We present a method for the simultaneous detection and segmentation of objects from static images. We employ lowlevel contour features that enable us to learn the coarse object sh...
The Recognizing Textual Entailment System shown here is based on the use of a broad-coverage parser to extract dependency relationships; in addition, WordNet relations are used to ...
—We develop an algorithm aimed at estimating travel time on segments of a road network using a convex optimization framework. Sampled travel time from probe vehicles are assumed ...
Sebastien Blandin, Laurent El Ghaoui, Alexandre M....
We present a novel approach to recognizing Textual nt. Structural features are constructed from abstract tree descriptions, which are automatically extracted from syntactic depend...
We are studying long term sequence prediction (forecasting). We approach this by investigating criteria for choosing a compact useful state representation. The state is supposed t...