1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Learning From Dances: Pose-Invariant Re-Identification For Multi-Person Tracking

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

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

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

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

Purchase

Videos in this product

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

00:12:43

0 views

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