AbstractVideo conferencing is an important application that has been extensively used in IP, ATM networks, and TV broadcasting as a means of interactive communications. Teleconferencing video traffic consists of video scenes in which one or more people are talking with low to medium motion and almost unchanged background. To reflect the properties of video signals in the design of communication and transmission networks, modeling this teleconference video has received considerable attention.For over a decade, there has been an enormous amount of interest and research in traffic modeling of compressed variable bit rate (VBR) video. An essential class of video models that has received much attention lately is regression models. This paper presents a survey of the state of the art regression traffic studies that have been proposed in the literature to model teleconference video. After an introduction to the basic definition of the regression process, the third section begins with a discussion of the earlier regression models. Then, a number of recent regression models are discussed. The paper concludes with a comparison of all the models, recommendations, and open problems. Copyright © 2004 John Wiley & Sons, Ltd.