Multi-modal unsupervised domain adaptation (MM-UDA) for 3D semantic
segm...
Multivariate Time-Series (MTS) data is crucial in various application fi...
Contrastive learning, as a self-supervised learning paradigm, becomes po...
Unsupervised domain adaptation (UDA) involves adapting a model trained o...
4D human perception plays an essential role in a myriad of applications,...
Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time...
Continuous Video Domain Adaptation (CVDA) is a scenario where a source m...
For video models to be transferred and applied seamlessly across video t...
WiFi-based smart human sensing technology enabled by Channel State
Infor...
As an important biomarker for human identification, human gait can be
co...
Avatar refers to a representative of a physical user in the virtual worl...
To enable video models to be applied seamlessly across video tasks in
di...
WiFi sensing has been evolving rapidly in recent years. Empowered by
pro...
Domain Adaptation of Black-box Predictors (DABP) aims to learn a model o...
Learning with noisy labels has aroused much research interest since data...
Assuming the source label space subsumes the target one, Partial Video D...
WiFi sensing technology has shown superiority in smart homes among vario...
WiFi technology has been applied to various places due to the increasing...
Deep neural networks have empowered accurate device-free human activity
...
A critical step in virtual dental treatment planning is to accurately
de...
Video-based Unsupervised Domain Adaptation (VUDA) methods improve the
ro...
While action recognition (AR) has gained large improvements with the
int...
Unsupervised Domain Adaptation (UDA), a branch of transfer learning wher...
The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) wit...
This paper introduces a novel self-supervised method that leverages
inco...
Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptat...
Partial Domain Adaptation (PDA) is a practical and general domain adapta...
Domain adaptation (DA) approaches address domain shift and enable networ...
Deep networks achieve excellent results on large-scale clean data but de...
Temporal feature extraction is an essential technique in video-based act...
Long-range spatiotemporal dependencies capturing plays an essential role...
The task of action recognition in dark videos is useful in various scena...
Temporal feature extraction is an important issue in video-based action
...
Domain adaptation tackles the problem of transferring knowledge from a
l...
Annotating a qualitative large-scale facial expression dataset is extrem...
This paper presents our approach for the engagement intensity regression...
Occlusion and pose variations, which can change facial appearance
signif...
Convolutional neural networks (CNNs) have enabled the state-of-the-art
p...