Object recognition can be formulated as matching image features to model features. When recognition is exemplar-based, feature correspondence is one-to-one. However, segmentation e...
M. Fatih Demirci, Ali Shokoufandeh, Yakov Keselman...
Abstract. We present a new shape descriptor for measuring the similarity between shapes and exploit it in graphical object recognition and retrieval. By statistically integrating t...
Abstract. In the pattern recognition context, objects can be represented as graphs with attributed nodes and edges involving their relations. Consequently, matching attributed grap...
W e introduce a novel view-based object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavele...
3D human pose recovery is considered as a fundamental step in view-invariant human action recognition. However, inferring 3D poses from a single view usually is slow due to the la...