Please use this identifier to cite or link to this item:
Title: Deep historical long short-term memory network for action recognition
Authors: Cai, Jiaxin
Hu, Junlin
Tang, Xin
Tan, Yap Peng
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2020
Source: Cai, J., Hu, J., Tang, X., Hung, T. & Tan, Y. P. (2020). Deep historical long short-term memory network for action recognition. Neurocomputing, 407, 428-438.
Journal: Neurocomputing
Abstract: Human action recognition technology has received increasing interest recently. The technology is very useful in sports video analysis. Most of the action recognition methods in sports mainly focus on recognizing which sport is being performed. However, recognizing of the specific action in videos is important for the analysis of some sports video such as tennis matches. Hence, in this paper, we proposed a deep historical long short-term memory network for video-based tennis action recognition and general action recognition. First, the spatial representations are extracted from each frame using a pre-trained convolutional neural network (CNN). To describe the temporal information, a stacked multi-layer long short-term memory network (LSTM) was used. The historical information of the past frames is important for modeling the action. So we propose a historical information layer that is added to the top of the multi-layered LSTM network. A historical feature of each video is generated for classification by hybridizing the hidden state of LSTM at time t and the historical updated feature at time t-1 with an updating scheme and utilized for classification. Experiments on the benchmark datasets demonstrate that our method that using only simple raw RGB video can outperform the state-of-the-art baselines for both general action recognition and tennis action recognition.
ISSN: 0925-2312
DOI: 10.1016/j.neucom.2020.03.111
Schools: School of Electrical and Electronic Engineering 
Rights: © 2020 Elsevier B.V. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Citations 20

Updated on Sep 23, 2023

Web of ScienceTM
Citations 20

Updated on Sep 25, 2023

Page view(s)

Updated on Sep 28, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.