{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T10:32:58Z","timestamp":1766485978152,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445852","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7995-7999","source":"Crossref","is-referenced-by-count":7,"title":["Video-Language Graph Convolutional Network for Human Action Recognition"],"prefix":"10.1109","author":[{"given":"Rui","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China,311100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoran","family":"Yan","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China,311100"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09904-8"},{"article-title":"Ct-net: Channel tensorization network for video classification","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Li","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059923"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00333"},{"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, ICML 2021, 18-24 July 2021, Virtual Event, 2021, vol. 139 of Proceedings of Machine Learning Research","author":"Radford"},{"key":"ref7","article-title":"Actionclip: A new paradigm for video action recognition","volume":"abs\/2109.08472","author":"Wang","year":"2021","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref9","first-page":"99","article-title":"Bayesian models of human action understanding","volume-title":"Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, NIPS 2005, December 5-8, 2005, Vancouver, British Columbia, Canada]","author":"Baker"},{"article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","author":"Kipf","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557223"},{"key":"ref12","article-title":"Fine-tuned CLIP models are efficient video learners","volume":"abs\/2212.03640","author":"Rasheed","year":"2022","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548257"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445852.pdf?arnumber=10445852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:56:58Z","timestamp":1722574618000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445852","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}