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

triplet-loss optimization methods

biblio

Visible to the public CNNs with cross-correlation matching for face recognition in video surveillance using a single training sample per person

Submitted by K_Hooper on Wed, 04/04/2018 - 9:56am
  • image representation
  • video surveillance
  • triplet-loss optimization methods
  • Training
  • still-to-video FR systems
  • single training sample
  • Scalability
  • Robustness
  • Resiliency
  • pubcrawl
  • Pipelines
  • optimization
  • optimisation
  • neural nets
  • matrix Hadamard product
  • adaptive weighted cross-correlation
  • image matching
  • Human behavior
  • Hadamard matrices
  • feature extraction
  • face recognition systems
  • face recognition
  • Face
  • discriminant face representations
  • cross-correlation matching
  • correlation methods
  • convolution
  • CCM-CNN parameters
  • camera distributed network

Terms of Use  |  ©2023. CPS-VO