Where's Waldo: Matching People in Images of Crowds
Abstract
Given a community-contributed set of photos of a
crowded public event, this paper addresses the problem of
finding all images of each person in the scene. This problem
is very challenging due to large changes in camera viewpoints,
severe occlusions, low resolution and photos from
tens or hundreds of different photographers. Despite these
challenges, the problem is made tractable by exploiting a
variety of visual and contextual cues – appearance, timestamps,
camera pose and co-occurrence of people. This paper
demonstrates an approach that integrates these cues to
enable high quality person matching in community photo
collections downloaded from Flickr.com.
Cite
@inproceedings{where-s-waldo-matching-people-in-images-of-2011,
author = {Rahul Garg and Deva Ramanan and Steve Seitz and Noah Snavely},
title = {Where's Waldo: Matching People in Images of Crowds},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2011},
doi = {10.1109/cvpr.2011.5995546},
url = {https://doi.org/10.1109/cvpr.2011.5995546},
}