{"id":"https://openalex.org/W4402981520","doi":"https://doi.org/10.1109/icme57554.2024.10687694","title":"Distinguishing Visually Similar Images: Triplet Contrastive Learning Framework for Image-text Retrieval","display_name":"Distinguishing Visually Similar Images: Triplet Contrastive Learning Framework for Image-text Retrieval","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981520","doi":"https://doi.org/10.1109/icme57554.2024.10687694"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687694","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687694","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/A5021417967","display_name":"Pengxiang Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengxiang Ouyang","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science & Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science & Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701920","display_name":"Jianan Chen","orcid":"https://orcid.org/0000-0002-6673-6884"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianan Chen","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science & Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science & Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101571340","display_name":"Qing Ma","orcid":"https://orcid.org/0000-0003-1749-9509"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Ma","raw_affiliation_strings":["Zhejiang University of Technology,College of Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Science,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401139","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0003-0758-2202"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science & Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science & Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013768600","display_name":"Cong Bai","orcid":"https://orcid.org/0000-0002-6177-3862"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Bai","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science & Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science & Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021417967"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16566396,"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":"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":0.991599977016449,"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":0.991599977016449,"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":0.9341999888420105,"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":0.7879959344863892},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6695104241371155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6288691759109497},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5628883242607117},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5036396384239197},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.44101274013519287},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4197938144207001},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40009772777557373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879959344863892},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6695104241371155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6288691759109497},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5628883242607117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5036396384239197},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.44101274013519287},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4197938144207001},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40009772777557373}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687694","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687694","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2071180033","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2147874738","https://openalex.org/W155590726","https://openalex.org/W2036058638"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"contrastive":[3],"learning":[4,103],"techniques,":[5],"particularly":[6],"InfoNCE":[7],"loss,":[8,52],"have":[9],"propelled":[10],"advancements":[11],"in":[12,131],"image-text":[13,18,62,106],"alignment.":[14],"However,":[15],"aligning":[16],"indistinguishable":[17],"pairs":[19],"remains":[20],"a":[21,75],"challenge":[22],"for":[23,85,101],"conventional":[24],"methods,":[25],"often":[26],"overlooking":[27],"semantically":[28],"similar":[29,86],"content.":[30],"To":[31],"overcome":[32],"these":[33],"limitations,":[34],"we":[35,65],"introduce":[36],"the":[37,46,67,125],"Triplet":[38],"Contrast":[39,49],"Learning":[40],"Framework":[41],"(TCLF).":[42],"Accompanying":[43],"TCLF":[44,100],"is":[45],"Stricter":[47],"Noise":[48],"Estimation":[50],"(SNCE)":[51],"designed":[53],"to":[54,73,119],"minimize":[55],"mutual":[56,69],"information":[57,70],"between":[58],"positive":[59],"and":[60,81,94,97,112,129],"negative":[61],"pairs.":[63,107],"Additionally,":[64],"propose":[66],"intra-modal":[68],"(IMI)":[71],"loss":[72],"encourage":[74],"uniform":[76],"distribution":[77],"of":[78,127],"image":[79,92],"features":[80],"enhance":[82],"discriminative":[83],"capacity":[84],"images.":[87],"SNCE":[88,96,128],"aligns":[89],"two":[90],"enhanced":[91],"versions,":[93],"collectively,":[95],"IMI":[98,130],"empower":[99],"effective":[102],"with":[104],"challenging":[105],"Experimental":[108],"evaluations":[109],"on":[110],"MSCOCO":[111],"Flickr30K":[113],"datasets":[114],"demonstrate":[115],"superior":[116],"performance":[117],"compared":[118],"state-of-the-art":[120],"methods.":[121],"Ablation":[122],"studies":[123],"confirm":[124],"efficacy":[126],"overcoming":[132],"identified":[133],"challenges.":[134]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}