Intuitive physics is pivotal for human understanding of the physical wor...
Existing methods for reconstructing interactive scenes primarily focus o...
Recent advances in large language models have led to renewed interest in...
We investigate the sequential manipulation planning problem for unmanned...
Without explicit feedback, humans can rapidly learn the meaning of words...
With significant annotation savings, point supervision has been proven
e...
We introduce SceneDiffuser, a conditional generative model for 3D scene
...
In this work, we present a reconfigurable data glove design to capture
d...
If scientific discovery is one of the main driving forces of human progr...
Learning to generate diverse scene-aware and goal-oriented human motions...
Is dynamics prediction indispensable for physical reasoning? If so, what...
We devise a 3D scene graph representation, contact graph+ (cg+), for
eff...
Theoretical ideas and empirical research have shown us a seemingly surpr...
We devise a cooperative planning framework to generate optimal trajector...
Humans communicate with graphical sketches apart from symbolic languages...
We study the understanding of embodied reference: One agent uses both
la...
To date, various 3D scene understanding tasks still lack practical and
g...
Human-robot collaboration is an essential research topic in artificial
i...
We construct a Virtual Kinematic Chain (VKC) that readily consolidates t...
The simple gesture of pointing can greatly augment ones ability to compr...
Existing grasp synthesis methods are either analytical or data-driven. T...
Humans possess a unique social cognition capability; nonverbal communica...
In this paper, we rethink the problem of scene reconstruction from an
em...
Causal induction, i.e., identifying unobservable mechanisms that lead to...
Spatial-temporal reasoning is a challenging task in Artificial Intellige...
Most typical click models assume that the probability of a document to b...
Understanding and interpreting human actions is a long-standing challeng...
We design and develop a new shared Augmented Reality (AR) workspace for
...
Aiming to understand how human (false-)belief–a core socio-cognitive
abi...
We present a congestion-aware routing solution for indoor evacuation, wh...
As a comprehensive indicator of mathematical thinking and intelligence, ...
Recent progress in deep learning is essentially based on a "big data for...
We propose LETO, a new hybrid Lagrangian-Eulerian method for topology
op...
Detecting 3D objects from a single RGB image is intrinsically ambiguous,...
"Thinking in pictures," [1] i.e., spatial-temporal reasoning, effortless...
Learning transferable knowledge across similar but different settings is...
We propose a new 3D holistic++ scene understanding problem, which jointl...
We propose VRGym, a virtual reality testbed for realistic human-robot
in...
Dramatic progress has been witnessed in basic vision tasks involving
low...
An unprecedented booming has been witnessed in the research area of arti...
Holistic 3D indoor scene understanding refers to jointly recovering the ...
We present a human-centric method to sample and synthesize 3D room layou...
We propose a computational framework to jointly parse a single RGB image...
We propose the configurable rendering of massive quantities of photoreal...