Discovering States and Transformations in Image Collections
Abstract
Objects in visual scenes come in a rich variety of transformed states. A few classes of transformation have been heavily studied in computer vision: mostly simple, parametric changes in color and geometry. However, transformations in the physical world occur in many more flavors, and they come with semantic meaning: e.g., bending, folding, aging, etc. The transformations an object can undergo tell us about its physical and functional properties. In this paper, we introduce a dataset of objects, scenes, and materials, each of which is found in a variety of transformed states. Given a novel collection of images, we show how to explain the collection in terms of the states and transformations it depicts. Our system works by generalizing across object classes: states and transformations learned on one set of objects are used to interpret the image collection for an entirely new object class.
Cite
Text
Isola et al. "Discovering States and Transformations in Image Collections." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298744Markdown
[Isola et al. "Discovering States and Transformations in Image Collections." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/isola2015cvpr-discovering/) doi:10.1109/CVPR.2015.7298744BibTeX
@inproceedings{isola2015cvpr-discovering,
title = {{Discovering States and Transformations in Image Collections}},
author = {Isola, Phillip and Lim, Joseph J. and Adelson, Edward H.},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2015},
doi = {10.1109/CVPR.2015.7298744},
url = {https://mlanthology.org/cvpr/2015/isola2015cvpr-discovering/}
}