Multiple instance learning (MIL) is a form of weakly supervised learning where training
instances are arranged in sets, called bags, and a label is provided for the entire bag. This …

In this paper, we present a study on learning visual recognition models from large scale
noisy web data. We build a new database called WebVision, which contains more than $2.4 …

Perceiving a scene most fully requires all the senses. Yet modeling how objects look and
sound is challenging: most natural scenes and events contain multiple objects, and the …

The recent development in learning deep representations has demonstrated its wide
applications in traditional vision tasks like classification and detection. However, there has …

We present an approach to utilize large amounts of web data for learning CNNs. Specifically
inspired by curriculum learning, we present a two-step approach for CNN training. First, we …

In this paper, we address the problem of tracking an object in a video given its location in the
first frame and no other information. Recently, a class of tracking techniques called “tracking …

This paper addresses the problem of learning object models from egocentric video of
household activities, using extremely weak supervision. For each activity sequence, we …

Labeling a histopathology image as having cancerous regions or not is a critical task in
cancer diagnosis; it is also clinically important to segment the cancer tissues and cluster …

Abstract General Purpose Vision (GPV) systems are models that are designed to solve a
wide array of visual tasks without requiring architectural changes. Today, GPVs primarily …

Recognition is graduating from labs to real-world applications. While it is encouraging to see
its potential being tapped, it brings forth a fundamental challenge to the vision researcher …