We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We use a bootstrap algorithm for training the networks, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting non-face training examples, which must be chosen to span the entire space of non-face images. Comparisons with other state-of-the-art face detection systems are presented; our system has better performance in terms of detection and false-positive rates. This work was partially supported by a grant from Siemens Corporate Research, Inc., by the Department of the Army, Army Research Office under grant number DAAH04-94-G-0006, and by the Office of Naval Research under grant number N00014-95-1-0591. This work was started while Shumeet Balu...

A visual scene is commonly defined as a view of an environment comprised of objects and surfaces organized in a meaningful way, like a kitchen, a street or a forest path. More broadly, the domain of scene perception encompasses any visual stimulus that contains multiple elements arranged in a

’ll describe it with adjectives like ‘indoors’, ‘cozy’, and ‘cluttered’. In computer vision, (or more specifically, in scene understanding), the most effective way to describe a visual scene is also a major question. Of the these three ways of describing a scene, (commonly referred to as categorization, scene

We present a visually-grounded language understanding model based on a study of how people verbally describe objects in scenes. The emphasis of the model is on the combination of individual word meanings to produce meanings for complex referring expressions. The model has been implemented

planar and panoramic mosaics, and for projective depth recovery. We also speculate about the ultimate usefulness of projective approaches to visual scene reconstruction. 1 Introduction The recovery of 3-D scene information from multiple views has long been one of the central problems in computer vision

In this paper, we present methods for 3D volumetric reconstruction of visual scenes photographed by multiple calibrated cameras placed at arbitrary viewpoints. Our goal is to generate a 3D model that can be rendered to synthesize new photo-realistic views of the scene. We improve upon existing

Computer vision algorithms have played a pivotal role in commercial video surveillance sys-tems for a number of years. However, a common weakness among these systems is their inability to handle crowded scenes. In this thesis, we have developed algorithms that overcome some of the challenges

When describing an object in a visual scene (referring expression generation; (Krahmer & Deemter, 2012), a speaker must devise an expression which allows a listener to quickly and accurately locate the target. Speakers often do so by describing both the target itself and other objects

Abstract not found

Abstract not found