0006-3398-8512"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhe Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-2676-6177","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018509620","display_name":"Pengyang Shao","orcid":"https://orcid.org/0000-0003-2838-1987"},"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":"Pengyang Shao","raw_affiliation_strings":["National University of Singapore, Singapore, China"],"raw_orcid":"https://orcid.org/0000-0003-2838-1987","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, China","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368524","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-5199-1428"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-5199-1428","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051925942","display_name":"Fuli Feng","orcid":"https://orcid.org/0000-0002-5828-9842"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuli Feng","raw_affiliation_strings":["University of Science and Technology of China, 0000-0002-5828-9842, China"],"raw_orcid":"https://orcid.org/0000-0002-5828-9842","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, 0000-0002-5828-9842, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5461-3986","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"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":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93969773,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7080000042915344,"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":0.7080000042915344,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.23199999332427979,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.014800000004470348,"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/feature","display_name":"Feature (linguistics)","score":0.5852000117301941},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5777000188827515},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5389999747276306},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4887000024318695},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4837999939918518},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46540001034736633},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.44510000944137573},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.3939000070095062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321999907493591},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5777000188827515},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120000243186951},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4837999939918518},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46540001034736633},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810864","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810864","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810864","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810864","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2997154779","https://openalex.org/W3021397474","https://openalex.org/W3120043490","https://openalex.org/W4297678984","https://openalex.org/W4312233877","https://openalex.org/W4389519972","https://openalex.org/W4390873312","https://openalex.org/W4402716330","https://openalex.org/W4402727764","https://openalex.org/W4404782721","https://openalex.org/W4412888456","https://openalex.org/W4415797729","https://openalex.org/W4416034444","https://openalex.org/W7122563326","https://openalex.org/W7133214597","https://openalex.org/W7133230123"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Document":[1],"Retrieval":[2],"(VDR)":[3],"requires":[4],"representations":[5],"that":[6,75,117,154],"capture":[7],"both":[8],"fine-grained":[9,41],"visual":[10,49,66,101,143,172],"details":[11],"and":[12,31,56,69,80,96,135],"global":[13],"document":[14],"structure":[15],"to":[16,28,86],"ensure":[17],"retrieval":[18,58],"efficacy":[19],"while":[20],"maintaining":[21],"computational":[22],"efficiency.":[23],"Existing":[24],"VDR":[25,151],"models":[26],"struggle":[27],"balance":[29],"effectiveness":[30,97],"efficiency":[32],"when":[33],"processing":[34],"high-resolution":[35],"documents:":[36],"they":[37],"often":[38],"either":[39],"lose":[40],"information":[42],"or":[43],"generate":[44],"an":[45],"excessive":[46],"number":[47],"of":[48,170],"tokens,":[50],"resulting":[51],"in":[52,98],"significant":[53],"indexing":[54],"overhead":[55],"high":[57],"latency.":[59],"In":[60],"this":[61],"work,":[62],"we":[63,110],"rethink":[64],"the":[65,108],"encoding":[67],"mechanism":[68,141],"propose":[70],"a":[71,114,121,137],"new":[72],"X-VisEmb":[73],"paradigm":[74],"progresses":[76],"from":[77],"multi-resolution":[78,123],"sampling":[79],"encoding,":[81],"through":[82],"cross-granularity":[83],"feature":[84,133],"fusion,":[85,134],"adaptive":[87],"representation":[88,128],"distillation.":[89],"A":[90],"preliminary":[91],"study":[92],"validates":[93],"its":[94,171],"feasibility":[95],"capturing":[99],"complementary":[100],"cues":[102],"at":[103],"varying":[104],"scales.":[105],"Building":[106],"on":[107,147],"insights,":[109],"develop":[111],"MURE":[112,156],",":[113],"novel":[115],"framework":[116,157],"employs":[118],"VLMs":[119],"as":[120],"hierarchical":[122,139],"encoder,":[124],"integrates":[125],"resolution-level":[126],"Matryoshka":[127],"learning":[129],"(RMRL)":[130],"for":[131,142],"effective":[132],"applies":[136],"semantic-aware":[138],"clustering":[140],"token":[144,173],"compression.":[145],"Experiments":[146],"two":[148],"widely":[149],"used":[150],"benchmarks":[152],"show":[153],"our":[155],"consistently":[158],"beats":[159],"strong":[160],"baselines.":[161],"Furthermore,":[162],"it":[163],"significantly":[164],"outperforms":[165],"ColPali":[166],"with":[167],"only":[168],"50%":[169],"budget.":[174]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}