C Zhou, M Wu, SK Lam - IEEE Transactions on Intelligent …, 2020 - ieeexplore.ieee.org
We present a unified multi-task learning architecture for fast and accurate pedestrian detection. Different from existing methods which often focus on either a new loss function or …
Pedestrian detection in the wild remains a challenging problem especially for scenes containing serious occlusion. In this paper, we propose a novel feature learning method in …
H Wang, Y Li, S Wang - IEEE Transactions on Intelligent …, 2019 - ieeexplore.ieee.org
Pedestrian detection has attracted more attention in the fields of computer vision and artificial intelligence. A variety of real-world applications involving pedestrian detection have …
P Yang, G Zhang, L Wang, L Xu… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Pedestrian detection is a crucial task in intelligent transportation systems, which can be applied in autonomous vehicles and traffic scene video surveillance systems. The past few …
W Liu, S Liao, W Hu, X Liang… - Proceedings of the …, 2018 - openaccess.thecvf.com
Abstract Though Faster R-CNN based two-stage detectors have witnessed significant boost in pedestrian detection accuracy, it is still slow for practical applications. One solution is to …
T Wang, L Wan, L Tang, M Liu - Applied Intelligence, 2022 - Springer
To solve the problem of numerous deep convolutions in YOLOv4, which generates many redundant background features so that it cannot focus on pedestrians at a specific scale, we …
Serious scale variation is a key challenge in pedestrian detection. Most works typically employ a feature pyramid network to detect objects at diverse scales. Such a method suffers …
Y Zhao, Z Yuan, B Chen - IEEE Transactions on Intelligent …, 2019 - ieeexplore.ieee.org
Recently, pedestrian detection has made significant advances benefiting from the region- based convolutional neural networks (R-CNN). However, training R-CNN with a holistic …
J Li, Y Bi, S Wang, Q Li - … on Circuits and Systems for Video …, 2023 - ieeexplore.ieee.org
High resolution and strong semantic representation are both vital for feature extraction networks of pedestrian detection. The existing high-resolution network (HRNet) has …