#### Filter Results:

- Full text PDF available (297)

#### Publication Year

1993

2017

- This year (13)
- Last 5 years (83)
- Last 10 years (170)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Key Phrases

Learn More

- Brian Fulkerson, Andrea Vedaldi, Stefano Soatto
- 2009 IEEE 12th International Conference on…
- 2009

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)

- Payam Saisan, Gianfranco Doretto, Ying Nian Wu, Stefano Soatto
- CVPR
- 2001

Dynamic textures are sequences of images that exhibit some form of temporal stationarity, such as waves, steam, and foliage. We pose the problem of recognizing and classifying dynamic textures in the space of dynamical systems where each dynamic texture is uniquely represented. Since the space is non-linear, a distance between models must be defined. We… (More)

- Andrea Vedaldi, Stefano Soatto
- ECCV
- 2008

We show that the complexity of the recently introduced medoid-shift algorithm in clustering N points is O(N), with a small constant, if the underlying distance is Euclidean. This makes medoid shift considerably faster than mean shift, contrarily to what previously believed. We then exploit kernel methods to extend both mean shift and the improved medoid… (More)

- Daniel Cremers, Stanley Osher, Stefano Soatto
- International Journal of Computer Vision
- 2006

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)

- Stefano Soatto, Gianfranco Doretto, Ying Nian Wu
- International Journal of Computer Vision
- 2001

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)

- Michalis Raptis, Iasonas Kokkinos, Stefano Soatto
- 2012 IEEE Conference on Computer Vision and…
- 2012

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)

- Haibin Ling, Stefano Soatto
- 2007 IEEE 11th International Conference on…
- 2007

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)

- Alessandro Chiuso, Paolo Favaro, Hailin Jin, Stefano Soatto
- IEEE Trans. Pattern Anal. Mach. Intell.
- 2002

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)

- Brian Fulkerson, Andrea Vedaldi, Stefano Soatto
- ECCV
- 2008

We present an approach to determine the category and location of objects in images. It performs very fast categorization of each pixel in an image, a brute-force approach made feasible by three key developments: First, our method reduces the size of a large generic dictionary (on the order of ten thousand words) to the low hundreds while increasing… (More)