Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle
This paper introduces a new operator to characterize a point in an image in a distinctive and invariant way. The robust recognition of points is a key technique in computer vision:...
Recognizing multiple interleaved activities in a video requires implicitly partitioning the detections for each activity. Furthermore, constraints between activities are important ...
Shape analysis requires invariance under translation, scale and rotation. Translation and scale invariance can be realized by normalizing shape vectors with respect to their mean ...
A new feature descriptor is presented for object and scene recognition. The new approach, called CDIKP, uniquely combines the scale-invariant feature detection with a robust proje...