Abstract. Subspace mapping methods aim at projecting high-dimensional data into a subspace where a specific objective function is optimized. Such dimension reduction allows the re...
Axel J. Soto, Marc Strickert, Gustavo E. Vazquez, ...
Recent approaches to action classification in videos have used sparse spatio-temporal words encoding local appearance around interesting movements. Most of these approaches use a ...
The paper describes a method for automatically extracting informative feature hierarchies for object classification, and shows the advantage of the features constructed hierarchic...
A requirement common to most dynamic vision applications is the ability to track objects in a sequence of frames. This problem has been extensively studied in the past few years, ...
Octavia I. Camps, Hwasup Lim, Cecilia Mazzaro, Mar...
In this paper we show that efficient object recognition can be obtained by combining informative features with linear classification. The results demonstrate the superiority of in...