Stefano Soatto

Learn More
We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class segmentation or pixel localization scheme. To this end, we construct a classifier on the histogram of local features found in each superpixel. We regularize this classifier by(More)
In this paper, we make two contributions to the field of level set based image segmentation. Firstly, we propose shape dissimilarity measures on the space of level set functions which are analytically invariant under the action of certain transformation groups. The invariance is obtained by an intrinsic registration of the evolving level set function. In(More)
In a broad figurative sense, vision is the inverse problem of image formation: the latter studies how objects give raise to images, while the former attempts to use images to recover a description of objects in space. Therefore, designing vision algorithms requires first developing a suitable model of image formation. Suitable in this context does not(More)
Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time; these include sea-waves, smoke, foliage, whirlwind etc. We present a characterization of dynamic textures that poses the problems of modeling, learning, recognizing and synthesizing dynamic textures on a firm analytical footing. We borrow tools(More)
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candidates for the parts of an action. The assembly of these clusters into an action class is governed by a graphical model that incorporates appearance and motion constraints for the(More)
We propose using the proximity distribution of vector- quantized local feature descriptors for object and category recognition. To this end, we introduce a novel "proximity distribution kernel" that naturally combines local geometric as well as photometric information from images. It satisfies Mercer's condition and can therefore be readily combined with a(More)
ÐWe describe an algorithm for reconstructing three-dimensional structure and motion causally, in real time from monocular sequences of images. We prove that the algorithm is minimal and stable, in the sense that the estimation error remains bounded with probability one throughout a sequence of arbitrary length. We discuss a scheme for handling occlusions(More)