Learning From Dances: Pose-Invariant Re-Identification For Multi-Person Tracking

This video program is a part of the Premium package:

Learning From Dances: Pose-Invariant Re-Identification For Multi-Person Tracking


  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

Learning From Dances: Pose-Invariant Re-Identification For Multi-Person Tracking

0 views
  • Share
Most existing multi-person tracking approaches rely on appearance based re-identification (re-ID) to resolve the fragmented tracklets. However, simply using appearance information could be insufficient for videos containing severe pose changes, such as sp
Most existing multi-person tracking approaches rely on appearance based re-identification (re-ID) to resolve the fragmented tracklets. However, simply using appearance information could be insufficient for videos containing severe pose changes, such as sp