Skip to content
GitLab
Projects Groups Snippets
  • /
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in
  • bob.pad.face bob.pad.face
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 1
    • Issues 1
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 0
    • Merge requests 0
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Packages and registries
    • Packages and registries
    • Package Registry
    • Infrastructure Registry
  • Monitor
    • Monitor
    • Incidents
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • bobbob
  • bob.pad.facebob.pad.face
  • Issues
  • #26
Closed
Open
Issue created Nov 26, 2018 by Amir MOHAMMADI@amohammadiOwner

Frame-level scoring is the default for (some) baselines?

Recently I noticed that the SVM PAD algorithm dumps scores as a frame-level basis and it is used by default in some baselines (e.g. qm-svm). However the evaluation using this frame-level analysis is much worse compared to video-level scoring. For example, I saw the EER decrease from 28% to 15% when switching to video-level scoring. Shouldn't we change the defaults in our baselines?

Assignee
Assign to
Time tracking