CMU-HCII-20-105
Human-Computer Interaction Institute
School of Computer Science, Carnegie Mellon University



CMU-HCII-20-105

Human-AI Systems for Visual Information Access

Anhong Guo

August 2020

Ph.D. Thesis

CMU-HCII-20-105.pdf
Pending


Keywords: Human-AI systems; human-computer interaction; intelligent systems; crowd-sourcing; artificial intelligence; computer vision; machine learning; accessibility; environmentalsensing; 3D printing; reverse engineering; augmented reality


In my work, I create hybrid human- and AI-powered intelligent interactive systemsto provide access to visual information in the real world. By combining the advantages of humans and AI, these systems can be nearly as robust and flexible as humans, and nearly as quick and low-cost as automated AI, enabling us to solve problems that are currently impossible with either alone.

I develop and deploy human-AI systems for two application domains: accessibility and environmental sensing. To make physical interfaces accessible for blind people, I develop systems to interpret static and dynamic interfaces, enabling blind people to independently access them through audio feedback or tactile overlays. For environmental sensing, I develop and deploy a camera sensing system that collects human labels to bootstrap automatic processes to answer real-world visual questions, allowing end users to actionalize AI in their everyday lives.

AI systems often require a huge amount of up front training data to get started, but targeted human intelligence can bootstrap the systems with relatively little data. Although humans may be slower initially, quickly bootstrapping to automated approaches provides a good balance, enabling human-AI systems to be scalable andrapidly deployable.

144 pages

Thesis Committee:
Jeffrey P. Bigham (Chair) (HCII/LTI)
Chris Harrison
Jodi Forlizzi (HCII/Design)
Meredith Ringel Morris (Microsoft Research)

Jodi Forlizzi, Head, Human-Computer Interaction Institute
Martial Hebert, Dean, School of Computer Science



Return to: SCS Technical Report Collection
School of Computer Science homepage

This page maintained by reports@cs.cmu.edu