3D Convolutional Neural Networks for Human Action Recognition

  title={3D Convolutional Neural Networks for Human Action Recognition},
  author={S. Ji and W. Xu and Ming Yang and Kai Yu},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  • S. Ji, W. Xu, +1 author Kai Yu
  • Published 2013
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • We consider the automated recognition of human actions in surveillance videos. [...] Key Method This model extracts features from both the spatial and the temporal dimensions by performing 3D convolutions, thereby capturing the motion information encoded in multiple adjacent frames. The developed model generates multiple channels of information from the input frames, and the final feature representation combines information from all channels.Expand Abstract
    3,262 Citations
    Using 3D convolutional neural network in surveillance videos for recognizing human actions
    • 2
    • PDF
    A 2D Convolutional Neural Network Approach for Human Action Recognition
    Human Action Recognition by Fusion of Convolutional Neural Networks and spatial-temporal Information
    • 1
    • Highly Influenced
    Human Action Recognition based on Convolutional Neural Networks with a Convolutional Auto-Encoder
    • 15
    • PDF
    Skeleton-Based Human Action Recognition Using Spatial Temporal 3D Convolutional Neural Networks
    • Juanhui Tu, M. Liu, H. Liu
    • Computer Science
    • 2018 IEEE International Conference on Multimedia and Expo (ICME)
    • 2018
    • 5
    • PDF
    Action Recognition with Image Based CNN Features
    • 41
    • PDF
    Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition
    • 40
    • PDF
    Fully convolutional networks for action recognition
    • 17
    Asymmetric 3D Convolutional Neural Networks for action recognition
    • 50
    • Highly Influenced
    • PDF


    Human Tracking Using Convolutional Neural Networks
    • 269
    • PDF
    Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin
    • Y. Wang, G. Mori
    • Computer Science, Medicine
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2011
    • 199
    • PDF
    Human action detection by boosting efficient motion features
    • 31
    • PDF
    Learning realistic human actions from movies
    • 3,376
    • PDF
    Detecting human actions in surveillance videos
    • 31
    • PDF
    Human Action Recognition Using a Modified Convolutional Neural Network
    • 42
    Recognizing realistic actions from videos
    • 207
    Evaluation of Local Spatio-temporal Features for Action Recognition
    • 1,383
    • PDF