The classification performance of deep neural networks has begun to asymptote at near-
perfect levels. However, their ability to generalize outside the training set and their …

Video summarization is a challenging problem in part because knowing which part of a
video is important requires prior knowledge about its main topic. We present TVSum, an …

In image classification, visual separability between different object categories is highly
uneven, and some categories are more difficult to distinguish than others. Such difficult …

In this paper we study how to perform object classification in a principled way that exploits
the rich structure of real world labels. We develop a new model that allows encoding of …

Convolutional Neural Network (CNN) image classifiers are traditionally designed to have
sequential convolutional layers with a single output layer. This is based on the assumption …

It is easy for people to imagine what a man with pink hair looks like, even if they have never
seen such a person before. We call the ability to create images of novel semantic concepts …

We present a tree-structured network architecture for large-scale image classification. The
trunk of the network contains convolutional layers optimized over all classes. At a given …

While machine learning approaches to visual emotion recognition offer great promise,
current methods consider training and testing models on small scale datasets covering …

Human actions capture a wide variety of interactions between people and objects. As a
result, the set of possible actions is extremely large and it is difficult to obtain sufficient …

I present my work towards learning a better computer vision system that learns and
generalizes object categories better, and behaves in ways closer to what human behave …