Learn More
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. While this is a necessity in order to generalize beyond a given set of training images, it is also a very difficult problem due to the high variability of visual appearance within each(More)
Entertainment and gaming systems such as the Wii and XBox Kinect have brought touchless, body-movement based interfaces to the masses. Systems like these enable the estimation of movements of various body parts from raw inertial motion or depth sensor data. However, the interface developer is still left with the challenging task of creating a system that(More)
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 histogram representation, discarding the temporal order among features. But this ordering information can contain important information about the action itself e.g. consider the(More)
Most modern computer vision systems for high-level tasks, such as image classification, object recognition and segmentation, are based on learning algorithms that are able to separate discriminative information from noise. In practice, however, the typical system consists of a long pipeline of pre-processing steps, such as extraction of different kinds of(More)
This supplementary document contains results that were omitted from the main paper due to a lack of space. In particular, we provide a closer look at the denoising quality of our method, as well as several exemplary predictions by all of our systems and its competitors, on the following tasks: 1. denoising (at all noise levels); 2. JPEG deblocking (at all(More)
R in sample Vol. xx, No xx (xxxx) 1–175 c xxxx xxxxxxxxx DOI: xxxxxx Abstract Powerful statistical models that can be learned efficiently from large amounts of data are currently revolutionizing computer vision. These models possess a rich internal structure reflecting task-specific relations and constraints. This tutorial introduces the reader to the most(More)
We introduce Regression Tree Fields (RTFs), a fully conditional random field model for image labeling problems. RTFs gain their expressive power from the use of non-parametric regression trees that specify a tractable Gaus-sian random field, thereby ensuring globally consistent predictions. Our approach improves on the recently introduced decision tree(More)
This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fields (CRF) which have been widely used in computer vision. In a typical CRF model the unary potentials are derived from sophisticated random forest or boosting based classifiers,(More)
Even years ago, Szeliski et al. published an influential study on energy minimization methods for Markov random fields (MRF). This study provided valuable insights in choosing the best optimization technique for certain classes of problems. While these insights remain generally useful today, the phenominal success of random field models means that the kinds(More)
Graph mining methods enumerate frequently appearing subgraph patterns, which can be used as features for subsequent classification or regression. However, frequent patterns are not necessarily informative for the given learning problem. We propose a mathematical programming boosting method (gBoost) that progressively collects informative patterns. Compared(More)