We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts co...
This paper presents a new, accurate, efficient and unified method for dynamic animation of one, two or three-dimensional deformable objects. The objects are modelled as d-dimensio...
Abstract: Most modern computer applications should run on heterogeneous platforms and, moreover, objects and respective code should be easily interchangeable between distinct platf...
—In this work, we address the problem of performing class-specific unsupervised object segmentation, i.e., automatic segmentation without annotated training images. Object segmen...
This paper addresses real-time automatic visual tracking,
labeling and classification of a variable number of
objects such as pedestrians or/and vehicles, under timevarying
illu...