Has my algorithm succeeded? An evaluator for human pose estimators
<p>Most current vision algorithms deliver their output ‘as is’, without indicating whether it is correct or not. In this paper we propose <em>evaluator algorithms</em> that predict if a vision algorithm has succeeded. We illustrate this idea fo...
Main Authors: | Jammalamadaka, N, Zisserman, A, Eichner, M, Ferrari, V, Jawahar, CV |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Springer
2012
|
Similar Items
-
Video retrieval by mimicking poses
by: Jammalamadaka, N, et al.
Published: (2012) -
Human pose search using deep poselets
by: Jammalamadaka, N, et al.
Published: (2015) -
Human pose search using deep networks
by: Jammalamadaka, N, et al.
Published: (2016) -
2D Articulated Human Pose Estimation and Retrieval in (Almost) Unconstrained Still Images
by: Eichner, M, et al.
Published: (2012) -
Recurrent human pose estimation
by: Belagiannis, V, et al.
Published: (2017)