{"id":"https://openalex.org/W4403791707","doi":"https://doi.org/10.1145/3664647.3681493","title":"Semantic Distillation from Neighborhood for Composed Image Retrieval","display_name":"Semantic Distillation from Neighborhood for Composed Image Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791707","doi":"https://doi.org/10.1145/3664647.3681493"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681493","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681493","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681493","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100398570","display_name":"Yifan Wang","orcid":"https://orcid.org/0000-0002-6719-5063"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifan Wang","raw_affiliation_strings":["Tsinghua Shenzhen International School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062743125","display_name":"Wuliang Huang","orcid":"https://orcid.org/0000-0002-6378-2498"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wuliang Huang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440317","display_name":"Lei Li","orcid":"https://orcid.org/0000-0002-4514-3617"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["Tsinghua Shenzhen International School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101456902","display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Tsinghua Shenzhen International School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100398570"],"corresponding_institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.7339,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72746805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5575","last_page":"5583"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8096016645431519},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6995818018913269},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6593925356864929},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6166263222694397},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5785692930221558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4432600736618042},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3240843415260315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8096016645431519},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6995818018913269},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6593925356864929},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6166263222694397},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5785692930221558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4432600736618042},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3240843415260315},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681493","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681493","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681493","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681493","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2905544595","https://openalex.org/W3026458074","https://openalex.org/W3035454331","https://openalex.org/W3099206234","https://openalex.org/W3102564565","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3175933895","https://openalex.org/W3176909828","https://openalex.org/W4285412251","https://openalex.org/W4287755032","https://openalex.org/W4289328742","https://openalex.org/W4292828970","https://openalex.org/W4297690113","https://openalex.org/W4304091775","https://openalex.org/W4312645695","https://openalex.org/W4312924260","https://openalex.org/W4312939067","https://openalex.org/W4312940158","https://openalex.org/W4312943450","https://openalex.org/W4366996284","https://openalex.org/W4384641262","https://openalex.org/W4385486155","https://openalex.org/W4385934203","https://openalex.org/W4386038408","https://openalex.org/W4386501573","https://openalex.org/W4387424307","https://openalex.org/W4387969591","https://openalex.org/W4390871692","https://openalex.org/W4390879096","https://openalex.org/W4391454577","https://openalex.org/W4393149552","https://openalex.org/W4393149559","https://openalex.org/W4394564353","https://openalex.org/W4394625619"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2768175398","https://openalex.org/W1986902711","https://openalex.org/W2396760013","https://openalex.org/W2148433556","https://openalex.org/W2655467144","https://openalex.org/W2171776552","https://openalex.org/W98391849","https://openalex.org/W1600907701","https://openalex.org/W2726741344"],"abstract_inverted_index":{"The":[0],"challenging":[1],"task":[2],"composed":[3,99],"image":[4,11,19,100],"retrieval":[5],"targets":[6],"at":[7],"identifying":[8],"the":[9,13,31,36,42,46,62,73,77,84,104,112,127,131,137,154,161,164,168,172,176,183,186,200],"matched":[10],"from":[12,35,95,111,157,204],"multi-modal":[14],"query":[15,33,37,48,63,117,128,184],"with":[16,122],"a":[17,21,89],"reference":[18],"and":[20,39,50,68,79,118,146,167,182,191,196],"textual":[22],"modifier.":[23],"Most":[24],"existing":[25],"methods":[26],"are":[27,54,134],"devoted":[28],"to":[29,72,125],"composing":[30],"unified":[32],"representations":[34,49,53],"images":[38],"texts,":[40],"yet":[41],"distribution":[43,105],"gaps":[44],"between":[45,179],"hybrid-modal":[47],"visual":[51],"target":[52,59,113],"neglected.":[55],"However,":[56],"directly":[57],"incorporating":[58],"features":[60,121,159],"on":[61,175,194],"may":[64],"cause":[65],"ambiguous":[66],"rankings":[67],"poor":[69],"robustness":[70],"due":[71],"insufficient":[74],"exploration":[75],"of":[76,139,163],"distinguishments":[78],"overfitting":[80],"issues.":[81],"To":[82],"address":[83],"above":[85],"concerns,":[86],"we":[87,107],"propose":[88],"novel":[90],"framework":[91],"termed":[92],"SemAntic":[93],"Distillation":[94],"Neighborhood":[96],"(SADN)":[97],"for":[98,115,152],"retrieval.":[101],"For":[102],"mitigating":[103],"divergences,":[106],"construct":[108],"neighborhood":[109,120,205],"sampling":[110],"domain":[114],"each":[116],"aggregate":[119],"adaptive":[123,132],"weights":[124,133,173],"restructure":[126],"representations.":[129],"Specifically,":[130],"determined":[135],"by":[136],"collaboration":[138],"two":[140],"individual":[141],"modules,":[142],"as":[143],"correspondence-induced":[144],"adaption":[145,150],"divergence-based":[147,169],"correction.":[148],"Correspondence-induced":[149],"accounts":[151],"capturing":[153],"correlation":[155],"alignments":[156],"neighbor":[158],"under":[160],"guidance":[162],"positive":[165],"representations,":[166],"correction":[170],"regulates":[171],"based":[174],"embedding":[177],"distances":[178],"hard":[180],"negatives":[181],"in":[185],"latent":[187],"space.":[188],"Extensive":[189],"results":[190],"ablation":[192],"studies":[193],"CIRR":[195],"FashionIQ":[197],"validate":[198],"that":[199],"proposed":[201],"semantic":[202],"distillation":[203],"significantly":[206],"outperforms":[207],"baseline":[208],"methods.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}