The classical optical flow assumes that a feature point maintains constant brightness across the frames. For fluidtype motions such as smoke or clouds, the constant brightness ass...
In this paper we investigate shape and motion retrieval in the context of multi-camera systems. We propose a new lowlevel analysis based on latent silhouette cues, particularly su...
Li Guan, Jean-Sebastien Franco, Edmond Boyer, Marc...
We present an effective method to optimize over the parameters of an image patch descriptor to obtain one that is computationally more efficient while maintaining a high recogniti...
We address the problem of object detection and segmentation using holistic properties of object shape. Global shape representations are highly susceptible to clutter inevitably pr...
The traditional SPM approach based on bag-of-features (BoF) must use nonlinear classifiers to achieve good image classification performance. This paper presents a simple but effec...
Ink-bleed interference is undesirable as it reduces the legibility and aesthetics of affected documents. We present a novel approach to reduce ink-bleed interference using functio...
Grani Adiwena Hanasusanto, Michael Brown, Zheng Wu
This paper overviews a new gesture recognition framework
based on learning local motion signatures (LMSs) introduced
by [1]. After the generation of these LMSs computed
on one i...
Interactive segmentation is useful for selecting objects of interest in images and continues to be a topic of much study. Methods that grow regions from foreground/background seed...
Many applications need to segment out all small round
regions in an image. This task of finding dots can be viewed
as a region segmentation problem where the dots form one
regio...
Two challenges in computer vision are to accommodate noisy data and missing data. Many problems in computer vision, such as segmentation, filtering, stereo, reconstruction, inpain...