Enhanced action recognition using multiple stream deep learning with optical flow and weighted sum

H Kim, S Park, H Park, J Paik - Sensors, 2020 - mdpi.com
Various action recognition approaches have recently been proposed with the aid of three-
dimensional (3D) convolution and a multiple stream structure. However, existing methods …

Learning spatio-temporal representations for action recognition: A genetic programming approach

L Liu, L Shao, X Li, K Lu - IEEE transactions on cybernetics, 2015 - ieeexplore.ieee.org
Extracting discriminative and robust features from video sequences is the first and most
critical step in human action recognition. In this paper, instead of using handcrafted features …

The literature review of action recognition in traffic context

H Zhang - Journal of Visual Communication and Image …, 2019 - Elsevier
With the development of science and technology and the progress of computing level, the
research field based on video is getting more and more attention. Video understanding is a …

A review of convolutional-neural-network-based action recognition

G Yao, T Lei, J Zhong - Pattern Recognition Letters, 2019 - Elsevier
Video action recognition is widely applied in video indexing, intelligent surveillance,
multimedia understanding, and other fields. Recently, it was greatly improved by …

Multiple feature fusion in convolutional neural networks for action recognition

H Li, J Chen, R Hu - Wuhan University Journal of Natural Sciences, 2017 - Springer
Action recognition is important for understanding the human behaviors in the video, and the
video representation is the basis for action recognition. This paper provides a new video …

Improving human action recognition with two-stream 3D convolutional neural network

VM Khong, TH Tran - 2018 1st international conference on …, 2018 - ieeexplore.ieee.org
Human action recognition has became a hot topic in recent years because it opens a wide
range of applications such as video surveillance, assisted living, entertainment. Recently …

A real-time action representation with temporal encoding and deep compression

K Liu, W Liu, H Ma, M Tan, C Gan - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Deep neural networks have achieved remarkable success for video-based action
recognition. However, most of existing approaches cannot be deployed in practice due to …

Robust action recognition via borrowing information across video modalities

NC Tang, YY Lin, JH Hua, SE Wei… - … on Image Processing, 2014 - ieeexplore.ieee.org
The recent advances in imaging devices have opened the opportunity of better solving the
tasks of video content analysis and understanding. Next-generation cameras, such as the …

Learning discriminative motion feature for enhancing multi-modal action recognition

J Yang, Y Huang, Z Shao, C Liu - Journal of Visual Communication and …, 2021 - Elsevier
Video action recognition is an important topic in computer vision tasks. Most of the existing
methods use CNN-based models, and multiple modalities of image features are captured …

Event-based diffractive neural network chip for dynamic action recognition

Z Li, H Su, B Li, H Luan, M Gu, X Fang - Optics & Laser Technology, 2024 - Elsevier
Dynamic action recognition has promising applications in human–computer interaction,
information encryption, and high-speed image processing. However, it is challenging for a …