We introduce an algorithm that, given n objects, learns a similarity matrix over all n2 pairs, from crowdsourced data alone. The algorithm samples responses to adaptively chosen t...
Omer Tamuz, Ce Liu, Serge Belongie, Ohad Shamir, A...
We present a motion classification approach to detect movements of interest (abnormal motion) based on local feature modeling within spatio-temporal detectors. The modeling is pe...
We introduce the Multiplicative Update Selector and Estimator (MUSE) algorithm for sparse approximation in underdetermined linear regression problems. Given f = Φα∗ + µ, the ...
Via an oracle experiment, we show that the upper bound on accuracy of a CCG parser is significantly lowered when its search space is pruned using a supertagger, though the supert...
We present a novel keyframe selection and recognition
method for robust markerless real-time camera tracking.
Our system contains an ofine module to select features
from a grou...