Aditya Khosla

Abstract While long term human visual memory can store a remarkable amount of visual information, it tends to degrade over time. Recent works have shown that image memorability is an intrinsic property of an image that can be reliably estimated using state-of-the-art image features and machine learning algorithms. However, the class of features and image information that is forgotten has not been explored yet.

Abstract When glancing at a magazine, or browsing the Internet, we are continuously being exposed to photographs. However, not all images are equal in memory; some stitch to our minds, while others are forgotten. In this paper we discuss the notion of image memorability and the elements that make it memorable. Our recent works have shown that image memorability is a stable and intrinsic property of images that is shared across different viewers.

Abstract: This paper presents methods to visualize feature spaces commonly used in object detection. The tools in this paper allow a human to put on" feature space glasses" and see the visual world as a computer might see it. We found that these" glasses" allow us to gain insight into the behavior of computer vision systems.

Abstract. The presence of bias in existing object recognition datasets is now well-known in the computer vision community. While it remains in question whether creating an unbiased dataset is possible given limited resources, in this work we propose a discriminative framework that directly exploits dataset bias during training.

Abstract In this paper, we consider two action recognition problems in still images. One is the conventional action classification task where we assign a class label to each action image; the other is a new problem where we measure the similarity between action images. We achieve the goals by using a mutual context model to jointly model the objects and human poses in images of human actions.

Abstract 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 human actions, while the parts of actions are objects and poselets that are closely related to the actions. We jointly model the attributes and parts by learning a set of sparse bases that are shown to carry much semantic meaning. Then, the attributes and parts of an action image can be reconstructed from sparse coefficients with respect to the learned bases.

Abstract Deep networks have been successfully applied to unsupervised feature learning for single modalities (eg, text, images or audio). In this work, we propose a novel application of deep networks to learn features over multiple modalities. We present a series of tasks for multimodal learning and show how to train deep networks that learn features to address these tasks.

Abstract: Exploration of time domain is now a vibrant area of research in astronomy, driven by the advent of digital synoptic sky surveys. While panoramic surveys can detect variable or transient events, typically some follow-up observations are needed; for short-lived phenomena, a rapid response is essential. Ability to automatically classify and prioritize transient events for follow-up studies becomes critical as the data rates increase.