Recognition for the People, by the People, and of the People

25 Mar
Monday, 03/25/2013 12:00pm to 1:00pm
Seminar

Tamara Berg
Stony Brook University
Computer Science

Computer Science Building, Room 151

Faculty Host: Erik Learned-Miller

Abstract:

Recognition research in computer vision has focused on producing complete lists of the contents of an image, especially the objects of scenes that are depicted. One aspect of recognition that has received relatively less attention is the people for whom we are creating these recognition outputs. People are usually the end consumers of visual content -- from viewing or watching general images and video on the web, to curating personal photo collections, to linking images on social networks. In this talk I will argue that recognition should move toward a more human centric focus, including taking a closer look at what kinds of recognition outputs our systems should produce, what information we can mine from the people looking at images and video under natural viewing conditions, and what pictures can convey about their viewers or owners. In particular I will describe several ongoing research projects to: a) generate natural language descriptions for images, b) incorporate informative human cues (e.g. gaze) for improved image understanding, and c) recognize aspects of our individual or collective socio-identities from photographs.

Bio:

Tamara Berg received her B.S. in Mathematics and Computer Science from the University of Wisconsin, Madison in 2001. She then completed a PhD from the University of California, Berkeley in 2007 and spent 1 year as a research scientist at Yahoo! Research. She is currently an Assistant Professor in the computer science department at Stony Brook University and a core member of the consortium for Digital Art, Culture, and Technology (cDACT). Her research straddles the boundary between Computer Vision and Natural Language Processing with applications to large scale recognition, retrieval, and social network analysis.

A reception will be held at 3:40 in the atrium, outside the presentation room.