{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T16:47:39Z","timestamp":1744303659833,"version":"3.28.0"},"reference-count":72,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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]]},"DOI":"10.1109\/cvpr52729.2023.01430","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:30:52Z","timestamp":1692725452000},"page":"14890-14900","source":"Crossref","is-referenced-by-count":35,"title":["Natural Language-Assisted Sign Language Recognition"],"prefix":"10.1109","author":[{"given":"Ronglai","family":"Zuo","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology"}]},{"given":"Fangyun","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Brian","family":"Mak","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3070438"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML","author":"Chen","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00506"},{"key":"ref7","article-title":"Two-stream network for sign language recognition and translation","volume-title":"NeurIPS","author":"Chen","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01823"},{"key":"ref9","first-page":"14084","article-title":"Learning to prompt for open-vocabulary ob-ject detection with vision-language model","volume-title":"CVPR","author":"Du","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01370"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref14","article-title":"Wukong: A 100 million large-scale chinese cross-modal pre-training benchmark","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Gu","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00347"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01090"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16247"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3436754"},{"journal-title":"Unsupervised prompt learning for vision-language models","year":"2022","author":"Huang","key":"ref21"},{"key":"ref22","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICML","author":"Jia","year":"2021"},{"journal-title":"Sign language recognition via skeleton-aware multi-model ensemble","year":"2021","author":"Jiang","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00380"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref26","article-title":"MS-ASL: A large-scale data set and benchmark for understanding American sign language","volume-title":"BMVC","author":"Joze","year":"2019"},{"journal-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_3"},{"key":"ref29","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional trans-formers for language understanding","volume-title":"NAACL-HLT","author":"Kenton","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01376"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"ref33","article-title":"Language-driven semantic segmentation","volume-title":"ICLR","author":"Li","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"ref35","article-title":"TSPNet: Hier-archical feature learning via temporal semantic pyramid for sign language translation","volume-title":"NeurIPS","author":"Li","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00624"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"journal-title":"Efficient estimation of word representations in vector space","year":"2013","author":"Mikolov","key":"ref38"},{"key":"ref39","article-title":"Advances in pre-training distributed word representations","volume-title":"Proceedings of the Inter-national Conference on Language Resources and Evaluation (LREC)","author":"Mikolov","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"ref41","article-title":"Learning word embeddings efficiently with noise-contrastive estimation","author":"Mnih","year":"2013","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_39"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_11"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language super-vision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref51","article-title":"ImageNet large scale visual recognition chal-lenge","author":"Russakovsky","year":"2014","journal-title":"IJCV"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139163910"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.150"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.427"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00584"},{"key":"ref56","first-page":"2818","article-title":"Rethinking the inception ar-chitecture for computer vision","volume-title":"CVPR","author":"Szegedy","year":"2016"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW52041.2021.00008"},{"issue":"6","key":"ref58","first-page":"1416","article-title":"Scaling up sign spot-ting through sign language dictionaries","volume":"130","author":"Varol","year":"2022","journal-title":"IICV"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"journal-title":"A simple baseline for zero-shot semantic segmentation with pre-trained vision-language model","year":"2021","author":"Xu","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref63","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"ICLR","author":"Yao","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00505"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475544"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_251"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2013.39"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25470"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7001"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00507"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-164"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2023,6,17]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10205130.pdf?arnumber=10205130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T03:58:57Z","timestamp":1710388737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10205130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/cvpr52729.2023.01430","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}