{"id":"https://openalex.org/W4414977866","doi":"https://doi.org/10.1145/3746027.3755765","title":"CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval","display_name":"CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4414977866","doi":"https://doi.org/10.1145/3746027.3755765"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755765","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755765","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bin Kang","orcid":"https://orcid.org/0009-0002-5587-6221"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Kang","raw_affiliation_strings":["Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5587-6221","affiliations":[{"raw_affiliation_string":"Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427335","display_name":"Bin Chen","orcid":"https://orcid.org/0000-0002-3979-021X"},"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":"Bin Chen","raw_affiliation_strings":["International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3979-021X","affiliations":[{"raw_affiliation_string":"International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junjie Wang","orcid":"https://orcid.org/0009-0001-6065-8045"},"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"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China","Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-6065-8045","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yulin Li","orcid":"https://orcid.org/0009-0007-1140-3066"},"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":"Yulin Li","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-1140-3066","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102200936","display_name":"Junzhi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhi Zhao","raw_affiliation_strings":["Southwest Jiaotong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0007-0261-6596","affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junle Wang","orcid":"https://orcid.org/0000-0002-9096-2670"},"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"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junle Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China","Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9096-2670","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038086218","display_name":"Zhuotao Tian","orcid":"https://orcid.org/0000-0003-2698-6923"},"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":"Zhuotao Tian","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2698-6923","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2346158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5140","last_page":"5149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955000281333923,"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/discriminative-model","display_name":"Discriminative model","score":0.9459999799728394},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6406999826431274},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5181999802589417},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47209998965263367},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4205999970436096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4092999994754791},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9459999799728394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494000196456909},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6406999826431274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6297000050544739},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5181999802589417},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4205999970436096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3693000078201294},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.266400009393692}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755765","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.05586","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.05586","pdf_url":"https://arxiv.org/pdf/2510.05586","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755765","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1219369694","display_name":null,"funder_award_id":"JCYJ20240813105901003, KJZD20240903102901003","funder_id":"https://openalex.org/F4320336569","funder_display_name":"Shenzhen Science and Technology Innovation Program"}],"funders":[{"id":"https://openalex.org/F4320336569","display_name":"Shenzhen Science and Technology Innovation Program","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"Visual":[1,61],"Language":[2],"Models":[3],"(VLMs)":[4],"suffer":[5],"structural":[6],"limitations":[7],"where":[8],"a":[9,40],"few":[10],"low":[11,71],"contribution":[12],"tokens":[13,78],"may":[14],"excessively":[15],"capture":[16],"global":[17],"semantics,":[18],"dominating":[19],"the":[20,26,46,54,59,84,89,104,109,117,124,144],"information":[21,72],"aggregation":[22],"process":[23],"and":[24,70,79,100,115],"suppressing":[25],"discriminative":[27,101,120],"features":[28,67],"in":[29,53],"text-driven":[30],"image":[31,140],"retrieval":[32,141],"tasks.":[33],"To":[34],"address":[35],"this,":[36],"we":[37,57,87],"introduce":[38,88],"\\textbf{CalibCLIP},":[39],"training-free":[41],"method":[42],"designed":[43],"to":[44,96],"calibrate":[45],"suppressive":[47],"effect":[48],"of":[49,119,146],"dominant":[50,77],"tokens.":[51],"Specifically,":[52],"visual":[55,66],"space,":[56,86],"propose":[58],"Contrastive":[60],"Enhancer":[62],"(CVE),":[63],"which":[64,94],"decouples":[65],"into":[68],"target":[69],"regions.":[73],"Subsequently,":[74],"it":[75],"identifies":[76],"dynamically":[80],"suppresses":[81],"their":[82],"representations.In":[83],"textual":[85],"Discriminative":[90],"Concept":[91],"Calibrator":[92],"(DCC),":[93],"aims":[95],"differentiate":[97],"between":[98],"general":[99],"concepts":[102,114],"within":[103],"text":[105],"query.":[106],"By":[107],"mitigating":[108],"challenges":[110],"posed":[111],"by":[112],"generic":[113],"improving":[116],"representations":[118],"concepts,":[121],"DCC":[122],"strengthens":[123],"differentiation":[125],"among":[126],"similar":[127],"samples.":[128],"Finally,":[129],"extensive":[130],"experiments":[131],"demonstrate":[132],"consistent":[133],"improvements":[134],"across":[135],"seven":[136],"benchmarks":[137],"spanning":[138],"three":[139],"tasks,":[142],"underscoring":[143],"effectiveness":[145],"CalibCLIP.":[147],"Code":[148],"is":[149],"available":[150],"at:":[151],"https://github.com/kangbin98/CalibCLIP":[152]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}