• Home
  • Search
  • Distinct Two-Stream Convolutional Networks for Human Action Recognition in Videos Using Segment-Based Temporal Modeling
  • Open Access IconOpen Access
  • Cite Icon22
  • https://doi.org/10.3390/data5040104Copy DOI Icon

Distinct Two-Stream Convolutional Networks for Human Action Recognition in Videos Using Segment-Based Temporal Modeling

  • Nov 11, 2020
  • Data
  • Ashok Sarabu +1 more
Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The Two-stream convolution neural network (CNN) has proven a great success in action recognition in videos. The main idea is to train the two CNNs in order to learn spatial and temporal features separately, and two scores are combined to obtain final scores. In the literature, we observed that most of the methods use similar CNNs for two streams. In this paper, we design a two-stream CNN architecture with different CNNs for the two streams to learn spatial and temporal features. Temporal Segment Networks (TSN) is applied in order to retrieve long-range temporal features, and to differentiate the similar type of sub-action in videos. Data augmentation techniques are employed to prevent over-fitting. Advanced cross-modal pre-training is discussed and introduced to the proposed architecture in order to enhance the accuracy of action recognition. The proposed two-stream model is evaluated on two challenging action recognition datasets: HMDB-51 and UCF-101. The findings of the proposed architecture shows the significant performance increase and it outperforms the existing methods.

Loading PDF

Similar Papers
  • Book Chapter
  • Citations9

Multi-stream with Deep Convolutional Neural Networks for Human Action Recognition in Videos

  • Jan 01, 2018
  • Xiao Liu +1
  • Research Article
  • Citations6

Analysis of CNN Architectures for Human Action Recognition in Video

  • Jun 30, 2022
  • Computación y Sistemas
  • David Silva +4
  • Conference Article
  • Citations3

Human action recognition in surveillance video of a computer laboratory

  • Aug 01, 2016
  • Abdul-Lateef Yussiff +2
  • PDF
  • Research Article
  • Citations52

Analysis of Deep Neural Networks for Human Activity Recognition in Videos—A Systematic Literature Review

  • Jan 01, 2021
  • IEEE Access
  • Hadiqa Aman Ullah +4
  • Research Article
  • Citations8

Learning correlations for human action recognition in videos

  • Feb 10, 2017
  • Multimedia Tools and Applications
  • Yun Yi +2
  • Book Chapter

Action Recognition in Haze Using an Efficient Fusion of Spatial and Temporal Features

  • Jan 01, 2021
  • Sri Girinadh Tanneru +1
  • Conference Article
  • Citations33

SCNN: Sequential convolutional neural network for human action recognition in videos

  • Sep 01, 2017
  • Hao Yang +3
  • Book Chapter
  • Citations2

Exploiting Sub-region Deep Features for Specific Action Recognition in Combat Sports Video

  • Jan 01, 2018
  • Yongqiang Kong +4
  • Conference Article

Global evaluate-and-rescale network: an efficient model for action recognition

  • Jan 31, 2020
  • Jianbang Qin +2
  • Research Article
  • Citations49

A fast human action recognition network based on spatio-temporal features

  • Nov 24, 2020
  • Neurocomputing
  • Jie Xu +5
  • Dissertation

Robust and efficient deep learning methods for vision-based action recognition

  • Jan 01, 2021
  • Yuecong Xu
  • Research Article
  • Citations9

Learning Video Actions in Two Stream Recurrent Neural Network

  • Nov 01, 2021
  • Pattern Recognition Letters
  • Ehtesham Hassan
  • Research Article
  • Citations5

Human Action Recognition Using Spatio-Temporal Multiplier Network and Attentive Correlated Temporal Feature

  • Oct 06, 2021
  • International Journal of Image and Graphics
  • C Indhumathi +2
  • Research Article

A Detail Study of Support Vector Machine, K-Nearest Neighbours and Convolutional Neural Network for Human Action Recognition in Videos

  • May 28, 2025
  • Power System Technology
  • Tammmarguddi Mahmad Husen, Swamy L N
  • Research Article
  • Citations96

Region-sequence based six-stream CNN features for general and fine-grained human action recognition in videos

  • Nov 21, 2017
  • Pattern Recognition
  • Miao Ma +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.