{"id":"https://openalex.org/W4415524320","doi":"https://doi.org/10.1109/mlsp62443.2025.11204231","title":"Colflor: Towards Bert-Size Vision-Language Document Retrieval Models","display_name":"Colflor: Towards Bert-Size Vision-Language Document Retrieval Models","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524320","doi":"https://doi.org/10.1109/mlsp62443.2025.11204231"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5054102478","display_name":"Ahmed Masry","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ahmed Masry","raw_affiliation_strings":["York University,Department of Electrical Engineering and Computer Science,Toronto,Canada"],"affiliations":[{"raw_affiliation_string":"York University,Department of Electrical Engineering and Computer Science,Toronto,Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111148229","display_name":"Enamul Hoque","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Enamul Hoque","raw_affiliation_strings":["York University,Department of Electrical Engineering and Computer Science,Toronto,Canada"],"affiliations":[{"raw_affiliation_string":"York University,Department of Electrical Engineering and Computer Science,Toronto,Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054102478"],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":5.6662,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96130175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9775000214576721,"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":0.9775000214576721,"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":0.9035999774932861,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9009000062942505,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/document-retrieval","display_name":"Document retrieval","score":0.7184000015258789},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5351999998092651},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5116999745368958},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.47540000081062317},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.461899995803833},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4523000121116638},{"id":"https://openalex.org/keywords/infographic","display_name":"Infographic","score":0.4359999895095825},{"id":"https://openalex.org/keywords/data-retrieval","display_name":"Data retrieval","score":0.3970000147819519},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.3944000005722046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840399980545044},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.7184000015258789},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7027000188827515},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.47540000081062317},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.461899995803833},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4523000121116638},{"id":"https://openalex.org/C156365220","wikidata":"https://www.wikidata.org/wiki/Q845734","display_name":"Infographic","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.3068999946117401},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C2278759","wikidata":"https://www.wikidata.org/wiki/Q831677","display_name":"Document management system","level":2,"score":0.2502000033855438},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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":12,"referenced_works":["https://openalex.org/W2970641574","https://openalex.org/W3021397474","https://openalex.org/W3034999214","https://openalex.org/W3120043490","https://openalex.org/W4213213306","https://openalex.org/W4285255856","https://openalex.org/W4297678984","https://openalex.org/W4312881242","https://openalex.org/W4386576685","https://openalex.org/W4390873312","https://openalex.org/W4402660140","https://openalex.org/W4402671151"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"document":[1,73,121],"retrieval":[2,39,74,122],"systems":[3,123],"for":[4,59,126],"PDFs,":[5],"charts,":[6],"and":[7,27,57,112,129],"infographics":[8],"rely":[9],"heavily":[10],"on":[11,87],"Optical":[12],"Character":[13],"Recognition":[14],"(OCR)":[15],"pipelines":[16],"to":[17,85,132],"extract":[18],"textual":[19],"content,":[20],"a":[21,93],"process":[22],"that":[23],"is":[24],"both":[25],"error-prone":[26],"resource-intensive.":[28],"Recent":[29],"advancements":[30],"in":[31,96,106],"multimodal":[32],"models":[33],"like":[34],"ColPali":[35,86],"have":[36],"enabled":[37],"OCRfree":[38],"by":[40,99],"processing":[41],"documents":[42],"directly":[43],"as":[44],"images,":[45],"but":[46],"their":[47],"large":[48],"size":[49],"(three":[50],"billion":[51],"parameters)":[52],"makes":[53,119],"them":[54],"computationally":[55],"expensive":[56],"impractical":[58],"large-scale":[60,127],"applications.":[61],"To":[62],"address":[63],"this":[64],"limitation,":[65],"we":[66],"introduce":[67],"ColFlor,":[68],"an":[69],"efficient":[70],"OCR-free":[71,120],"visual":[72],"model":[75],"with":[76,91,134],"only":[77,92],"174":[78],"million":[79],"parameters.":[80],"ColFlor":[81],"achieves":[82],"comparable":[83],"performance":[84,97],"text-rich":[88],"English":[89],"documents,":[90],"1.8%":[94],"decrease":[95],"(measured":[98],"NDCG@5":[100],"metric),":[101],"while":[102],"being":[103],"significantly":[104],"faster":[105],"image":[107],"encoding":[108,114],"(5.25":[109],"times":[110,116],"faster)":[111],"query":[113],"(9.8":[115],"faster).":[117],"This":[118],"more":[124,130],"cost-effective":[125],"applications":[128],"accessible":[131],"users":[133],"limited":[135],"computational":[136],"resources.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}