{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:29:31Z","timestamp":1753601371699},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096661","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"source":"Crossref","is-referenced-by-count":4,"title":["Semantic-Preserving Augmentation for Robust Image-Text Retrieval"],"prefix":"10.1109","author":[{"given":"Sunwoo","family":"Kim","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyuhong","family":"Shim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luong Trung","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byonghyo","family":"Shim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"Frome","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3093983"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3236671"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC49870.2020.9289280"},{"key":"ref6","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. BMVC","author":"Faghri"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00590"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01553"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747741"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref13","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref14","article-title":"Autoaugment: Learning augmentation policies from data","author":"Cubuk","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00492-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref18","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. ICLR","author":"Hendrycks"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.01028","article-title":"In defense of grid features for visual question answering","volume-title":"Proc. ICCV","author":"Jiang"},{"key":"ref21","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096661.pdf?arnumber=10096661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:12:29Z","timestamp":1710367949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096661","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}