Binge Watching: Scaling Affordance Learning From Sitcoms

July 2017

Binge Watching: Scaling Affordance Learning From Sitcoms

Conference Paper
Proceedings of (CVPR) Computer Vision and Pattern Recognition

Abstract:

In recent years, there has been a renewed interest in jointly modeling perception and action. At the core of this investigation is the idea of modeling affordances. However, when it comes to predicting affordances, even the state of the art approaches still do not use any ConvNets. Why is that? Unlike semantic or 3D tasks, there still does not exist any large-scale dataset for affordances. In this paper, we tackle the challenge of creating one of the biggest dataset for learning affordances. We use seven sitcoms to extract a diverse set of scenes and how actors interact with different objects in the scenes. Our dataset consists of more than 10K scenes and 28K ways humans can interact with these 10K images. We also propose a two-step approach to predict affordances in a new scene. In the first step, given a location in the scene we classify which of the 30 pose classes is the likely affordance pose. Given the pose class and the scene, we then use a Variational Autoencoder (VAE) to extract the scale and deformation of the pose. The VAE allows us to sample the distribution of possible poses at test time. Finally, we show the importance of large-scale data in learning a generalizable and robust model of affordances.
@conference{Wang-2017-113311,
author = {Xiaolong Wang And Rohit Girdhar And Abhinav Gupta},
title = {Binge Watching: Scaling Affordance Learning From Sitcoms},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2017},
month = {July},
pages = {3366 - 3375},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.