{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T08:17:39Z","timestamp":1725610659367},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956317","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:34:13Z","timestamp":1669732453000},"page":"4693-4699","source":"Crossref","is-referenced-by-count":0,"title":["Cross-modal Retrieval Using Contrastive Learning of Visual-Semantic Embeddings"],"prefix":"10.1109","author":[{"given":"Anurag","family":"Jain","sequence":"first","affiliation":[{"name":"Cadence Design Systems (India) Private Limited"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yashaswi","family":"Verma","sequence":"additional","affiliation":[{"name":"IIT,Jodhpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/ICCV48922.2021.00148"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1587\/transinf.2020MUP0003"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","article-title":"Contrastive learning of visual-semantic embeddings","author":"jain","year":"2021","journal-title":"CoRR"},{"key":"ref31","article-title":"Self-supervised multimodal versatile networks","author":"alayrac","year":"2020","journal-title":"NeurIPS 2020"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/CVPR42600.2020.00674"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"ref36","article-title":"T-vse: Transformer-based visual semantic embedding","author":"bastan","year":"2020","journal-title":"ArXiv"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1145\/3343031.3350894"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR.2018.00419"},{"key":"ref28","article-title":"Supervised contrastive learning","author":"khosla","year":"2020","journal-title":"NeurIPS 2020"},{"key":"ref27","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"h\u00e9naff","year":"2020","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"ref2","article-title":"DeViSE: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref1","article-title":"WSABIE: Scaling up to large vocabulary image annotation","author":"weston","year":"2011","journal-title":"IJCAI"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1162\/tacl_a_00177"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICCV.2017.283"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref24","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1007\/978-3-030-58523-5_19"},{"key":"ref26","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref25","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1145\/1873951.1873987"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR.2012.6247923"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1162\/tacl_a_00166"},{"key":"ref12","article-title":"Cluster canonical correlation analysis","author":"rasiwasia","year":"2014","journal-title":"AISTATS"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/s11263-013-0658-4"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICCV.2015.466"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1016\/j.patcog.2021.107905"},{"key":"ref16","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2015","journal-title":"ICLRE"},{"key":"ref17","article-title":"Learning two-branch neural networks for image-text matching tasks","author":"wang","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1145\/3314577"},{"key":"ref19","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"BMVC"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.18653\/v1\/N18-2125"},{"key":"ref3","article-title":"Im2Text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"NIPS"},{"key":"ref6","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref8","first-page":"1393","article-title":"Bilingual word embeddings for phrase-based machine translation","author":"zou","year":"2013","journal-title":"EMNLP"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICCV.2015.9"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1016\/j.patcog.2021.107983"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1162\/0899766042321814"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1007\/978-3-030-01246-5_42"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/CVPR.2017.232"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1145\/3383184"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"CoRR"},{"key":"ref41","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1109\/ICCV.2017.442"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/CVPR.2017.767"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956317.pdf?arnumber=9956317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T15:05:38Z","timestamp":1671462338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956317\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956317","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}