3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation

no code implementations • 2 Jun 2022 • Zhidan Liu, Zhen Xing, Xiangdong Zhou, Yijiang Chen, Guichun Zhou

We enhance the performance of image-based methods for category-agnostic object pose estimation by exploiting 3D knowledge learned by a multi-modal method.

Contrastive Learning Knowledge Distillation +2

CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification

no code implementations • 8 Mar 2022 • Yijiang Chen, Xiangdong Zhou, Zhen Xing, Zhidan Liu, Minyang Xu

Many previous works focus on the pretext task of self-supervised learning and usually neglect the complex problem of MTS encoding, leading to unpromising results.

Representation Learning Self-Supervised Learning +3

Context-aware taxi dispatching at city-scale using deep reinforcement learning

no code implementations • IEEE Transactions on Intelligent Transportation Systems 2021 • Zhidan Liu, Jiangzhou Li, and Kaishun Wu, Member, IEEE

Abstract— Proactive taxi dispatching is of great importance to balance taxi demand-supply gaps among different locations in a city.

Action Generation reinforcement-learning +1