{"id":"https://openalex.org/W4285138127","doi":"https://doi.org/10.1109/lsp.2022.3178899","title":"Regularizing Visual Semantic Embedding With Contrastive Learning for Image-Text Matching","display_name":"Regularizing Visual Semantic Embedding With Contrastive Learning for Image-Text Matching","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285138127","doi":"https://doi.org/10.1109/lsp.2022.3178899"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3178899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3178899","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101810463","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-5159-5954"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-5159-5954","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410326","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-7498-6541"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Key Labotatory of Machine Perception, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7498-6541","affiliations":[{"raw_affiliation_string":"Key Labotatory of Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046380673","display_name":"Huaqiu Wang","orcid":"https://orcid.org/0000-0002-6789-6775"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaqiu Wang","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100705472","display_name":"Mengyuan Liu","orcid":"https://orcid.org/0000-0002-6332-8316"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyuan Liu","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6332-8316","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3353,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.89804436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1332","last_page":"1336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9969000220298767,"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":0.9968000054359436,"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/embedding","display_name":"Embedding","score":0.8254604339599609},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868844270706177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.663010835647583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5913377404212952},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.536088764667511},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5319647789001465},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4488796889781952},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.4341365694999695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38595670461654663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10254499316215515}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8254604339599609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868844270706177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.663010835647583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5913377404212952},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.536088764667511},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5319647789001465},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4488796889781952},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.4341365694999695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38595670461654663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10254499316215515},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2022.3178899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3178899","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W639708223","https://openalex.org/W1527575280","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2138621090","https://openalex.org/W2157331557","https://openalex.org/W2187089797","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2343257424","https://openalex.org/W2745461083","https://openalex.org/W2798991696","https://openalex.org/W2962964995","https://openalex.org/W2965848243","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W3035454331","https://openalex.org/W3035524453","https://openalex.org/W3035552787","https://openalex.org/W3040948901","https://openalex.org/W3110042533","https://openalex.org/W3137191861","https://openalex.org/W3156636935","https://openalex.org/W3171007011","https://openalex.org/W3173220247","https://openalex.org/W3175888430","https://openalex.org/W3196281958","https://openalex.org/W6631516269","https://openalex.org/W6678470764","https://openalex.org/W6747225742","https://openalex.org/W6754278344","https://openalex.org/W6774314701"],"related_works":["https://openalex.org/W2312145515","https://openalex.org/W1986106996","https://openalex.org/W2315716767","https://openalex.org/W2374902383","https://openalex.org/W4387489691","https://openalex.org/W2375695570","https://openalex.org/W4285012873","https://openalex.org/W2139549667","https://openalex.org/W2355975607","https://openalex.org/W2792318346"],"abstract_inverted_index":{"Learning":[0],"visual":[1,46,71,121,142],"semantic":[2,23,34,47,54,72,81,95,122,143],"embedding":[3,48,73],"for":[4],"image-text":[5,18,29,103],"matching":[6],"has":[7],"achieved":[8],"high":[9],"success":[10],"by":[11,83,97,140],"using":[12],"triplet":[13,100],"loss":[14,101],"to":[15,26,115],"pull":[16],"positive":[17],"pairs":[19,30,91],"which":[20,31,78],"share":[21,32],"similar":[22,57,61],"meaning":[24],"and":[25,92,130,146,152],"push":[27],"negative":[28],"different":[33],"meaning.":[35],"Without":[36],"modeling":[37],"constraints":[38],"from":[39,86],"image-image":[40,88],"or":[41,59],"text-text":[42],"pairs,":[43],"the":[44,51,106,113,134],"generated":[45],"inevitably":[49],"faces":[50],"problem":[52],"of":[53,108,136],"misalignments":[55],"among":[56,60],"images":[58],"texts.":[62],"To":[63,105],"solve":[64],"this":[65],"problem,":[66],"we":[67,111],"present":[68],"a":[69],"contrastive":[70,84,118],"framework,":[74],"named":[75],"as":[76],"ConVSE,":[77],"achieves":[79,93],"intra-modal":[80],"alignment":[82,96],"learning":[85,119],"augmented":[87],"(or":[89],"text-text)":[90],"inter-modal":[94],"applying":[98],"hardest-negative-enhanced":[99],"on":[102,126],"pairs.":[104],"best":[107],"our":[109,137],"knowledge,":[110],"are":[112,155],"first":[114],"find":[116],"that":[117],"benefits":[120],"embedding.":[123],"Extensive":[124],"experiments":[125],"large":[127],"scale":[128],"MSCOCO":[129],"Flickr30K":[131],"datasets":[132],"verify":[133],"effectiveness":[135],"proposed":[138],"ConVSE":[139],"outperforming":[141],"embedding-based":[144],"methods":[145],"achieving":[147],"new":[148],"state-of-the-arts.":[149],"Our":[150],"code":[151],"pretrained":[153],"model":[154],"publicly":[156],"available":[157],"at:":[158],"\\url{https://github.com/liuyyy111/ConVSE}.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}