-of-the-art results on the standard KTH action dataset by achieving 91.8 % accuracy. Given the inherent problem of noisy labels in automatic annotation, we particularly investigate and show high tolerance of our method to annotation errors in the training set. We finally apply the method to learning and classifying

. This approach extends the nearest neighbor algorithm, which has large storage requirements. We describe how storage requirements can be significantly reduced with, at most, minor sacrifices in learning rate and classification accuracy. While the storage-reducing algorithm performs well on several realworld

the Continuously Adaptive Mean Shift (CAMSHIFT) algorithm. CAMSHIFT’s tracking accuracy is compared against a Polhemus tracker. Tolerance to noise, distractors and performance is studied. CAMSHIFT is then used as a computer interface for controlling commercial computer games and for exploring immersive 3D graphic

by separating the interface from the core auction procedures. This design provides a responsive interface and tolerates system and network disruptions, but necessitates careful timekeeping procedures to ensure temporal accuracy. The AuctionBot has been used extensively in classroom exercises, and is available

and the interpolation of gaps are presented. Finally, strategies for processing almost arbitrarily large images and fusion of disparity images using orthographic projection are proposed. A comparison on standard stereo images shows that SGM is among the currently top-ranked algorithms and is best, if subpixel accuracy

An ad-hoc wireless sensor network-based system is presented that detects and accurately locates shooters even in urban environments. The system consists of a large number of cheap sensors communicating through an ad-hoc wireless network, thus it is capable of tolerating multiple sensor failures

optimal accuracy -- the accuracy of synchronized clocks (with respect to real time) is as good as that specified for the underlying hardware clocks. The solution is also optimal with respect to the number of faulty processes that can be tolerated to achieve this accuracy.

of the radio beacon infrastructure. In our deployment of MoteTrack, consisting of 20 beacon nodes distributed across our Computer Science building, we achieve a 50 th percentile and 80 th percentile location-tracking accuracy of 2 meters and 3 meters respectively. In addition, MoteTrack can tolerate

the more the estimation error that the user can tolerate, the less is the energy consumed. We present a distributed estimation algorithm that can be applied to explore the energy-accuracy subspace for a sub-class of periodic aggregation problems, and present extensive simulation results that validate our

Abstract—Collaboration in sensor networks must be fault-tolerant due to the harsh environmental conditions in which such networks can be deployed. This paper focuses on finding algorithms for collaborative target detection that are efficient in terms of communication cost, precision, accuracy