I've seen the term "poselet" mentioned a few times (e.g. A and B) as some sort of construct used in facial recognition.
Asked
Active
Viewed 865 times
3
-
1Your reference "B" explains that it's a construct *specific* to facial recognition. – whuber Feb 17 '16 at 18:03
-
1@whuber Ah, I see what you're saying, I've edited my question to reflect this. – Esteemator Feb 17 '16 at 18:09
1 Answers
1
The short answer is:
A poselet describes a particular part of the human pose under a given viewpoint.
The quote comes from this paper "Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations" where I think the term may have been coined.
In the paper mentioned above, they are used as intermediate features in a computer vision pipeline for torso detection, keypoint detection, and people detection. The researchers train a large number of SVM models to identify specific poselets, which are then fed as features into a final top level model which performs the learning tasks. You could see this as feature engineering for a task-specific type of model stacking.
MachineEpsilon
- 2,686
- 1
- 17
- 29