@conference{Altwaijry2016b,
title = {Learning to Detect and Match Keypoints with Deep Architectures},
author = {Hani Altwaijry and Andreas Veit and Serge Belongie},
url = {http://vision.cornell.edu/se3/wp-content/uploads/2016/08/learning-detect-match.pdf},
year = {2016},
date = {2016-09-19},
booktitle = {British Machine Vision Conference (BMVC)},
address = {York, UK},
keywords = {}
}

@conference{Altwaijry2016,
title = {Learning to Match Aerial Images with Deep Attentive Architectures},
author = {Hani Altwaijry and Eduard Trulls and James Hays and Pascal Fua and Serge Belongie},
url = {http://vision.cornell.edu/se3/wp-content/uploads/2016/04/1204.pdf},
year = {2016},
date = {2016-06-27},
booktitle = {Computer Vision and Pattern Recognition (CVPR)},
address = {Las Vegas, NV},
keywords = {}
}

@inproceedings{488,
title = {Recognizing Locations with Google Glass: A Case Study},
author = {Hani Altwaijry and Mohammad Moghimi and Serge Belongie},
url = {/se3/wp-content/uploads/2014/09/recognizing_locations_altwaijry_web.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
address = {Steamboat Springs, Colorado},
keywords = {}
}

@inproceedings{455,
title = {Relative Ranking of Facial Attractiveness},
author = {Hani Altwaijry and Serge Belongie},
url = {/se3/wp-content/uploads/2014/09/043-wacv.pdf},
year = {2013},
date = {2013-01-01},
booktitle = {Workshop on the Applications of Computer Vision (WACV)},
address = {Clearwater Beach, Florida},
abstract = {Automatic evaluation of human facial attractiveness is a challenging problem that has received relatively little attention from the computer vision community. Previous work in this area had posed attractiveness as a classification problem. However, for applications that require fine-grained relationships between objects, learning to rank has been shown to be superior over the direct interpretation of classifier scores as ranks [27]. In this paper, we propose and implement a personalized relative beauty ranking system. Given training data of faces sorted based on a subjecttextquoterights personal taste, we learn how to rank novel faces according to that persontextquoterights taste. Using a blend of Facial Geometric Relations, HOG, GIST, L*a*b* Color Histograms, and Dense-SIFT + PCA feature types, our system achieves an average accuracy of 63% on pairwise comparisons of novel test faces. We examine the effectiveness of our method through lesion testing and find that the most effective feature types for predicting beauty preferences are HOG, GIST, and Dense-SIFT + PCA features.},
keywords = {}
}

@inproceedings{469,
title = {Ultra-wide Baseline Aerial Imagery Matching in Urban Environments},
author = {Hani Altwaijry and Serge Belongie},
url = {/se3/wp-content/uploads/2014/09/bmvc2013_ultrawide_matching.pdf},
year = {2013},
date = {2013-01-01},
booktitle = {British Machine Vision Conference (BMVC)},
address = {Bristol},
keywords = {}
}