Text-to-motion generation is a formidable task, aiming to produce human
...
Vision Transformer has demonstrated impressive success across various vi...
Diffusion Probabilistic Models (DPMs) have recently demonstrated impress...
Image restoration (IR) has been an indispensable and challenging task in...
Exploring spatial-temporal dependencies from observed motions is one of ...
Recently, polar-based representation has shown promising properties in
p...
Unsupervised domain adaptation (UDA) has witnessed remarkable advancemen...
Machine learning society has witnessed the emergence of a myriad of
Out-...
Class Incremental Semantic Segmentation (CISS) has been a trend recently...
Large language models (LLMs) have shown remarkable capabilities in langu...
Generative modeling has recently undergone remarkable advancements, prim...
The primary challenge in video super-resolution (VSR) is to handle large...
In this paper, we explore a novel model reusing task tailored for graph
...
Transformer-based models achieve favorable performance in artistic style...
The recent work known as Segment Anything (SA) has made significant stri...
3D reconstruction from a single-RGB image in unconstrained real-world
sc...
Style transfer aims to render the style of a given image for style refer...
Temporal graphs exhibit dynamic interactions between nodes over continuo...
We propose a novel task for generating 3D dance movements that simultane...
Learning to predict agent motions with relationship reasoning is importa...
In this paper, we study a novel task that enables partial knowledge tran...
Structural pruning enables model acceleration by removing
structurally-g...
Recent success of deep learning can be largely attributed to the huge am...
Despite the recent visually-pleasing results achieved, the massive
compu...
Large-scale vision-language models (VLMs) pre-trained on billion-level d...
In this paper, we study \xw{dataset distillation (DD)}, from a novel
per...
In Reinforcement Learning (RL), Laplacian Representation (LapRep) is a
t...
Existing fine-tuning methods either tune all parameters of the pre-train...
Spiking neural networks (SNNs) are shown to be more biologically plausib...
Convolutional neural networks (CNNs) have demonstrated gratifying result...
In multi-person 2D pose estimation, the bottom-up methods simultaneously...
Unsupervised generation of clothed virtual humans with various appearanc...
In this paper, we explore a new knowledge-amalgamation problem, termed
F...
Anomaly detection aims at identifying deviant samples from the normal da...
State-of-the-art parametric and non-parametric style transfer approaches...
Life-long learning aims at learning a sequence of tasks without forgetti...
One key challenge of exemplar-guided image generation lies in establishi...
Despite the promising results achieved, state-of-the-art interactive
rei...
In this paper, we explore a novel and ambitious knowledge-transfer task,...
Vanilla unsupervised domain adaptation methods tend to optimize the mode...
Self-training for unsupervised domain adaptive object detection is a
cha...
How to accurately predict the properties of molecules is an essential pr...
Face recognition, as one of the most successful applications in artifici...
Data-free knowledge distillation (DFKD) conducts knowledge distillation ...
Learning with noisy labels has aroused much research interest since data...
Existing self-supervised 3D human pose estimation schemes have largely r...
We present a simple and effective framework, named Point2Seq, for 3D obj...
Dataset condensation aims at reducing the network training effort throug...
Conventional 3D human pose estimation relies on first detecting 2D body
...
Data-free knowledge distillation (DFKD) has recently been attracting
inc...