Pose Induction for Novel Object Categories

Shubham Tulsiani, Joao Carreira, Jitendra Malik

ICCV 2015

doi:10.1109/ICCV.2015.16 /iccv/2015/tulsiani2015iccv-pose/

Abstract

We address the task of predicting pose for objects of unannotated object categories from a small seed set of annotated object classes. We present a generalized classifier that can reliably induce pose given a single instance of a novel category. In case of availability of a large collection of novel instances, our approach then jointly reasons over all instances to improve the initial estimates. We empirically validate the various components of our algorithm and quantitatively show that our method produces reliable pose estimates. We also show qualitative results on a diverse set of classes and further demonstrate the applicability of our system for learning shape models of novel object classes.

PDF ICCV Semantic Scholar

Cite

Text

Tulsiani et al. "Pose Induction for Novel Object Categories." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.16

Markdown

[Tulsiani et al. "Pose Induction for Novel Object Categories." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/tulsiani2015iccv-pose/) doi:10.1109/ICCV.2015.16

BibTeX

@inproceedings{tulsiani2015iccv-pose,
  title     = {{Pose Induction for Novel Object Categories}},
  author    = {Tulsiani, Shubham and Carreira, Joao and Malik, Jitendra},
  booktitle = {International Conference on Computer Vision},
  year      = {2015},
  doi       = {10.1109/ICCV.2015.16},
  url       = {https://mlanthology.org/iccv/2015/tulsiani2015iccv-pose/}
}