Abstract--This work is dedicated to a statistical trajectorybased approach addressing two issues related to dynamic video content understanding: recognition of events and detection...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
We describe a new invariant-based data model for image databases under our approach for shape-based retrieval. The data model relies on contours description of the image shape, an...
This paper presents a geometric approach to recognizing smooth objects from their outlines. We define a signature function that associates feature vectors with objects and baseline...
Svetlana Lazebnik, Amit Sethi, Cordelia Schmid, Da...
We propose novel algorithms for the detection, segmentation, recognition, and pose estimation of threedimensional objects. Our approach initially infers geometric primitives to de...