TY - GEN
T1 - A latent model of discriminative aspect
AU - Farhadi, Ali
AU - Tabrizi, Mostafa Kamali
AU - Endres, Ian
AU - Forsyth, David
N1 - Copyright:
Copyright 2010 Elsevier B.V., All rights reserved.
PY - 2009
Y1 - 2009
N2 - Recognition using appearance features is confounded by phenomena that cause images of the same object to look different, or images of different objects to look the same. This may occur because the same object looks different from different viewing directions, or because two generally different objects have views from which they look similar. In this paper, we introduce the idea of discriminative aspect, a set of latent variables that encode these phenomena. Changes in view direction are one cause of changes in discriminative aspect, but others include changes in texture or lighting. However, images are not labelled with relevant discriminative aspect parameters. We describe a method to improve discrimination by inferring and then using latent discriminative aspect parameters. We apply our method to two parallel problems: object category recognition and human activity recognition. In each case, appearance features are powerful given appropriate training data, but traditionally fail badly under large changes in view. Our method can recognize an object quite reliably in a view for which it possesses no training example. Our method also reweights features to discount accidental similarities in appearance. We demonstrate that our method produces a significant improvement on the state of the art for both object and activity recognition.
AB - Recognition using appearance features is confounded by phenomena that cause images of the same object to look different, or images of different objects to look the same. This may occur because the same object looks different from different viewing directions, or because two generally different objects have views from which they look similar. In this paper, we introduce the idea of discriminative aspect, a set of latent variables that encode these phenomena. Changes in view direction are one cause of changes in discriminative aspect, but others include changes in texture or lighting. However, images are not labelled with relevant discriminative aspect parameters. We describe a method to improve discrimination by inferring and then using latent discriminative aspect parameters. We apply our method to two parallel problems: object category recognition and human activity recognition. In each case, appearance features are powerful given appropriate training data, but traditionally fail badly under large changes in view. Our method can recognize an object quite reliably in a view for which it possesses no training example. Our method also reweights features to discount accidental similarities in appearance. We demonstrate that our method produces a significant improvement on the state of the art for both object and activity recognition.
UR - http://www.scopus.com/inward/record.url?scp=77953218597&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77953218597&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2009.5459350
DO - 10.1109/ICCV.2009.5459350
M3 - Conference contribution
AN - SCOPUS:77953218597
SN - 9781424444205
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 948
EP - 955
BT - 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009
T2 - 12th International Conference on Computer Vision, ICCV 2009
Y2 - 29 September 2009 through 2 October 2009
ER -