{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T03:28:46Z","timestamp":1768620526485,"version":"3.49.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,25]]},"DOI":"10.1109\/ijcb57857.2023.10448749","type":"proceedings-article","created":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T18:31:14Z","timestamp":1709317874000},"page":"1-10","source":"Crossref","is-referenced-by-count":3,"title":["Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation"],"prefix":"10.1109","author":[{"given":"Md Mahedi","family":"Hasan","sequence":"first","affiliation":[{"name":"West Virginia University,Morgantown,West Virginia,USA"}]},{"given":"Nasser","family":"Nasrabadi","sequence":"additional","affiliation":[{"name":"West Virginia University,Morgantown,West Virginia,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv:1607.06450"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00322"},{"key":"ref4","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"North American Chapter of the Association for Computational Linguistics","author":"Devlin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2807791"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0447-x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916751"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_9"},{"key":"ref12","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ioffe"},{"key":"ref13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01819"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref17","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_26"},{"key":"ref21","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","volume":"abs\/1907.11692","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref23","article-title":"SGDR: stochastic gradient descent with warm restarts","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref24","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01400"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford"},{"key":"ref28","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv preprint arXiv:1910.01108"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2014.2299975"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00342"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref36","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015","journal-title":"arXiv preprint arXiv:1505.00853"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69532-3_19"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.03.003"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_37"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01035"}],"event":{"name":"2023 IEEE International Joint Conference on Biometrics (IJCB)","location":"Ljubljana, Slovenia","start":{"date-parts":[[2023,9,25]]},"end":{"date-parts":[[2023,9,28]]}},"container-title":["2023 IEEE International Joint Conference on Biometrics (IJCB)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10447019\/10448524\/10448749.pdf?arnumber=10448749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T01:14:26Z","timestamp":1709860466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,25]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ijcb57857.2023.10448749","relation":{},"subject":[],"published":{"date-parts":[[2023,9,25]]}}}