Henry Kautz

Henry Kautz

Auto-generated profile, based on publicly available information

Henry Kautz

Department of Computer Science, University of Rochester, Rochester, NY, United States

Research Focus & Metrics

Academic Career Length

40Years (1987-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 1997 in Communications of the ACM
Verified
Journal Article
Open access
HKHenry Kautz
Henry Kautz
BSBart Selman
Bart Selman
MSMehul Shah
Mehul Shah

1 April 2007 in Artificial Intelligence
Verified
Journal Article
Closed access
LLLin Liao
Lin Liao
DPDonald J. Patterson
Donald J. Patterson
DFDieter Fox
Dieter Fox
HKHenry Kautz
Henry Kautz

1 September 2009
Verified
Conference Paper
Closed access
RMRoss Messing
Ross Messing
CPChris Pal
Chris Pal
HKHenry Kautz
Henry Kautz
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.

1 January 2007 in The International Journal of Robotics Research
Verified
Journal Article
Closed access
LLLin Liao
Lin Liao
DFDieter Fox
Dieter Fox
HKHenry Kautz
Henry Kautz
Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. This paper describes how to extract a person’s activities and significant places from traces of GPS data. The system uses hierarchically structured conditional random fields to generate a consistent model of a person’s activities and places. In contrast to existing techniques, this approach takes the high-level context into account in order to detect the significant places of a person. Experiments show significant improvements over existing techniques. Furthermore, they indicate that the proposed system is able to robustly estimate a person’s activities using a model that is trained from data collected by other persons.

1 February 2000 in Journal of Automated Reasoning
Verified
Journal Article
Closed access
PDF file
CGCarla P. Gomes
Carla P. Gomes
BSBart Selman
Bart Selman
NCNuno Crato
Nuno Crato
HKHenry Kautz
Henry Kautz

1 January 2003
Verified
Book Chapter
Closed access
PDF file
DPDonald J. Patterson
Donald J. Patterson
LLLin Liao
Lin Liao
DFDieter Fox
Dieter Fox
HKHenry Kautz
Henry Kautz