Given a single outdoor image, we present a method for estimating the likely illumination conditions of the scene. In particular, we compute the probability distribution over the su...
Jean-François Lalonde, Alexei A. Efros, Srinivasa...
We present an activity recognition feature inspired by
human psychophysical performance. This feature is based
on the velocity history of tracked keypoints. We present a
generat...
Methods for super-resolution can be broadly classified
into two families of methods: (i) The classical multi-image
super-resolution (combining images obtained at subpixel
misali...
A key ingredient in the design of visual object classification
systems is the identification of relevant class specific
aspects while being robust to intra-class variations. Whil...
Object tracking typically relies on a dynamic model to
predict the object’s location from its past trajectory. In
crowded scenarios a strong dynamic model is particularly
impo...
We describe a method for producing a smooth, stabilized
video from the shaky input of a hand-held light field video camera—
specifically, a small camera array. Traditional stab...
Brandon M. Smith, Li Zhang, Hailin Jin, Aseem Agar...
We propose a novel approach to reconstruct complete
3D deformable models over time by a single depth camera,
provided that most parts of the models are observed by the
camera at...
We present methods for training high quality object detectors
very quickly. The core contribution is a pair of fast
training algorithms for piece-wise linear classifiers, which
...
High-level, or holistic, scene understanding involves
reasoning about objects, regions, and the 3D relationships
between them. This requires a representation above the
level of ...
User-provided object bounding box is a simple and
popular interaction paradigm considered by many existing
interactive image segmentation frameworks. However,
these frameworks t...
Victor Lempitsky, Pushmeet Kohli, Carsten Rother, ...