I lead the Image and Video Computing (IVC) Group at University of Colorado Boulder. Our aim is to create computing systems that enable and accelerate the analysis of visual information, as a critical precursor to discoveries and innovations that can benefit society at large. Our research involves computer vision, machine learning, crowdsourcing, human computation, human-computer interaction, accessibility, and (bio)medical image analysis. We develop both scalable automated algorithms and crowdsourced human intelligence systems for analyzing images and videos. Research problems addressed by our group include salient object detection, object segmentation, object tracking, (bio)medical image and video analysis, visual question answering, image captioning, assistive technologies for people who are blind and with low vision, image inpainting, and style transfer.
machine learning, human computation, crowdsourcing, (bio)medical image and video analysis
CSCI 5922 - Neural Networks and Deep Learning
Introduces modern approaches to machine learning using neural networks. Neural nets, popular in the early 1990s, have undergone a resurgence due to significant advances in computing power and the availability of very large data sets. Now rechristened 'deep learning', the field has produced state-of-the-art results in a range of artificial intelligence problems, including vision, speech and natural language processing.