Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into...
In recent work, we presented a framework for many-to-many matching of multi-scale feature hierarchies, in which features and their relations were captured in a vertex-labeled, edge...
M. Fatih Demirci, Ali Shokoufandeh, Sven J. Dickin...
We address the problem of computing joint sparse representation of visual signal across multiple kernel-based representations. Such a problem arises naturally in supervised visual...
Image object retrieval – locating image occurrences of specific objects in large-scale image collections – is essential for manipulating the sheer amount of photos. Current s...