Search Results for author:
Found 2 papers, 2 papers with code
A Robotic Visual Grasping Design: Rethinking Convolution Neural Network with High-Resolutions
We demonstrate that using parallel branches as opposed to serial stacked convolutional layers will be a more powerful design for robotic visual grasping tasks.
When Transformer Meets Robotic Grasping: Exploits Context for Efficient Grasp Detection
The first key design is that we adopt the local window attention to capture local contextual information and detailed features of graspable objects.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
