With the surge in attention to Egocentric Hand-Object Interaction (Ego-H...
In recent years, there has been a significant effort dedicated to develo...
In daily life, humans utilize hands to manipulate objects. Modeling the ...
We present ClothesNet: a large-scale dataset of 3D clothes objects with
...
The reconstruction of object surfaces from multi-view images or monocula...
A key challenge in robotic manipulation in open domains is how to acquir...
Data-efficient learning has drawn significant attention, especially give...
With the progress of 3D human pose and shape estimation, state-of-the-ar...
Recovering whole-body mesh by inferring the abstract pose and shape
para...
Enable neural networks to capture 3D geometrical-aware features is essen...
Action understanding matters and attracts attention. It can be formed as...
Tactile sensing is one of the modalities humans rely on heavily to perce...
Garments are important to humans. A visual system that can estimate and ...
Deep neural networks (DNNs) often perform poorly in the presence of doma...
Various recent methods attempt to implement rotation-invariant 3D deep
l...
As the basis for prehensile manipulation, it is vital to enable robots t...
Understanding objects is a central building block of artificial intellig...
Object pose estimation is an important topic in 3D vision. Though most
c...
This paper presents a general one-shot object localization algorithm cal...
Spatio-temporal Human-Object Interaction (ST-HOI) detection aims at dete...
Accurate whole-body multi-person pose estimation and tracking is an impo...
We present RCareWorld, a human-centric simulation world for physical and...
Hand, the bearer of human productivity and intelligence, is receiving mu...
Neural Radiance Fields (NeRFs), despite their outstanding performance on...
3D human pose estimation from a monocular video has recently seen signif...
Long-tailed image recognition presents massive challenges to deep learni...
Human-Object Interaction (HOI) detection plays a crucial role in activit...
In this paper, we propose a genuine group-level contrastive visual
repre...
Estimating the 6D pose for unseen objects is in great demand for many
re...
Human-Object Interaction (HOI) detection plays a core role in activity
u...
Anticipating future events is an essential feature for intelligent syste...
Learning how humans manipulate objects requires machines to acquire know...
Typical vision backbones manipulate structured features. As a compromise...
In this paper, we tackle the problem of category-level 9D pose estimatio...
Human-Object Interaction (HOI) detection plays a core role in activity
u...
Transparent objects are common in our daily life and frequently handled ...
Human life is populated with articulated objects. A comprehensive
unders...
Human activity understanding is of widespread interest in artificial
int...
Household environments are important testbeds for embodied AI research. ...
A large-scale dataset is essential for learning good features in 3D shap...
Articulated objects are pervasive in daily life. However, due to the
int...
Anomaly detection in surveillance videos is challenging and important fo...
Building general-purpose robots to perform an enormous amount of tasks i...
Pixel-level 2D object semantic understanding is an important topic in
co...
Skeleton data carries valuable motion information and is widely explored...
Soft-argmax operation is commonly adopted in detection-based methods to
...
Attributes and objects can compose diverse compositions. To model the
co...
Estimating the articulated 3D hand-object pose from a single RGB image i...
Heatmap-based methods dominate in the field of human pose estimation by
...
Direct contour regression for instance segmentation is a challenging tas...