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...
Saved in:
Main Authors: | Mingyu Liu, Fanman Meng, Qingbo Wu, Linfeng Xu, Qianghua Liao |
---|---|
Format: | article |
Language: | EN |
Published: |
Wiley
2021
|
Subjects: | |
Online Access: | https://doaj.org/article/e18bac49cba44e608faa4e3b7caa524d |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Multi‐dimensional weighted cross‐attention network in crowded scenes
by: Yefan Xie, et al.
Published: (2021) -
Human behaviour recognition with mid‐level representations for crowd understanding and analysis
by: Bangyong Sun, et al.
Published: (2021) -
Crowd understanding and analysis
by: Qi Wang, et al.
Published: (2021) -
Learn from Object Counting: Crowd Counting with Meta‐learning
by: Changtong Zan, et al.
Published: (2021) -
MFP‐Net: Multi‐scale feature pyramid network for crowd counting
by: Tao Lei, et al.
Published: (2021)