{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:30:09Z","timestamp":1777995009884,"version":"3.51.4"},"reference-count":26,"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"}],"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447118","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3195-3199","source":"Crossref","is-referenced-by-count":2,"title":["Open-Vocabulary Skeleton Action Recognition with Diffusion Graph Convolutional Network and Pre-Trained Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Chao","family":"Wei","sequence":"first","affiliation":[{"name":"Institute for Artificial Intelligence at Tsinghua University (THUAI),Beijing National Research Center for Information Science and Technology (BNRist)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhidong","family":"Deng","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence at Tsinghua University (THUAI),Beijing National Research Center for Information Science and Technology (BNRist)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01433"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/app12010004"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref4","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref5","author":"Schuhmann","year":"2021","journal-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs"},{"key":"ref6","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref8","first-page":"7793","article-title":"Beyond homophily in graph neural networks: Current limitations and effective designs","volume":"33","author":"Zhu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","author":"Oono","year":"2019","journal-title":"Graph neural networks exponentially lose expressive power for node classification"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref15","author":"Kipf","year":"2016","journal-title":"Semi-supervised classification with graph convolutional networks"},{"key":"ref16","author":"Li","year":"2020","journal-title":"Fourier neural operator for parametric partial differential equations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s41468-019-00038-7"},{"key":"ref18","author":"van den Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref20","author":"Kay","year":"2017","journal-title":"The kinetics human action video dataset"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506179"},{"key":"ref23","author":"Huang","year":"2023","journal-title":"Graph contrastive learning for skeleton-based action recognition"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.386"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10447118.pdf?arnumber=10447118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:29:59Z","timestamp":1722576599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447118","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}