Using linking features in learning non-parametric part models thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Using linking features in learning non-parametric part models

Published on Nov 12, 20123192 Views

We present an approach to the detection of parts of highly deformable objects, such as the human body. Instead of using kinematic constraints on relative angles used by most existing approaches for mo

Related categories

Chapter list

Using linking features in learning non-parametric part models00:00
Introduction (1)00:05
Introduction (2)00:16
Introduction (3)00:21
Pictorial Structures00:24
General Intuition (1)01:00
General Intuition (2)01:17
General Intuition (3)01:26
Linking Features01:41
The linking features method (1)02:13
The linking features method (2)02:36
The linking features method (3)03:02
Detecting part candidates (1)03:11
Detecting part candidates (2)03:23
Detecting part candidates (3)03:55
Detecting part candidates (3)04:09
The FLPM (1)04:29
The FLPM (2)04:53
The FLPM (3)05:20
The FLPM (4)05:50
The FLPM (5)05:56
Experiments06:22
Upper body – PASCAL dataset (v1.1)06:24
Upper body – PASCAL dataset (v2.1)07:06
Upper body – FAQ ...07:27
Facial Landmarks – the AR dataset08:52
Summary09:32
The End and Questions10:41