Deep Integration of Human and Machine Intelligence for Accessibility - - PowerPoint PPT Presentation

deep integration of human and machine intelligence for
SMART_READER_LITE
LIVE PREVIEW

Deep Integration of Human and Machine Intelligence for Accessibility - - PowerPoint PPT Presentation

Deep Integration of Human and Machine Intelligence for Accessibility Jeffrey P. Bigham Carnegie Mellon University Jeffrey P. Bigham Carnegie Mellon University Jeffrey P. Bigham @jeffbigham @jeffbigham What do blind people want to know?


slide-1
SLIDE 1

Jeffrey P. Bigham @jeffbigham

Jeffrey P. Bigham Carnegie Mellon University

Deep Integration of Human and Machine Intelligence for Accessibility

Jeffrey P. Bigham

Carnegie Mellon University @jeffbigham

slide-2
SLIDE 2

Jeffrey P. Bigham @jeffbigham

What do blind people want to know?

vizwiz.org

slide-3
SLIDE 3

Jeffrey P. Bigham @jeffbigham

slide-4
SLIDE 4

Jeffrey P. Bigham @jeffbigham

slide-5
SLIDE 5

Jeffrey P. Bigham @jeffbigham

slide-6
SLIDE 6

Jeffrey P. Bigham @jeffbigham

slide-7
SLIDE 7

Jeffrey P. Bigham @jeffbigham

VizWiz Dataset

vizwiz.org/data

Check out Microsoft’s Seeing AI!

slide-8
SLIDE 8

Jeffrey P. Bigham @jeffbigham

Using Devices

User + AI + Crowds

X

Bigham, Jeffrey, et al. "VizWiz: nearly real-time answers to visual questions." UIST 2010. Brady, Erin, et al. “Visual challenges in the everyday lives of blind people.” CHI 2013.

slide-9
SLIDE 9

Jeffrey P. Bigham @jeffbigham

slide-10
SLIDE 10

Jeffrey P. Bigham @jeffbigham

slide-11
SLIDE 11

Jeffrey P. Bigham @jeffbigham

slide-12
SLIDE 12

Jeffrey P. Bigham @jeffbigham

slide-13
SLIDE 13

Jeffrey P. Bigham @jeffbigham

slide-14
SLIDE 14

Jeffrey P. Bigham @jeffbigham

slide-15
SLIDE 15

Jeffrey P. Bigham @jeffbigham

What do blind people want to know?

vizwiz.org

slide-16
SLIDE 16

Jeffrey P. Bigham @jeffbigham

Working with AI

slide-17
SLIDE 17

Jeffrey P. Bigham @jeffbigham

Supporting Blind Photography

Supporting Blind Photography. Jayant, Chandrika, Ji, Hanjie, White, Samuel, Bigham, Jeffrey P. ASSETS 2011.

Working with AI

slide-18
SLIDE 18

Jeffrey P. Bigham @jeffbigham

Wu, et al. Automatic Alt-text: Computer-generated Image Descriptions for Blind Users on a Social Network Service. CSCW 2017.

Target What People Want to Know

Working with AI

slide-19
SLIDE 19

Jeffrey P. Bigham @jeffbigham

Errors are Important and Not Created Equa

MacLeod, Bennett, Morris, Cuttrell, et al. Understanding Blind People’s Experiences with Computer-Generated Captions of Social Media Images. CHI 2017.

Measure and Express Confidence Well

Working with AI

slide-20
SLIDE 20

Jeffrey P. Bigham @jeffbigham

* Amplify Users with AI Support (blind photograph * Solve Real Problems (understand user needs) * Embrace and Understand Errors (all errors are * Measure Confidence and Express it Well

Working with AI

slide-21
SLIDE 21

Jeffrey P. Bigham @jeffbigham

The End

VizWiz Dataset: http://www.vizwiz.org/data VizWiz Publications: http://www.jeffreybigham.com

* Amplify Users with AI Support (blind photography) * Solve Real Problems (understand user needs) * Embrace and Understand Errors (all errors are not equal) * Measure Confidence and Express it Well

Funded by: Google, Microsoft, NSF, NIDILRR