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...
Current state-of-the-art image-based scene reconstruction
techniques are capable of generating high-fidelity 3D
models when used under controlled capture conditions.
However, th...
Jean-Yves Guillemaut, Joe Kilner and Adrian Hilton
In soccer videos, most significant actions are usually followed by close–up shots of players that take part in the action itself. Automatically annotating the identity of the p...
Algebraic video uses a set of basic operations on video segments to create a desired video stream. The video algebraconsists ofoperations fortemporallyand spatially combining vide...
High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...