{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:24:23Z","timestamp":1771262663900,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"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","award":["1846076"],"award-info":[{"award-number":["1846076"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/fg52635.2021.9667027","type":"proceedings-article","created":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T05:34:23Z","timestamp":1643175263000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Dynamic Cross-Feature Fusion for American Sign Language Translation"],"prefix":"10.1109","author":[{"given":"Tejaswini","family":"Ananthanarayana","sequence":"first","affiliation":[]},{"given":"Nikunj","family":"Kotecha","sequence":"additional","affiliation":[]},{"given":"Priyanshu","family":"Srivastava","sequence":"additional","affiliation":[]},{"given":"Lipisha","family":"Chaudhary","sequence":"additional","affiliation":[]},{"given":"Nicholas","family":"Wilkins","sequence":"additional","affiliation":[]},{"given":"Ifeoma","family":"Nwogu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref38","article-title":"Contrastive bidirectional transformer for temporal representation learning","volume":"abs 1906 5743","author":"sun","year":"2019","journal-title":"CoRR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/123"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.365"},{"key":"ref31","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref37","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"simonyan","year":"2014","journal-title":"NIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1021\/ac60214a047"},{"key":"ref35","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref34","author":"radford","year":"2018","journal-title":"Improving language understanding by generative pretraining"},{"key":"ref28","article-title":"Rwth-phoenix-weather 2014 t: Parallel corpus of sign language video, gloss and translation","volume":"5","author":"camg\u00f6z","year":"2018","journal-title":"ICPR 2018"},{"key":"ref27","article-title":"Towards continuous sign language recognition with deep learning","author":"mocialov","year":"2017","journal-title":"Proc of the Workshop on the Creating Meaning With Robot Assistants The Gap Left by Smart Devices"},{"key":"ref29","article-title":"An end-to-end baseline for video captioning","volume":"abs 1904 2628","author":"olivastri","year":"2019","journal-title":"CoRR"},{"key":"ref2","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref1","first-page":"2236","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"zadeh","year":"2018","journal-title":"Proceedings of the 56th Annual Meeting of the ACL"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.69"},{"key":"ref22","author":"li","year":"2020","journal-title":"Tspnet Hierarchical feature learning via temporal semantic pyramid for sign language translation"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.412"},{"key":"ref24","author":"lu","year":"2019","journal-title":"Vilbert Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-69923-3_77"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1093\/deafed\/enj004"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756506"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"ref40","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs 1810 4805","author":"devlin","year":"2018","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3131672.3131693"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","first-page":"1700","article-title":"Recurrent continuous translation models","author":"kalchbrenner","year":"2013","journal-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911077"},{"key":"ref4","author":"brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_18"},{"key":"ref8","first-page":"847","article-title":"Tvt: Two-view transformer network for video captioning","volume":"95","author":"chen","year":"2018","journal-title":"ACML"},{"key":"ref49","article-title":"Attention is all you sign: Sign language translation with transformers","author":"yin","year":"2020","journal-title":"ECCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.332"},{"key":"ref46","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","volume":"abs 1609 8144","author":"wu","year":"2016","journal-title":"CoRR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240671"},{"key":"ref48","article-title":"Sign language translation with transformers","author":"yin","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00280"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"137","DOI":"10.5201\/ipol.2013.26","article-title":"TV-Ll Optical Flow Estimation","volume":"3","author":"perez","year":"2013","journal-title":"Image Processing on Line"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref43","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"NIPS"}],"event":{"name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","location":"Jodhpur, India","start":{"date-parts":[[2021,12,15]]},"end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9666787\/9666788\/09667027.pdf?arnumber=9667027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:31Z","timestamp":1652201731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9667027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/fg52635.2021.9667027","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}