Event Location: NSH 1507
Bio: Ross Messing is a senior Ph.D. candidate in computer vision and machine
learing at the University of Rochester, Department of Computer Science.
Ross’s thesis work, advised by Chris Pal and Henry Kautz, develops new
features and statistical models for activity recognition in video. Ross
has particular experience in video analysis, structured Bayesian
modeling, cluster / GPU computing for applied machine learning/vision
problems, and human psychophysics. Ross Messing holds an M.S. in
Computer Science from the University of Rochester, and a B.A. with
honors in Psychology and Computer Science from Swarthmore College.

Abstract: We present an activity recognition feature inspired by human
psychophysical performance. This feature is based on the velocity
history of tracked keypoints. We present a generative mixture model for
video sequences using this feature, and show that it performs comparably
to local spatio-temporal features on the KTH activity recognition
dataset. In addition, we contribute a new activity recognition dataset,
focusing on activities of daily living, with high resolution video
sequences of complex actions. We demonstrate the superiority of our
velocity history feature on high resolution video sequences of
complicated activities. Further, we show how the velocity history
feature can be extended, both with a more sophisticated latent velocity
model, and by combining the velocity history feature with other useful
information, like appearance, position, and high level semantic
information. Our approach performs comparably to established and state
of the art methods on the KTH dataset, and significantly outperforms all
other methods on our challenging new dataset.