AI-generated content (AIGC) methods aim to produce text, images, videos,...
Recovering a 3D human mesh from a single RGB image is a challenging task...
Recently, deep learning based approaches have shown promising results in...
Learning with large-scale unlabeled data has become a powerful tool for
...
Currently, salience-based channel pruning makes continuous breakthroughs...
Dynamic neural networks can greatly reduce computation redundancy withou...
Monocular 3D human pose estimation is quite challenging due to the inher...
The goal of fine-grained action recognition is to successfully discrimin...
Human interaction recognition is very important in many applications. On...
Early action prediction aims to successfully predict the class label of ...
In contrast to batch learning where all training data is available at on...
In this paper, we introduce the Multi-Modal Video Reasoning and Analyzin...
In this paper, we propose a novel hand-based person recognition method f...
In cases of serious crime, including sexual abuse, often the only availa...
The rapid outbreak of COVID-19 threatens humans life all around the worl...
Human Action Recognition (HAR), aiming to understand human behaviors and...
Regularization plays a vital role in the context of deep learning by
pre...
Recognizing human actions from unknown and unseen (novel) views is a
cha...
Existing techniques for 3D action recognition are sensitive to viewpoint...
We propose an action classification algorithm which uses Locality-constr...
Existing techniques for 3D action recognition are sensitive to viewpoint...