Solving Person Re-identification in Non-overlapping Camera using Efficient Gibbs Sampling thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Solving Person Re-identification in Non-overlapping Camera using Efficient Gibbs Sampling

Published on Apr 03, 20142470 Views

This paper proposes a novel probabilistic approach for appearance-based person reidentification in non-overlapping camera networks. It accounts for varying illumination, varying camera gain and has

Related categories

Chapter list

Solving Person Re-identification in Non-overlapping Cameras using Efficient Gibbs Sampling00:00
Person Re-identification: Problem Formulation - 100:19
Person Re-identification: Problem Formulation - 201:09
Person Re-identification: Algorithm Overview02:44
Person Re-identification: Probabilistic Graphical Model - 103:35
Person Re-identification: Analytical Update05:08
Person Re-identification: Probabilistic Graphical Model - 207:27
Person Re-identification: Efficient Gibbs Sampling08:45
Person Re-identification: Book Keeping - 109:55
Person Re-identification: Book Keeping - 211:53
Person Re-identification: Experimental Results - 112:21
Person Re-identification: Experimental Results - 214:47
Person Re-identification: Summary16:35
Thank you17:27