{"id":"https://openalex.org/W7164836612","doi":"https://doi.org/10.1145/3805622.3810802","title":"Mitigating Semantic Bias in Multilingual Visual Document Retrieval via Language-Vision-Aware Late Interaction","display_name":"Mitigating Semantic Bias in Multilingual Visual Document Retrieval via Language-Vision-Aware Late Interaction","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164836612","doi":"https://doi.org/10.1145/3805622.3810802"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810802","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/10.1145/3805622.3810802","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138653277","display_name":"Haowei Li","orcid":"https://orcid.org/0009-0008-5588-8015"},"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":"Haowei Li","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0008-5588-8015","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102522945","display_name":"Haojie Wu","orcid":"https://orcid.org/0009-0002-1848-4245"},"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":"Haojie Wu","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0002-1848-4245","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138663895","display_name":"Jie Bao","orcid":"https://orcid.org/0009-0001-5129-3945"},"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":"Jie Bao","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0001-5129-3945","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101471727","display_name":"Zhen Chen","orcid":"https://orcid.org/0009-0002-2151-7028"},"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":"Zhen Chen","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0002-2151-7028","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051983841","display_name":"Yong Liao","orcid":"https://orcid.org/0000-0001-6403-0557"},"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":"Yong Liao","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-6403-0557","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.93733331,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.910099983215332,"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":0.910099983215332,"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":0.05770000070333481,"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":0.005900000222027302,"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/security-token","display_name":"Security token","score":0.6694999933242798},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6096000075340271},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5612999796867371},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5288000106811523},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5210999846458435},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.47380000352859497},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.46810001134872437},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.46709999442100525},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4366999864578247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749999761581421},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6694999933242798},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6096000075340271},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5370000004768372},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5210999846458435},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.46810001134872437},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46560001373291016},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4366999864578247},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.385699987411499},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3100999891757965},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810802","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:10.1145/3805622.3810802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810802","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":[{"score":0.7146477699279785,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W2963526661","https://openalex.org/W3021397474","https://openalex.org/W3035390927","https://openalex.org/W3213148312","https://openalex.org/W4372266552","https://openalex.org/W4382202677","https://openalex.org/W4385572320","https://openalex.org/W4385573236","https://openalex.org/W4402670856","https://openalex.org/W4404782721","https://openalex.org/W4411403346","https://openalex.org/W4412376954","https://openalex.org/W4412944915","https://openalex.org/W4416034444","https://openalex.org/W4416036201"],"related_works":[],"abstract_inverted_index":{"Multilingual":[0],"Visual":[1],"Document":[2],"Retrieval":[3],"(VDR)":[4],"aims":[5],"to":[6,56,131,154],"retrieve":[7],"relevant":[8],"document":[9,139],"screenshots":[10],"given":[11],"a":[12,89,104,119],"textual":[13],"query":[14,58],"across":[15,77],"different":[16],"languages.":[17,78],"Recent":[18],"late-interaction":[19],"VDR":[20,161],"models":[21],"estimate":[22],"relevance":[23,75],"via":[24],"token-level":[25,111,175],"maximum":[26],"similarity":[27,135,147],"aggregation":[28],"(MaxSim),":[29],"but":[30],"this":[31],"heuristic":[32],"can":[33,54],"introduce":[34],"semantic":[35],"bias":[36],"in":[37,69,137,166],"multilingual":[38,160],"settings.":[39],"In":[40],"particular,":[41],"linguistic":[42],"differences":[43],"such":[44,65],"as":[45],"morphological":[46],"variation,":[47],"functional":[48],"word":[49],"distribution,":[50],"and":[51,73,117,168],"tokenization":[52],"granularity":[53],"lead":[55],"heterogeneous":[57],"token":[59,71,106],"representations.":[60],"When":[61],"aggregated":[62],"under":[63],"MaxSim,":[64],"heterogeneity":[66],"may":[67],"result":[68],"disproportionate":[70],"contributions":[72,112],"inconsistent":[74],"estimation":[76],"To":[79],"address":[80],"these":[81],"limitations,":[82],"we":[83],"propose":[84],"Language-Vision-Aware":[85],"Late":[86],"Interaction":[87],"(LVALI),":[88],"lightweight":[90,174],"calibration":[91,176],"framework":[92],"without":[93],"modifying":[94],"the":[95,114,132,138,145],"original":[96],"embeddings.":[97],"LVALI":[98],"introduces":[99],"two":[100],"complementary":[101],"mechanisms:":[102],"(1)":[103],"language-aware":[105],"weighting":[107],"scheme":[108],"that":[109,125],"calibrates":[110],"at":[113],"vocabulary":[115],"level,":[116],"(2)":[118],"visual":[120],"alignment":[121],"stability-based":[122],"correction":[123],"term":[124],"downweights":[126],"low-confidence":[127],"token-patch":[128],"matches":[129],"according":[130],"dispersion":[133],"of":[134,149],"distributions":[136],"image":[140],"space.":[141],"This":[142],"design":[143],"preserves":[144],"underlying":[146],"structure":[148],"MaxSim":[150],"while":[151],"improving":[152],"robustness":[153,167],"cross-lingual":[155,169],"variability.":[156],"Experiments":[157],"on":[158],"multiple":[159],"benchmarks":[162],"demonstrate":[163],"consistent":[164],"improvements":[165],"consistency,":[170],"achieved":[171],"with":[172],"only":[173],"training.":[177]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}