Pose Estimation Errors, the Ultimate Diagnosis
Abstract
This paper proposes a thorough diagnosis for the problem of object detection and pose estimation. We provide a diagnostic tool to examine the impact in the performance of the different types of false positives, and the effects of the main object characteristics. We focus our study on the PASCAL 3D+ dataset, developing a complete diagnosis of four different state-of-the-art approaches, which span from hand-crafted models, to deep learning solutions. We show that gaining a clear understanding of typical failure cases and the effects of object characteristics on the performance of the models, is fundamental in order to facilitate further progress towards more accurate solutions for this challenging task.
Cite
Text
Redondo-Cabrera et al. "Pose Estimation Errors, the Ultimate Diagnosis." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46478-7_8Markdown
[Redondo-Cabrera et al. "Pose Estimation Errors, the Ultimate Diagnosis." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/redondocabrera2016eccv-pose/) doi:10.1007/978-3-319-46478-7_8BibTeX
@inproceedings{redondocabrera2016eccv-pose,
title = {{Pose Estimation Errors, the Ultimate Diagnosis}},
author = {Redondo-Cabrera, Carolina and López-Sastre, Roberto Javier and Xiang, Yu and Tuytelaars, Tinne and Savarese, Silvio},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {118-134},
doi = {10.1007/978-3-319-46478-7_8},
url = {https://mlanthology.org/eccv/2016/redondocabrera2016eccv-pose/}
}