Skip to Main Content Area
  • CPS-VO
    • Contact Support
  • Browse
    • Calendar
    • Announcements
    • Repositories
    • Groups
  • Search
    • Search for Content
    • Search for a Group
    • Search for People
    • Search for a Project
    • Tagcloud
      
 
Not a member?
Click here to register!
Forgot username or password?
 
Home
National Science Foundation

Cyber-Physical Systems Virtual Organization

Read-only archive of site from September 29, 2023.

CPS-VO

MSTRNN model aid

biblio

Visible to the public Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks

Submitted by grigby1 on Mon, 10/05/2020 - 2:01pm
  • RGB input data
  • MSTRNN model aid
  • multiple spatio-temporal scales recurrent neural network model
  • multiple timescale recurrent dynamics
  • neural activities
  • pubcrawl
  • recurrent neural nets
  • recurrent neural network
  • Recurrent neural networks
  • learning (artificial intelligence)
  • spatio-temporal constraints
  • spatio-temporal information extraction
  • Spatiotemporal phenomena
  • symbol grounding
  • Training
  • visualization
  • visually perceived compositional human action recognition
  • different compositionality levels
  • Biological neural networks
  • Compositionality
  • conventional convolutional neural network model
  • convolution
  • Convolutional codes
  • convolutional neural network (CNN)
  • critical spatio-temporal information
  • deep learning model
  • action recognition
  • dynamic vision processing
  • feature extraction
  • feedforward neural nets
  • gesture recognition
  • human action datasets
  • image motion analysis
  • image representation

Terms of Use  |  ©2023. CPS-VO