Parsing Occluded People by Flexible Compositions
Name
CBMM-Memo-034.pdf
Size
5.54 MB
Format
Adobe PDF
Checksum (MD5)
663a871dfba6a16b8f702042c4ba5e2a
Author(s)
Chen, Xianjie
Yuille, Alan L.
Date Issued
June 1, 2015
Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1412.1526
Series/Report no.
CBMM Memo Series;034
Abstract
This paper presents an approach to parsing humans when there is significant occlusion. We model humans using a graphical model which has a tree structure building on recent work [32, 6] and exploit the connectivity prior that, even in presence of occlusion, the visible nodes form a connected subtree of the graphical model. We call each connected subtree a flexible composition of object parts. This involves a novel method for learning occlusion cues. During inference we need to search over a mixture of different flexible models. By exploiting part sharing, we show that this inference can be done extremely efficiently requiring only twice as many computations as searching for the entire object (i.e., not modeling occlusion). We evaluate our model on the standard benchmarked “We Are Family" Stickmen dataset and obtain significant performance improvements over the best alternative algorithms.
Subjects
Occlusion
Inference
Machine Learning
Artificial Intelligence
Terms of Use
Attribution-NonCommercial 3.0 United States
Persistent DSpace Link
