"Scene recognition is one of the hallmark tasks of computer vision, allowing defining a context for object recognition. Here we introduce a new Scene-centric database called Places, with 205 Scene categories and 2.5 millions of images with a category label. Using convolutional neural network (CNN), we learn deep Scene features for Scene recognition tasks, and establish new state-of-the-art performances on Scene-centric benchmarks. Here we provide the Places Database and the trained CNNs for academic research and education purposes."