We introduce novel discriminative learning algorithms for dynamical systems. Models such as Conditional Random Fields or Maximum Entropy Markov Models outperform the generative Hi...
As computer vision research considers more object categories and greater variation within object categories, it is clear that larger and more exhaustive datasets are necessary. How...
Brendan Collins, Jia Deng, Kai Li, Fei-Fei Li 0002
In many real world applications, active selection of training examples can significantly reduce the number of labelled training examples to learn a classification function. Differ...
In the task of adaptive information filtering, a system receives a stream of documents but delivers only those that match a person's information need. As the system filters i...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...