{"id":"https://openalex.org/W7124910485","doi":"https://doi.org/10.1109/cbmi66578.2025.11339290","title":"ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval","display_name":"ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124910485","doi":"https://doi.org/10.1109/cbmi66578.2025.11339290"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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":null,"display_name":"Guanqi Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Guanqi Zhan","raw_affiliation_strings":["University of Oxford,VGG"],"affiliations":[{"raw_affiliation_string":"University of Oxford,VGG","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuanpei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuanpei Liu","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Han","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Han","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weidi Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["University of Oxford,VGG"],"affiliations":[{"raw_affiliation_string":"University of Oxford,VGG","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":null,"display_name":"Andrew Zisserman","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["University of Oxford,VGG"],"affiliations":[{"raw_affiliation_string":"University of Oxford,VGG","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67164664,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8945000171661377,"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":0.8945000171661377,"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":0.03319999948143959,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.013700000010430813,"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/image-retrieval","display_name":"Image retrieval","score":0.6381999850273132},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6251000165939331},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5302000045776367},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.46549999713897705},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3366999924182892},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.3264000117778778},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.31200000643730164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657999992370605},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6381999850273132},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317999720573425},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3781999945640564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.2685000002384186},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4427552819252014}],"awards":[{"id":"https://openalex.org/G7984080911","display_name":null,"funder_award_id":"VisualAI EP /T028572/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1556531089","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1979931042","https://openalex.org/W2003340926","https://openalex.org/W2023991840","https://openalex.org/W2100398441","https://openalex.org/W2141362318","https://openalex.org/W2552579943","https://openalex.org/W2606473278","https://openalex.org/W2886641317","https://openalex.org/W2894786240","https://openalex.org/W2904347197","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2963467339","https://openalex.org/W2964276596","https://openalex.org/W2982078236","https://openalex.org/W2985524396","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2994818707","https://openalex.org/W3035212740","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3037492894","https://openalex.org/W3090449556","https://openalex.org/W3110042533","https://openalex.org/W3110536152","https://openalex.org/W3117993946","https://openalex.org/W3118694826","https://openalex.org/W3137228985","https://openalex.org/W3168433561","https://openalex.org/W3171668871","https://openalex.org/W3173736705","https://openalex.org/W3175888430","https://openalex.org/W3177343494","https://openalex.org/W3216100300","https://openalex.org/W4247726808","https://openalex.org/W4283394402","https://openalex.org/W4283812943","https://openalex.org/W4312651322","https://openalex.org/W4312761738","https://openalex.org/W4367060669","https://openalex.org/W4386065567","https://openalex.org/W4386071687","https://openalex.org/W4386071847","https://openalex.org/W4386075677","https://openalex.org/W4386083043","https://openalex.org/W4386273457","https://openalex.org/W4390873312","https://openalex.org/W4390873539","https://openalex.org/W4400528838","https://openalex.org/W4402713111","https://openalex.org/W4402727234","https://openalex.org/W4403990736","https://openalex.org/W4404545360","https://openalex.org/W4413156992","https://openalex.org/W4413157159","https://openalex.org/W4415795285"],"related_works":[],"abstract_inverted_index":{"The":[0,40,110],"objective":[1],"in":[2],"this":[3,14],"paper":[4],"is":[5],"to":[6,56,63,74,99,107,134,136],"improve":[7],"the":[8,24,47,65,75,84,101,105],"per-formance":[9],"of":[10,26,60,104],"text-to-image":[11,38,118],"retrieval.":[12],"To":[13],"end,":[15],"we":[16,87],"introduce":[17],"a":[18,51,58],"new":[19,91],"framework":[20],"that":[21,32,113],"can":[22,34,70],"boost":[23],"performance":[25,120],"large-scale":[27],"pre-trained":[28],"vision-language":[29],"models,":[30],"so":[31],"they":[33],"be":[35,72],"used":[36,77],"for":[37],"re-ranking.":[39],"approach,":[41],"Enhanced":[42],"Language-Image":[43],"Pre-training":[44],"(ELIP),":[45],"uses":[46],"text":[48],"query,":[49],"via":[50],"simple":[52],"MLP":[53],"mapping":[54],"network,":[55],"predict":[57],"set":[59,88],"visual":[61],"prompts":[62],"condition":[64],"ViT":[66],"image":[67],"encoding.":[68],"ELIP":[69,114],"easily":[71],"applied":[73],"commonly":[76],"CLIP,":[78],"SigLIP":[79],"and":[80,97,121],"BLIP-2":[81,123],"networks.":[82],"On":[83],"evaluation":[85],"side,":[86],"up":[89],"two":[90],"out-of-distribution":[92],"(OOD)":[93],"benchmarks,":[94,126],"Occluded":[95],"COCO":[96],"ImageNet-R,":[98],"assess":[100],"zero-shot":[102],"generalisation":[103],"models":[106],"different":[108],"domains.":[109],"results":[111],"demonstrate":[112],"significantly":[115],"boosts":[116],"CLIP/SigLIP/SigLIP-2":[117],"retrieval":[119],"outperforms":[122],"on":[124],"several":[125],"as":[127,129],"well":[128],"providing":[130],"an":[131],"easy":[132],"means":[133],"adapt":[135],"OOD":[137],"datasets.":[138]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-10T00:00:00"}