Huaxia Xia

Do We Really Need Explicit Position Encodings for Vision Transformers? pdf

Bo Zhang, Xiaolin Wei, Xiangxiang Chu, 2021, ArXiv.

Twins: Revisiting Spatial Attention Design in Vision Transformers pdf

Chunhua Shen, Xiaolin Wei, Xiangxiang Chu, 2021, ArXiv.

Visionnet: A Coarse-To-Fine Motion Prediction Algorithm Based On Active Interaction-Aware Drivable Space Learning

Dongchun Ren, Zhu Yanliang, Mingyu Fan, 2021, 2021 IEEE International Conference on Multimedia and Expo (ICME).

Star Topology based Interaction for Robust Trajectory Forecasting in Dynamic Scene

Dongchun Ren, Deheng Qian, Xin Li, 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

AST-GNN: An attention-based spatio-temporal graph neural network for Interaction-aware pedestrian trajectory prediction

Mingyu Fan, Dongchun Ren, Hai Huang, 2021, Neurocomputing.

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

Chunhua Shen, Xiaolin Wei, Xiangxiang Chu, 2021, NeurIPS.

Learning-Based Safety-Critical Motion Planning with Input-to-State Barrier Certificate

Huaxia Xia, Qing-Shan Jia, Xinze Jin, 2021, 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE).