Aditya Khosla

ImageNet Large Scale Visual Recognition Challenge

Learning Deep Features for Discriminative Localization

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable...

Human action recognition by learning bases of action attributes and parts

In this work, we propose to use attributes and parts for recognizing human actions in still images. We define action attributes as the verbs that describe the properties of huma...

HOGgles: Visualizing Object Detection Features

We introduce algorithms to visualize feature spaces used by object detectors. The tools in this paper allow a human to put on 'HOG goggles' and perceive the visual world as a HO...