1

DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation
We propose GenDexGrasp, a versatile dexterous grasping method that can generalize to out-of-domain robotic hands. In addition, we contribute MultiDex, a large-scale synthetic dexterous grasping dataset.
PDF Cite Arxiv
DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation
GenDexGrasp: Generalizable Dexterous Grasping
We propose GenDexGrasp, a versatile dexterous grasping method that can generalize to out-of-domain robotic hands. In addition, we contribute MultiDex, a large-scale synthetic dexterous grasping dataset.
PDF Cite Code Dataset Video Arxiv
GenDexGrasp: Generalizable Dexterous Grasping
A Context-Integrated Transformer-Based Neural Network for Auction Design
One of the central problems in auction design is developing an incentive-compatible mechanism that maximizes the auctioneer’s …
PDF Cite Code Arxiv
Unsupervised Object-Centric Learning with Bi-Level Optimized Query Slot Attention
Cite
Denoising Masked Autoencoders are Certifiable Robust Vision Learners
In this paper, we propose a new self-supervised method, which is called denoising masked autoencoders (DMAE), for learning certified …
PDF Cite Code Dataset Video Arxiv
Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
While the voxel-based methods have achieved promising results for multi-person 3D pose estimation from multi-cameras, they suffer from …
PDF Cite Code Dataset Video Arxiv