Skip to content

  • Projects
  • Groups
  • Snippets
  • Help
    • Loading...
    • Help
    • Support
    • Submit feedback
    • Contribute to GitLab
  • Sign in
bob.pad.face
bob.pad.face
  • Project overview
    • Project overview
    • Details
    • Activity
    • Releases
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 13
    • Issues 13
    • List
    • Boards
    • Labels
    • Milestones
  • Merge Requests 2
    • Merge Requests 2
  • CI / CD
    • CI / CD
    • Pipelines
    • Jobs
    • Schedules
  • Analytics
    • Analytics
    • CI / CD
    • Repository
    • Value Stream
  • Members
    • Members
  • Collapse sidebar
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
  • bob
  • bob.pad.facebob.pad.face
  • Issues
  • #26

Closed
Open
Opened Nov 26, 2018 by Amir MOHAMMADI@amohammadi
  • Report abuse
  • New issue
Report abuse New issue

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
None
Milestone
None
Assign milestone
Time tracking
None
Due date
None
0
Labels
None
Assign labels
  • View project labels
Reference: bob/bob.pad.face#26