In this paper we propose a new wavelet transform applicable to functions defined on graphs, high dimensional data and networks. The proposed method generalizes the Haar-like transf...
In this paper, we propose a novel framework for contour based object detection. Compared to previous work, our contribution is three-fold. 1) A novel shape matching scheme suitabl...
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....
Many recent keypoint detectors associate a local scale (for multiscale detectors) or even a full affine frame (for affine-invariant detectors) to each detected keypoint. Although ...
—We present a multiresolution scheme for symbol representation and recognition based on statistical shape features. We define a symbol as a set of shape points, each of which is...