We present a new and efficient semi-supervised training method for parameter estimation and feature selection in conditional random fields (CRFs). In real-world applications suc...
We study activity recognition using 104 hours of annotated data collected from a person living in an instrumented home. The home contained over 900 sensor inputs, including wired r...
Beth Logan, Jennifer Healey, Matthai Philipose, Em...
We present a method for spotting sporadically occurring gestures in a continuous data stream from body-worn inertial sensors. Our method is based on a natural partitioning of cont...
Holger Junker, Oliver Amft, Paul Lukowicz, Gerhard...
This paper reports the preliminary experiments on the cow identification via gait recognition of motion images. The eight cows walking under two different situations have been pr...
Shu Mimura, Keichi Itoh, Takumi Kobayashi, Tomohir...
Motion trajectories provide rich spatio-temporal information about an object's activity. The trajectory information can be obtained using a tracking algorithm on data streams ...
Faisal I. Bashir, Ashfaq A. Khokhar, Dan Schonfeld