Abstract : Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. We propose to cast the training of parts as a quadratic assignment problem in which optimal correspondences between image regions and parts are automatically learned. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets: Willow actions and MIT 67 scenes.
https://hal.archives-ouvertes.fr/hal-01623148 Contributor : Frederic JurieConnect in order to contact the contributor Submitted on : Wednesday, October 25, 2017 - 9:51:56 AM Last modification on : Friday, April 8, 2022 - 4:08:03 PM Long-term archiving on: : Friday, January 26, 2018 - 12:39:55 PM