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...
Enregistré dans:
Auteurs principaux: | Mingyu Liu, Fanman Meng, Qingbo Wu, Linfeng Xu, Qianghua Liao |
---|---|
Format: | article |
Langue: | EN |
Publié: |
Wiley
2021
|
Sujets: | |
Accès en ligne: | https://doaj.org/article/e18bac49cba44e608faa4e3b7caa524d |
Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
-
Multi‐dimensional weighted cross‐attention network in crowded scenes
par: Yefan Xie, et autres
Publié: (2021) -
Human behaviour recognition with mid‐level representations for crowd understanding and analysis
par: Bangyong Sun, et autres
Publié: (2021) -
Crowd understanding and analysis
par: Qi Wang, et autres
Publié: (2021) -
Learn from Object Counting: Crowd Counting with Meta‐learning
par: Changtong Zan, et autres
Publié: (2021) -
MFP‐Net: Multi‐scale feature pyramid network for crowd counting
par: Tao Lei, et autres
Publié: (2021)