SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

1 code implementation • CVPR 2023 • Xuanyao Chen, Zhijian Liu, Haotian Tang, Li Yi, Hang Zhao, Song Han

High-resolution images enable neural networks to learn richer visual representations.

2D Semantic Segmentation Instance Segmentation +4

ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries

1 code implementation • CVPR 2023 • Junru Gu, Chenxu Hu, Tianyuan Zhang, Xuanyao Chen, Yilun Wang, Yue Wang, Hang Zhao

In this work, we propose ViP3D, a query-based visual trajectory prediction pipeline that exploits rich information from raw videos to directly predict future trajectories of agents in a scene.

Autonomous Driving Trajectory Prediction

MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries

1 code implementation • 2 May 2022 • Tianyuan Zhang, Xuanyao Chen, Yue Wang, Yilun Wang, Hang Zhao

In contrast to prior works, MUTR3D does not explicitly rely on the spatial and appearance similarity of objects.

Autonomous Driving Depth Estimation

FUTR3D: A Unified Sensor Fusion Framework for 3D Detection

1 code implementation • 20 Mar 2022 • Xuanyao Chen, Tianyuan Zhang, Yue Wang, Yilun Wang, Hang Zhao

Sensor fusion is an essential topic in many perception systems, such as autonomous driving and robotics.

Autonomous Driving Sensor Fusion

What Makes Multi-modal Learning Better than Single (Provably)

no code implementations • NeurIPS 2021 • Yu Huang, Chenzhuang Du, Zihui Xue, Xuanyao Chen, Hang Zhao, Longbo Huang

The world provides us with data of multiple modalities.