Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can...
Robert Fergus, Fei-Fei Li 0002, Pietro Perona, And...
Fingerprint distortion changes both the geometric position and orientation of minutiae, and leads to difficulties in establishing a match among multiple impressions acquired from ...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Abstract. In this paper, we present a fully automatic approach to multiple human detection and tracking in high density crowds in the presence of extreme occlusion. Human detection...
There are moves in the Internet architecture community to add multipath capabilities to TCP, so that end-systems will be able to shift their traffic away from congested parts of th...