rapidly. Operating on 384 by 288 pixel images, faces are detected at 15 frames per second on a conventional 700 MHz Intel Pentium III. In other face detection systems, auxiliary information, such as image differences in video sequences, or pixel color in color images, have been used to achieve high frame

This paper describes a pedestrian detection system that integrates image intensity information with motion information. We use a detection style algorithm that scans a detector over two consecutive frames of a video sequence. The detector is trained (using AdaBoost) to take advantage of both

as a multi-threaded software entity and as a stand-alone ATM network-attached playback device. Scalability of the video distribution network is obtained by using multicast features of the underlying network. Feedback from the clients and a single video frame retransmission mechanism are used

Human motion analysis is receiving increasing at-tention from computer vision researchers. This inter-est is motivated by a wide spectrum of applications, such as athletic performance analysis, surveillance, man-machine interfaces, content-based image storage and retrieval, and video conferencing

The human visual system appears to be capable of temporally integrating information in a video sequence in such a way that the perceived spatial resolution of a sequence appears much higher than the spatial resolution of an individual frame. While the mechanisms in the human visual system which do

Layered Video Multicast with Retransmissions (LVMR) is a system for distributing video using layered coding over the Internet. The two key contributions of the system are: (1) improving the quality of reception within each layer by retransmitting lost packets given an upper bound on recovery

We present a system that estimates the motion of a stereo head or a single moving camera based on video input. The system operates in real-time with low delay and the motion estimates are used for navigational purposes. The front end of the system is a feature tracker. Point features are matched

Frames from a voice-driven animation, computed from a single baby picture and an adult model of facial control. Note the changes in upper facial expression. See figures 5, 6 and 7 for more examples of predicted mouth shapes. We introduce a method for predicting a control signal from another related

An ontology is a set of definitions of content-specific knowledge representation primitives: classes, relations, functions, and object constants. Ontolingua is mechanism for writing ontologies in a canonical format, such that they can be easily translated into a variety of representation

early, but such retransmitted segments may have already been successfully received. A Selective Acknowledgment (SACK) mechanism, combined with a selective repeat retransmission policy, can help to overcome these limitations. The receiving TCP sends back SACK packets to the sender informing the sender