Behaviour detection in crowded classroom scenes via enhancing features robust to scale and perspective variations
Abstract Detecting human behaviours in images of crowded classroom scenes is a challenging task, due to the large variations of humans in scale and pose perspective. In this paper, two modules are proposed to tackle these two variations. First, an attention‐based RoI (region‐of‐interest) extractor i...
Main Authors: | Mingyu Liu, Fanman Meng, Qingbo Wu, Linfeng Xu, Qianghua Liao |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-12-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.12318 |
Similar Items
-
Multi‐level features extraction network with gating mechanism for crowd counting
by: Xin Zeng, et al.
Published: (2021-12-01) -
Crowd counting with segmentation attention convolutional neural network
by: Jiwei Chen, et al.
Published: (2021-05-01) -
MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting
by: Haoyu Zhao, et al.
Published: (2021-12-01) -
Human behaviour recognition with mid‐level representations for crowd understanding and analysis
by: Bangyong Sun, et al.
Published: (2021-12-01) -
Multi‐view facial action unit detection via deep feature enhancement
by: Chuangao Tang, et al.
Published: (2021-12-01)