Unsupervised Domain Adaptation (UDA) is quite challenging due to the lar...
Translating images from a source domain to a target domain for learning
...
Currently, salience-based channel pruning makes continuous breakthroughs...
Dynamic neural networks can greatly reduce computation redundancy withou...
Images of realistic scenes often contain intra-class objects that are he...
Monocular 3D human pose estimation is quite challenging due to the inher...
Spectral clustering is an effective methodology for unsupervised learnin...
Skeleton-based action recognition receives increasing attention because ...
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 ...
Existing computer vision systems can compete with humans in understandin...
In recent years, one of the most popular techniques in the computer visi...
Currently, single image inpainting has achieved promising results based ...
Effective learning of spatial-temporal information within a point cloud
...
In this paper, we introduce the Multi-Modal Video Reasoning and Analyzin...
Understanding the actions of both humans and artificial intelligence (AI...
Human Action Recognition (HAR), aiming to understand human behaviors and...
Street Scene Change Detection (SSCD) aims to locate the changed regions
...
With the success of deep learning methods in analyzing activities in vid...
This paper presents a new method for 3D action recognition with skeleton...
Predicting an interaction before it is fully executed is very important ...