Estimating 6D poses and reconstructing 3D shapes of objects in open-worl...
Currently, salience-based channel pruning makes continuous breakthroughs...
Dynamic neural networks can greatly reduce computation redundancy withou...
Recent years have witnessed great progress in deep neural networks for
r...
3D hand pose estimation is a long-standing challenge in both robotics an...
Monocular 3D human pose estimation is quite challenging due to the inher...