This work focuses on the 3D reconstruction of non-rigid objects based on...
In recent years, self-supervised learning (SSL) has emerged as a promisi...
Due to limitations in data quality, some essential visual tasks are diff...
It has been discovered that Graph Convolutional Networks (GCNs) encounte...
Learning high-quality Q-value functions plays a key role in the success ...
Learning a shared policy that guides the locomotion of different agents ...
We propose SE-Bridge, a novel method for speech enhancement (SE). After
...
Binary Neural Network (BNN) represents convolution weights with 1-bit va...
Generative adversarial networks (GANs) have achieved remarkable progress...
In this paper, a novel robotic grasping system is established to
automat...
While Reinforcement Learning (RL) achieves tremendous success in sequent...
Benefiting from the injection of human prior knowledge, graphs, as deriv...
Simulation is widely applied in robotics research to save time and resou...
Video action segmentation aims to slice the video into several action
se...
Adversarial attacks can easily fool object recognition systems based on ...
Diffusion model, as a new generative model which is very popular in imag...
Currently, task-oriented grasp detection approaches are mostly based on
...
Designing and analyzing model-based RL (MBRL) algorithms with guaranteed...
3D object detection is a crucial research topic in computer vision, whic...
Audio-visual embodied navigation, as a hot research topic, aims training...
Few-shot learning models learn representations with limited human
annota...
The prevailing graph neural network models have achieved significant pro...
The ability to handle objects in cluttered environment has been long
ant...
Graph instance contrastive learning has been proved as an effective task...
Detecting 3D keypoints from point clouds is important for shape
reconstr...
Many adaptations of transformers have emerged to address the single-moda...
After the great success of Vision Transformer variants (ViTs) in compute...
Learning to reason about relations and dynamics over multiple interactin...
Nowadays, cameras equipped with AI systems can capture and analyze image...
Audio-visual navigation task requires an agent to find a sound source in...
Equivariant Graph neural Networks (EGNs) are powerful in characterizing ...
Keypoint detection and description play a central role in computer visio...
In the Vision-and-Language Navigation task, the embodied agent follows
l...
Recent works explore learning graph representations in a self-supervised...
Multimodal fusion and multitask learning are two vital topics in machine...
In the low-bit quantization field, training Binary Neural Networks (BNNs...
Referring expressions are commonly used when referring to a specific tar...
In visual semantic navigation, the robot navigates to a target object wi...
In this paper, we propose a novel Knowledge-based Embodied Question Answ...
Tactile sensing plays an important role in robotic perception and
manipu...
We propose a compact and effective framework to fuse multimodal features...
Currently, robotic grasping methods based on sparse partial point clouds...
It has been a challenge to learning skills for an agent from long-horizo...
Model Predictive Control (MPC) has shown the great performance of target...
Tactile sensing plays an important role in robotic perception and
manipu...
Robots have limited adaptation ability compared to humans and animals in...
Deep multimodal fusion by using multiple sources of data for classificat...
Deep reinforcement learning has made significant progress in robotic
man...
Increasing the depth of Graph Convolutional Networks (GCN), which in
pri...
Generalized Zero-Shot Learning (GZSL) is a challenging topic that has
pr...