Off-line trained class-specific object detectors are designed to detect any instance of the class in a given image or video sequence. In the context of object tracking, however, o...
We describe efficient techniques for construction of large term co-occurrence graphs, and investigate an application to the discovery of numerous fine-grained (specific) topics. A...
We consider the problem of finding the best arm in a stochastic multi-armed bandit game. The regret of a forecaster is here defined by the gap between the mean reward of the optim...
We analyze the regret, measured in terms of log loss, of the maximum likelihood (ML) sequential prediction strategy. This "follow the leader" strategy also defines one o...
We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object s...
Long Zhu, Yuanhao Chen, Antonio Torralba, William ...