RoLoD 2014 - International Workshop on Robust local descriptors for computer vision 2014

There has been much interest in object and view matching using local invariant features, classification of textured regions using micro textons and in face recognition using local features. How to extract robust representations for many computer vision tasks is still a challenging problem. This workshop will focus on the developing of new robust local descriptors to extract useful feature representations for these challenges.
Topics
We encourage researchers to develop new robust local descriptors to extract useful feature representations for these challenges. We also encourage new theories and processes related to local descriptors for dealing with these challenges. We are soliciting original contributions that address a wide range of theoretical and practical issues including, but not limited to:
New local descriptors robust to noise, illuminations, scale, rotations and occlusions,
New applications of local descriptors in different domains, e.g. medical domain,
Other application in different domain, such as one dimension (1D) digital signal processing, 2D images, 3D videos and 4D videos,
Evaluations of current local descriptors.
Evaluations between the features learned by deep learning and the traditional descriptors (e.g., LBP, SIFT, HOG)
Motivation
The goal of the RoLoD Workshop 2014 is to accelerate the study of robustness of local descriptors in computer vision problems. With the increase of acceleration of digital photography and the advances in storage devices over the last decade, we have seen explosive growth in the available amount of visual data and equally explosive growth in the computational capacities for data understanding. How to extract robust representations for many computer vision tasks is still a challenging problem. This problem becomes more difficult when the data show different types of variations, e.g., noise, illuminations, scale, rotations and occlusions.