{"id":"https://openalex.org/W4402979975","doi":"https://doi.org/10.1109/icme57554.2024.10687730","title":"ClipComb: Global-Local Composition Network based on CLIP for Composed Image Retrieval","display_name":"ClipComb: Global-Local Composition Network based on CLIP for Composed Image Retrieval","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979975","doi":"https://doi.org/10.1109/icme57554.2024.10687730"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101719228","display_name":"Yingying Zhu","orcid":"https://orcid.org/0000-0002-5366-974X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yingying Zhu","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028455716","display_name":"Dafeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dafeng Li","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101890300","display_name":"Zhihang Liu","orcid":"https://orcid.org/0009-0000-6281-418X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihang Liu","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112878209","display_name":"Hong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhou","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101719228"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54283579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9973999857902527,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9973999857902527,"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":0.9782999753952026,"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":0.7225677371025085},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.668361485004425},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.571255624294281},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.49623948335647583},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4397992789745331},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43816977739334106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4042118191719055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225677371025085},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.668361485004425},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.571255624294281},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49623948335647583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4397992789745331},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43816977739334106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4042118191719055},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326279","display_name":"Department of Education of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2798951647","https://openalex.org/W2905544595","https://openalex.org/W3025297341","https://openalex.org/W3176909828","https://openalex.org/W4214926101","https://openalex.org/W4385486155","https://openalex.org/W6631190155","https://openalex.org/W6631694491","https://openalex.org/W6720467090","https://openalex.org/W6739901393","https://openalex.org/W6750141061","https://openalex.org/W6751039726","https://openalex.org/W6755207826","https://openalex.org/W6756026235","https://openalex.org/W6763623397","https://openalex.org/W6776944941","https://openalex.org/W6791353385","https://openalex.org/W6797148833","https://openalex.org/W6810496820","https://openalex.org/W6841169458","https://openalex.org/W6852075244"],"related_works":["https://openalex.org/W2396760013","https://openalex.org/W45217788","https://openalex.org/W1986902711","https://openalex.org/W2655467144","https://openalex.org/W2171776552","https://openalex.org/W2148433556","https://openalex.org/W98391849","https://openalex.org/W1600907701","https://openalex.org/W2062250142","https://openalex.org/W53120221"],"abstract_inverted_index":{"In":[0],"this":[1,73],"paper,":[2],"we":[3,21,58,93],"focus":[4],"on":[5,30,81,101,138],"the":[6,31,43,48,54,60,66,89,102,114,125],"task":[7],"of":[8,17,40,65,113],"composed":[9],"image":[10,18,63],"retrieval.":[11],"To":[12],"develop":[13],"a":[14,23,95,120],"comprehensive":[15],"understanding":[16],"and":[19,47,62,84],"text,":[20],"propose":[22],"novel":[24],"global-local":[25,96],"composition":[26,49,90,97,104],"network":[27],"(ClipComb)":[28],"based":[29,100],"vision-language":[32],"pretraining":[33,116],"CLIP":[34,67,71],"model.":[35],"The":[36,107],"two":[37,139],"main":[38],"phases":[39],"ClipComb":[41],"are":[42],"fine-tuning":[44,55],"training":[45,50,56,91],"stage":[46],"stage.":[51],"First,":[52],"in":[53],"step,":[57],"fine-tune":[59],"text":[61],"encoders":[64],"model":[68],"to":[69,72,118],"transfer":[70],"task.":[74],"We":[75],"also":[76],"perform":[77],"contrastive":[78],"loss":[79],"alignment":[80],"both":[82],"global":[83],"local":[85],"features.":[86],"Second,":[87],"during":[88],"phase,":[92],"devise":[94],"module":[98,109],"(GLC)":[99],"fine-tuned":[103],"learning":[105],"framework.":[106],"GLC":[108],"make":[110],"full":[111],"use":[112],"CLIP\u2019s":[115],"knowledge":[117],"generate":[119],"composite":[121],"representation":[122],"aligned":[123],"with":[124],"target":[126],"representation.":[127],"Extensive":[128],"experimental":[129],"results":[130],"demonstrate":[131],"that":[132],"our":[133],"method":[134],"achieves":[135],"state-of-the-art":[136],"performance":[137],"benchmark":[140],"datasets.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}