{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T04:43:49Z","timestamp":1758861829492,"version":"3.37.3"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T00:00:00Z","timestamp":1670630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T00:00:00Z","timestamp":1670630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,10]]},"DOI":"10.1109\/icsai57119.2022.10005459","type":"proceedings-article","created":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T21:28:16Z","timestamp":1673299696000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["SkeletonCLIP: Recognizing Skeleton-based Human Actions with Text Prompts"],"prefix":"10.1109","author":[{"given":"Lin","family":"Yuan","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Department of Control Science and Engineering,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"He","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Department of Control Science and Engineering,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Department of Control Science and Engineering,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leiyang","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Department of Control Science and Engineering,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Ma","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Department of Control Science and Engineering,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref2","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"arXiv preprint arXiv:1212.0402"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.24"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"article-title":"Bootstrap your own latent: A new approach to self-supervised learning","year":"2020","author":"Grill","key":"ref5"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"139","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"et al.","author":"Dosovitskiy","key":"ref17"},{"key":"ref18","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2785279"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2818328"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103348"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103219"},{"article-title":"Clip2tv: Align, match and distill for video-text retrieval","year":"2021","author":"Gao","key":"ref26"},{"article-title":"Clip2video: Mastering videotext retrieval via image clip","year":"2021","author":"Fang","key":"ref27"},{"article-title":"Language-driven semantic segmentation","year":"2022","author":"Li","key":"ref28"},{"article-title":"Actionclip: A new paradigm for video action recognition","year":"2021","author":"Wang","key":"ref29"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-19772-7_1","article-title":"Expanding language-image pretrained models for general video recognition","author":"Ni","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1145\/3503161.3548546","article-title":"Pyskl: Towards good practices for skeleton action recognition","author":"Duan","year":"2022"},{"article-title":"Neural machine translation of rare words with subword units","year":"2015","author":"Sennrich","key":"ref35"},{"key":"ref36","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","start":{"date-parts":[[2022,12,10]]},"location":"Kunming, China","end":{"date-parts":[[2022,12,12]]}},"container-title":["2022 8th International Conference on Systems and Informatics (ICSAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10005314\/10005319\/10005459.pdf?arnumber=10005459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T14:11:44Z","timestamp":1709388704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10005459\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,10]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icsai57119.2022.10005459","relation":{},"subject":[],"published":{"date-parts":[[2022,12,10]]}}}