Large language models (LLMs) have demonstrated exceptional performance i...
Traditional convolutional neural networks are limited to handling Euclid...
EIE proposed to accelerate pruned and compressed neural networks, exploi...
In many practical scenarios – like hyperparameter search or continual
re...
Accurately estimating 3D hand pose is crucial for understanding how huma...
The ability to learn from human demonstration endows robots with the abi...
Rapid progress and superior performance have been achieved for skeleton-...
While category-level 9DoF object pose estimation has emerged recently,
p...
6D object pose estimation is a fundamental yet challenging problem in
co...
Samples in large-scale datasets may be mislabeled due to various reasons...
A popular paradigm in robotic learning is to train a policy from scratch...
Terms and conditions (T Cs) are pervasive on the web and often contain...
Manipulating articulated objects requires multiple robot arms in general...
A key component of understanding hand-object interactions is the ability...
We present KDFNet, a novel method for 6D object pose estimation from RGB...
We present a large-scale stereo RGB image object pose estimation dataset...
The use of iterative pose refinement is a critical processing step for 6...
This paper presents a time-efficient scheme for Mars exploration by the
...
Estimating the 3D pose of desktop objects is crucial for applications su...
Understanding dynamic 3D environment is crucial for robotic agents and m...
Correspondences between frames encode rich information about dynamic con...
Many applications in robotics and human-computer interaction can benefit...
Convolutional Neural Networks (CNNs) are computationally intensive, whic...
Sparsity helps reduce the computational complexity of deep neural networ...
State-of-the-art deep neural networks (DNNs) have hundreds of millions o...