We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3...
Gabriel J. Brostow, Jamie Shotton, Julien Fauqueur...
—In this paper, a new model that can ultimately create its own set of perceptual features is proposed. Using a bidirectional associative memory (BAM)-inspired architecture, the r...
In recent years there has been substantial work on the important problem of coreference resolution, most of which has concentrated on the development of new models and algorithmic...
Objects can exhibit different dynamics at different scales, and this is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image fea...
Leonid Taycher, John W. Fisher III, Trevor Darrell
Despite significant recent progress, the best available visual saliency models still lag behind human performance in predicting eye fixations in free-viewing of natural scenes. ...