• Home
  • Search
  • Hierarchical dynamic depth projected difference images–based action recognition in videos with convolutional neural networks
  • Cite Icon17
  • https://doi.org/10.1177/1729881418825093Copy DOI Icon

Hierarchical dynamic depth projected difference images–based action recognition in videos with convolutional neural networks

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Temporal information plays a significant role in video-based human action recognition. How to effectively extract the spatial–temporal characteristics of actions in videos has always been a challenging problem. Most existing methods acquire spatial and temporal cues in videos individually. In this article, we propose a new effective representation for depth video sequences, called hierarchical dynamic depth projected difference images that can aggregate the action spatial and temporal information simultaneously at different temporal scales. We firstly project depth video sequences onto three orthogonal Cartesian views to capture the 3D shape and motion information of human actions. Hierarchical dynamic depth projected difference images are constructed with the rank pooling in each projected view to hierarchically encode the spatial–temporal motion dynamics in depth videos. Convolutional neural networks can automatically learn discriminative features from images and have been extended to video classification because of their superior performance. To verify the effectiveness of hierarchical dynamic depth projected difference images representation, we construct a hierarchical dynamic depth projected difference images–based action recognition framework where hierarchical dynamic depth projected difference images in three views are fed into three identical pretrained convolutional neural networks independently for finely retuning. We design three classification schemes in the framework and different schemes utilize different convolutional neural network layers to compare their effects on action recognition. Three views are combined to describe the actions more comprehensively in each classification scheme. The proposed framework is evaluated on three challenging public human action data sets. Experiments indicate that our method has better performance and can provide discriminative spatial–temporal information for human action recognition in depth videos.

Loading PDF

Similar Papers
  • Book Chapter

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

  • Jan 01, 2021
  • Sri Girinadh Tanneru +1
  • Conference Article
  • Citations3

Human action recognition in surveillance video of a computer laboratory

  • Aug 01, 2016
  • Abdul-Lateef Yussiff +2
  • Conference Article
  • Citations28

DarkLight Networks for Action Recognition in the Dark

  • Jun 01, 2021
  • Rui Chen +4
  • Research Article
  • Citations6

Analysis of CNN Architectures for Human Action Recognition in Video

  • Jun 30, 2022
  • Computación y Sistemas
  • David Silva +4
  • Research Article
  • Citations8

Learning correlations for human action recognition in videos

  • Feb 10, 2017
  • Multimedia Tools and Applications
  • Yun Yi +2
  • Book Chapter
  • Citations2

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

  • Jan 01, 2018
  • Yongqiang Kong +4
  • Conference Article
  • Citations33

Understanding action recognition in still images

  • Jun 01, 2020
  • Deeptha Girish +2
  • Book Chapter
  • Citations1

Action Recognition in Videos with Temporal Segments Fusions

  • Jan 01, 2020
  • Yuanye Fang +3
  • Research Article
  • Citations36

Convolutional Networks With Channel and STIPs Attention Model for Action Recognition in Videos

  • Nov 22, 2019
  • IEEE Transactions on Multimedia
  • Hanbo Wu +2
  • 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
  • Research Article
  • Citations10

GA-STIP: Action Recognition in Multi-Channel Videos With Geometric Algebra Based Spatio-Temporal Interest Points

  • Jan 01, 2018
  • IEEE Access
  • Rui Wang +4
  • Book Chapter
  • Citations9

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

  • Jan 01, 2018
  • Xiao Liu +1
  • Book Chapter
  • Citations6

Audio and Video Feature Fusion for Activity Recognition in Unconstrained Videos

  • Jan 01, 2006
  • José Lopes +1
  • Conference Article

Accelerated action recognition and segmentation in videos

  • Apr 07, 2021
  • Emna Ghodhbani +2
  • Dissertation

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

  • Jan 01, 2021
  • Yuecong Xu
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.