The last decade has witnessed the success of deep learning and the surge...
We present ArtiGrasp, a novel method to synthesize bi-manual hand-object...
We present EMDB, the Electromagnetic Database of Global 3D Human Pose an...
Weight Average (WA) is an active research topic due to its simplicity in...
Centralized Training with Decentralized Execution (CTDE) has recently em...
In this paper, we propose a novel hybrid representation and end-to-end
t...
Temporal graphs exhibit dynamic interactions between nodes over continuo...
We propose a method to estimate 3D human poses from substantially blurre...
We propose Hi4D, a method and dataset for the automatic analysis of
phys...
We present X-Avatar, a novel avatar model that captures the full
express...
We present Vid2Avatar, a method to learn human avatars from monocular
in...
Retrosynthesis is the cornerstone of organic chemistry, providing chemis...
In this paper, we take a significant step towards real-world applicabili...
Neural fields have revolutionized the area of 3D reconstruction and nove...
Value Decomposition (VD) aims to deduce the contributions of agents for
...
Reinforcement Learning (RL) is a popular machine learning paradigm where...
Convolutional neural networks (CNNs) have demonstrated gratifying result...
Neural networks (NNs) and decision trees (DTs) are both popular models o...
Prototypical part network (ProtoPNet) has drawn wide attention and boost...
In this paper, we explore a new knowledge-amalgamation problem, termed
F...
Life-long learning aims at learning a sequence of tasks without forgetti...
Deep cooperative multi-agent reinforcement learning has demonstrated its...
Despite the promising results achieved, state-of-the-art interactive
rei...
Vanilla unsupervised domain adaptation methods tend to optimize the mode...
Semi-supervised object detection has made significant progress with the
...
Self-training for unsupervised domain adaptive object detection is a
cha...
The real-time transient stability assessment (TSA) plays a critical role...
Knowledge distillation (KD) has become a well established paradigm for
c...
There is a complex correlation among the data of scientific papers. The
...
Learning knowledge representation of scientific paper data is a problem ...
Continual learning is a longstanding research topic due to its crucial r...
Retrosynthesis prediction is a fundamental problem in organic synthesis,...
Knowledge amalgamation (KA) is a novel deep model reusing task aiming to...
We present a novel method to learn Personalized Implicit Neural Avatars
...
The proposal of perceptual loss solves the problem that per-pixel differ...
To make 3D human avatars widely available, we must be able to generate a...
Data-free knowledge distillation (DFKD) has recently been attracting
inc...
As data lakes become increasingly popular in large enterprises today, th...
Recently, Convolutional Neural Network (CNN) has achieved excellent
perf...
Recently, vision Transformers (ViTs) are developing rapidly and starting...
Object detection is a fundamental task in computer vision and image
proc...
Knowledge distillation (KD) has recently emerged as a powerful strategy ...
We introduce the dynamic grasp synthesis task: given an object with a kn...
Capturing the dynamically deforming 3D shape of clothed human is essenti...
Upsampling videos of human activity is an interesting yet challenging ta...
Knowledge distillation (KD) aims to craft a compact student model that
i...
Dimensionality Reduction (DR) techniques can generate 2D projections and...
In this paper we contribute a simple yet effective approach for estimati...
Graph-level representation learning is the pivotal step for downstream t...
Model inversion, whose goal is to recover training data from a pre-train...