{"id":"https://openalex.org/W4399257586","doi":"https://doi.org/10.1145/3653804.3654720","title":"Improve Visual Semantic Embeddings via Regularization for Image-Text Retrieval","display_name":"Improve Visual Semantic Embeddings via Regularization for Image-Text Retrieval","publication_year":2024,"publication_date":"2024-01-19","ids":{"openalex":"https://openalex.org/W4399257586","doi":"https://doi.org/10.1145/3653804.3654720"},"language":"en","primary_location":{"id":"doi:10.1145/3653804.3654720","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653804.3654720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Vision and Deep Learning","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/A5111289140","display_name":"Hui Liu","orcid":"https://orcid.org/0009-0003-4062-685X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hui Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China, China and Avic Chengdu Aircraft Design and Research Institute, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China and Avic Chengdu Aircraft Design and Research Institute, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000627199","display_name":"Xiaoping Chen","orcid":"https://orcid.org/0009-0004-8307-9515"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoping Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038538654","display_name":"Rui Hong","orcid":"https://orcid.org/0000-0002-7627-4628"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Hong","raw_affiliation_strings":["University of Electronic Science and Technology of China, China and Avic Chengdu Aircraft Design and Research Institute, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China and Avic Chengdu Aircraft Design and Research Institute, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102890327","display_name":"Yan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, China and Avic Chengdu Aircraft Design and Research Institute, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China and Avic Chengdu Aircraft Design and Research Institute, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101497907","display_name":"Tiancai Wan","orcid":"https://orcid.org/0009-0003-9201-6068"},"institutions":[{"id":"https://openalex.org/I4210094459","display_name":"Craft Group (China)","ror":"https://ror.org/00gxm5663","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210094459"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiancai Wan","raw_affiliation_strings":["Avic Chengdu Aircraft Design and Research Institute, China"],"affiliations":[{"raw_affiliation_string":"Avic Chengdu Aircraft Design and Research Institute, China","institution_ids":["https://openalex.org/I4210094459"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5098972468","display_name":"Taili Bai","orcid":"https://orcid.org/0009-0004-6877-4384"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taili Bai","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5111289140"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06656392,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7796016931533813},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6638075113296509},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6109071373939514},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5660845637321472},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5423577427864075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5220022797584534},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4666578471660614},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45413196086883545},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41161084175109863},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3625516891479492},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1869792640209198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7796016931533813},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6638075113296509},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6109071373939514},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5660845637321472},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5423577427864075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220022797584534},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4666578471660614},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45413196086883545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41161084175109863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3625516891479492},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1869792640209198},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer 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:10.1145/3653804.3654720","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653804.3654720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Vision and Deep Learning","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/W2900511962","https://openalex.org/W2962964995","https://openalex.org/W2988823324","https://openalex.org/W3030204642","https://openalex.org/W3035454331","https://openalex.org/W3118694826","https://openalex.org/W3175888430","https://openalex.org/W4214819138","https://openalex.org/W4304014355","https://openalex.org/W4312761738","https://openalex.org/W4323338501","https://openalex.org/W4386071498","https://openalex.org/W4386071757"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W4239293476","https://openalex.org/W1566995892"],"abstract_inverted_index":{"In":[0],"the":[1,7,14,25,36,56,59,74,80,84,92,103,107],"last":[2],"few":[3],"years,":[4],"due":[5],"to":[6,47,54,78,130],"quick":[8],"expansion":[9],"of":[10,27,38,62,76,87],"multimedia":[11],"data":[12,40],"and":[13,106],"progress":[15],"in":[16,24,58],"deep":[17],"learning,":[18],"notable":[19],"accomplishments":[20],"have":[21],"been":[22],"made":[23],"field":[26],"image-text":[28],"retrieval.":[29,89],"Current":[30],"approaches":[31,115],"predominantly":[32],"concentrate":[33],"on":[34,95],"enhancing":[35],"representation":[37],"cross-modal":[39,63,99],"or":[41],"devising":[42],"advanced":[43],"similarity":[44],"inference":[45],"modules":[46],"boost":[48],"retrieval":[49],"performance.":[50],"Nevertheless,":[51],"they":[52],"tend":[53],"overlook":[55],"stability":[57],"self-optimization":[60],"process":[61],"models.":[64],"This":[65],"paper":[66],"introduces":[67],"a":[68],"novel":[69],"approach,":[70],"namely":[71],"ITRR,":[72],"from":[73,116],"perspective":[75],"regularization,":[77],"enhance":[79],"reliability,":[81],"thus":[82],"boosting":[83],"recall":[85],"performance":[86],"bi-direction":[88],"We":[90],"assess":[91],"proposed":[93],"ITRR":[94],"two":[96],"broadly":[97],"used":[98],"benchmark":[100],"datasets,":[101],"i.e.,":[102],"Flickr30K":[104],"dataset":[105],"MS-COCO":[108],"dataset,":[109],"comparing":[110],"it":[111],"against":[112],"several":[113],"state-of-the-art":[114],"recent":[117],"years.":[118],"The":[119],"experimental":[120],"results":[121],"indicate":[122],"that":[123],"regularization":[124],"serves":[125],"as":[126],"an":[127],"effective":[128],"means":[129],"improve":[131],"visual":[132],"semantic":[133],"embeddings.":[134]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}