X Li, D Wang, Y Zhang - Applied Computational Intelligence …, 2017 - Wiley Online Library
The dense trajectories and low‐level local features are widely used in action recognition recently. However, most of these methods ignore the motion part of action which is the key …
S Arif, J Wang, Z Fei, F Hussain - KSII Transactions on Internet and …, 2019 - koreascience.kr
In human activity recognition system both static and motion information play crucial role for efficient and competitive results. Most of the existing methods are insufficient to extract video …
S Mukherjee, KK Singh - Multimedia Tools and Applications, 2018 - Springer
We propose a unified method for recognizing human action and human related events in a realistic video. We use an efficient pipeline of (a) a 3D representation of the Improved Dense …
W You, J Guo, K Shan, Y Dai - Procedia Computer Science, 2019 - Elsevier
Recognition of human actions in videos has been an active research area in computer vision community due to its important theoretical research significance and extensive …
X Xiao, H Hu, W Wang - 2017 IEEE International Conference …, 2017 - ieeexplore.ieee.org
Recently, a common and popular method that produces competitive accuracy is to employ dense trajectories to identity human action. However, computing descriptors of dense …
S Arif, J Wang, F Hussain, Z Fei - Journal of Information …, 2019 - search.ebscohost.com
This article presents a new method for video representation, called trajectory based 3D convolutional descriptor (TCD), which incorporates the advantages of both deep learned …
Action recognition methods enable several intelligent machines to recognize human action in their daily life videos. Indeed, many action recognition methods give a noticeable …
Spatiotemporal features have significant importance in human action recognition, as they provide the actor's shape and motion characteristics specific to each action class. This paper …
L Qi, X Lu, X Li - Proceedings of the 2nd International Conference on …, 2018 - dl.acm.org
As a popular research field in computer vision community, human action recognition in videos is a challenging task. In recent years, trajectory based methods have been proven …