Zhidong Deng

6

Papers

39

Total Citations

Papers (6)

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection

Exploring Timeline Control for Facial Motion Generation

DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios

Fast Object Detection in Compressed Video

3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment