DMCA
Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
Cached
Download Links
| Citations: | 14 - 5 self |
BibTeX
@MISC{Chen_detectwhat,
author = {Xianjie Chen and Roozbeh Mottaghi and Xiaobai Liu and Sanja Fidler and Raquel Urtasun and Alan Yuille},
title = {Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Detecting objects becomes difficult when we need to deal with large shape deformation, occlusion and low resolu-tion. We propose a novel approach to i) handle large de-formations and partial occlusions in animals (as examples of highly deformable objects), ii) describe them in terms of body parts, and iii) detect them when their body parts are hard to detect (e.g., animals depicted at low resolution). We represent the holistic object and body parts separately and use a fully connected model to arrange templates for the holistic object and body parts. Our model automatically decouples the holistic object or body parts from the model when they are hard to detect. This enables us to represent a large number of holistic object and body part combinations to better deal with different “detectability ” patterns caused by deformations, occlusion and/or low resolution. We apply our method to the six animal categories in the PASCAL VOC dataset and show that our method signifi-cantly improves state-of-the-art (by 4.1 % AP) and provides a richer representation for objects. During training we use annotations for body parts (e.g., head, torso, etc), making use of a new dataset of fully annotated object parts for PAS-CAL VOC 2010, which provides a mask for each part. 1.
Keyphrases
body part holistic object holistic model representing object low resolution object part low resolu-tion different detectability pattern new dataset large shape deformation large de-formations pascal voc dataset method signifi-cantly improves deformable object body part combination novel approach animal category pas-cal voc large number partial occlusion
