Active Vision Dataset Benchmark.

Several recent efforts in computer vision indicate a trend toward studying and understanding problems in larger scale environments, beyond single images, and focus on connections to tasks in navigation, mobile manipulation, and visual question answering. A common goal of these tasks is the capability of moving in the environment, acquiring novel views during perception and while performing a task. This capability comes easily in synthetic environments, however achieving the same effect with real images is much more laborious. We propose using the existing Active Vision Dataset to form a benchmark for such problems in a real-world settings with real images. The dataset is well suited for evaluating tasks of multiview active recognition, target driven navigation, and target search, and also can be effective for studying the transfer of strategies learned in simulation to real settings.