Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion

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.

Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition

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.

Action Recognition Skeleton Based Action Recognition +1

Decentralized Bayesian Learning over Graphs

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.

Bayesian Inference Federated Learning