no code implementations • 17 Apr 2024 • Xinghan Wang, Zixi Kang, Yadong Mu
We address these challenges by proposing Text-controlled Motion Mamba (TM-Mamba), a unified model that integrates temporal global context, language query control, and spatial graph topology with only linear memory cost.
1 code implementation • CVPR 2023 • Xinghan Wang, Xin Xu, Yadong Mu
Besides, we also show that our Koopman pooling framework can be easily extended to one-shot action recognition when combined with Dynamic Mode Decomposition.
no code implementations • 24 May 2019 • Anusha Lalitha, Xinghan Wang, Osman Kilinc, Yongxi Lu, Tara Javidi, Farinaz Koushanfar
The proposed algorithm can be viewed as a Bayesian and peer-to-peer variant of federated learning in which each agent keeps a "posterior probability distribution" over a global model parameters.