{"id":"https://openalex.org/W4411553075","doi":"https://doi.org/10.1145/3733566.3734428","title":"CSD: Cross-Modal Similarity Distillation for Zero-Shot Composed Image Retrieval","display_name":"CSD: Cross-Modal Similarity Distillation for Zero-Shot Composed Image Retrieval","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4411553075","doi":"https://doi.org/10.1145/3733566.3734428"},"language":"en","primary_location":{"id":"doi:10.1145/3733566.3734428","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3733566.3734428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Intelligent Cross-Data Analysis and Retrieval","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/A5100585766","display_name":"Shuping Hui","orcid":null},"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":true,"raw_author_name":"Shuping Hui","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0003-1059-6549","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340979","display_name":"Min Wang","orcid":"https://orcid.org/0000-0003-3048-6980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Wang","raw_affiliation_strings":["Hefei Comprehensive National Science Center, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-3048-6980","affiliations":[{"raw_affiliation_string":"Hefei Comprehensive National Science Center, Hefei, Anhui, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045796157","display_name":"Hui Wu","orcid":"https://orcid.org/0009-0009-2353-3508"},"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":"Hui Wu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0009-2353-3508","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"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":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-1690-9836","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"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":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-3028","affiliations":[{"raw_affiliation_string":"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":["https://openalex.org/A5100585766"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11818963,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7472020387649536},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6451566219329834},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6232613325119019},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6146339178085327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6112838387489319},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5171796083450317},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.515622079372406},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5040661096572876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48428457975387573},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44798946380615234},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34697940945625305},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3342203199863434},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1671757698059082},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.12295621633529663},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0978868305683136}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7472020387649536},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6451566219329834},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6232613325119019},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6146339178085327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6112838387489319},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5171796083450317},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.515622079372406},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5040661096572876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48428457975387573},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44798946380615234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34697940945625305},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3342203199863434},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1671757698059082},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.12295621633529663},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0978868305683136},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3733566.3734428","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3733566.3734428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Intelligent Cross-Data Analysis and Retrieval","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":13,"referenced_works":["https://openalex.org/W2905544595","https://openalex.org/W3026458074","https://openalex.org/W4312825288","https://openalex.org/W4379806362","https://openalex.org/W4386071700","https://openalex.org/W4390203954","https://openalex.org/W4390873539","https://openalex.org/W4393159265","https://openalex.org/W4402727158","https://openalex.org/W4402915471","https://openalex.org/W4403792064","https://openalex.org/W4403792412","https://openalex.org/W4405079042"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Zero-shot":[0],"composed":[1],"image":[2,20],"retrieval":[3],"(CIR)":[4],"aims":[5],"to":[6,30,88],"retrieve":[7],"images":[8,12],"based":[9,117],"on":[10,17,118],"reference":[11],"and":[13,36,75,101,121,129,139],"text":[14],"modifications,":[15],"focusing":[16],"mapping":[18],"an":[19],"into":[21],"a":[22,63],"pseudo-token.":[23],"Existing":[24],"methods":[25],"employ":[26],"contrastive":[27],"instance":[28],"learning":[29],"enforce":[31],"alignment":[32],"between":[33,99,127],"visual":[34,100,128],"features":[35],"corresponding":[37],"mapped":[38,102],"textual":[39,103,130],"representations.":[40,104],"However,":[41],"the":[42,45,59,93,109,140,143],"paradigm":[43],"overlooks":[44],"semantic":[46],"relationships":[47],"among":[48],"samples,":[49],"which":[50,71],"are":[51,137],"crucial":[52],"for":[53],"effective":[54],"feature":[55,94,113],"alignment.":[56],"To":[57],"address":[58],"limitation,":[60],"we":[61,84,122],"propose":[62],"plug-and-play":[64],"approach":[65],"called":[66],"Cross-Modal":[67],"Similarity":[68],"Distillation":[69],"(CSD),":[70],"consists":[72],"of":[73,112,145],"local":[74,81,90],"global":[76,106,110,124],"similarity":[77,82,107,125],"distillation":[78],"components.":[79],"In":[80,105],"distillation,":[83,108],"leverage":[85],"k-NN":[86],"samples":[87],"construct":[89],"structure":[91,111],"within":[92],"space,":[95],"optimizing":[96],"neighborhood":[97],"consistency":[98,126],"space":[114],"is":[115],"modeled":[116],"product":[119],"quantization":[120],"constrain":[123],"modalities.":[131],"Extensive":[132],"experiments":[133],"across":[134],"four":[135],"benchmarks":[136],"conducted":[138],"results":[141],"demonstrate":[142],"superiority":[144],"our":[146],"method.":[147],"The":[148],"source":[149],"code":[150],"will":[151],"be":[152],"made":[153],"publicly":[154],"available.":[155]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}