A comparison of several approaches that use graph matching and cascade filtering for landmark localisation in 3D face data is presented. For the first method, we apply the structur...
We propose a new method for handwritten word-spotting which does not require prior training or gathering examples for querying. More precisely, a model is trained "on the fly...
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
P2CS (http://www.p2cs.org) is a specialized database for prokaryotic two-component systems (TCSs), virtually ubiquitous signalling proteins which regulate a wide range of physiolo...
Mohamed Barakat, Philippe Ortet, David E. Whitwort...
We address the problem of reconstructing 3D face models from large unstructured photo collections, e.g., obtained by Google image search or from personal photo collections in iPho...