In recent years, deep learning (DL), a rebranding of neural networks (NNs), has risen to the top in numerous areas, namely computer vision (CV), speech recognition, and natural …
One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art …
Y Tang, Y Tian, J Lu, P Li… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
In this paper, we propose a deep progressive reinforcement learning (DPRL) method for action recognition in skeleton-based videos, which aims to distil the most informative frames …
Long-Term person re-identification (LT-reID) exposes extreme challenges because of the longer time gaps between two recording footages where a person is likely to change …
M Wang, W Deng - … of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
Racial equality is an important theme of international human rights law, but it has been largely obscured when the overall face recognition accuracy is pursued blindly. More facts …
Q Leng, M Ye, Q Tian - … on Circuits and Systems for Video …, 2019 - ieeexplore.ieee.org
Person re-identification (re-ID) has been a popular topic in computer vision and pattern recognition communities for a decade. Several important milestones such as metric-based …
Q Yang, A Wu, WS Zheng - IEEE transactions on pattern …, 2019 - ieeexplore.ieee.org
Person re-identification (re-id), the process of matching pedestrian images across different camera views, is an important task in visual surveillance. Substantial development of re-id …
Fine-grained classification is challenging because categories can only be discriminated by subtle and local differences. Variances in the pose, scale or rotation usually make the …
Z Zhou, Y Huang, W Wang… - Proceedings of the …, 2017 - openaccess.thecvf.com
Surveillance cameras have been widely used in different scenes. Accordingly, a demanding need is to recognize a person under different cameras, which is called person re …