We introduce a saliency model based on two key ideas. The first one is considering local and global image patch rarities as two complementary processes. The second one is based o...
Improving coding and spatial pooling for bag-of-words based feature design have gained a lot of attention in recent works addressing object recognition and scene classification. ...
racting these leads us to introduce the notion of a path object category. This is a relatively simple axiomatic framework, which is nonetheless sufficiently strong to allow the con...
We propose a new matrix completion algorithm— Kernelized Probabilistic Matrix Factorization (KPMF), which effectively incorporates external side information into the matrix fac...
Planning under uncertainty is an important and challenging problem in multiagent systems. Multiagent Partially Observable Markov Decision Processes (MPOMDPs) provide a powerful fr...