Sciweavers

330 search results - page 49 / 66
» Learning Features by Contrasting Natural Images with Noise
Sort
View
TIP
2008
169views more  TIP 2008»
13 years 7 months ago
Weakly Supervised Learning of a Classifier for Unusual Event Detection
In this paper, we present an automatic classification framework combining appearance based features and Hidden Markov Models (HMM) to detect unusual events in image sequences. One...
Mark Jager, Christian Knoll, Fred A. Hamprecht
ICCV
2005
IEEE
14 years 1 months ago
Learning Hierarchical Models of Scenes, Objects, and Parts
We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the e...
Erik B. Sudderth, Antonio B. Torralba, William T. ...
CVPR
2011
IEEE
13 years 4 months ago
On Deep Generative Models with Applications to Recognition
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to...
Marc', Aurelio Ranzato, Joshua Susskind, Volodymyr...
ECCV
2010
Springer
13 years 10 months ago
Object Segmentation by Long Term Analysis of Point Trajectories
Unsupervised learning requires a grouping step that defines which data belong together. A natural way of grouping in images is the segmentation of objects or parts of objects. Whi...
WACV
2008
IEEE
14 years 2 months ago
Mosaicfaces: a discrete representation for face recognition
Most face recognition algorithms use a “distancebased” approach: gallery and probe images are projected into a low dimensional feature space and decisions about matching are b...
Jania Aghajanian, Simon J. D. Prince