Sciweavers

CVPR
2012
IEEE
11 years 7 months ago
Image matching using local symmetry features
We present a new technique for extracting local features from images of architectural scenes, based on detecting and representing local symmetries. These new features are motivate...
Daniel Cabrini Hauagge, Noah Snavely
PAMI
2012
11 years 7 months ago
Tracking-Learning-Detection
A novel system for long-term tracking of a human face in unconstrained videos is built on Tracking-Learning-Detection (TLD) approach. The system extends TLD with the concept of a ...
Zdenek Kalal, Krystian Mikolajczyk, Jiri Matas
ICCV
2011
IEEE
12 years 5 months ago
An adaptive coupled-layer visual model for robust visual tracking
This paper addresses the problem of tracking objects which undergo rapid and significant appearance changes. We propose a novel coupled-layer visual model that combines the targe...
Luka Cehovin, Matej Kristan, Ales Leonardis
ECCV
2008
Springer
14 years 6 months ago
Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers
Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion. Also, an object may leave the fie...
Gérard G. Medioni, Qian Yu, Thang Ba Dinh
ECCV
2008
Springer
14 years 6 months ago
Learning to Recognize Activities from the Wrong View Point
Appearance features are good at discriminating activities in a fixed view, but behave poorly when aspect is changed. We describe a method to build features that are highly stable u...
Ali Farhadi, Mostafa Kamali Tabrizi
ICCV
1998
IEEE
14 years 7 months ago
A Framework for Modeling Appearance Change in Image Sequences
Image "appearance" may change over time due to a variety of causes such as 1) object or camera motion; 2) generic photometric events including variations in illumination...
Michael J. Black, David J. Fleet, Yaser Yacoob
CVPR
2007
IEEE
14 years 7 months ago
Change Detection in a 3-d World
This paper examines the problem of detecting changes in a 3-d scene from a sequence of images, taken by cameras with arbitrary but known pose. No prior knowledge of the state of n...
Thomas Pollard, Joseph L. Mundy