Event

 
 

ICSI BEARS Open House

ICSI Research Staff


Thursday, February 12, 2009
2:00-4:00 p.m.

The ICSI BEARS Open House is held in conjunction with the Berkeley EECS Annual Research Symposium. ICSI scientists will be on hand throughout to discuss and demonstrate their latest research in networking, bioinformatics, artificial intelligence, speech and natural language processing, and machine learning.

Agenda:

2:00 Poster Session
2:45 Featured Presentation: "Image Recognition for Intelligent Multimodal Interfaces"
Prof. Trevor Darrell
UC Berkeley and Leader of ICSI's new Vision Group
3:30 Refreshments and continuation of Poster Session

A shuttle service will be available to transport guests from BEARS to ICSI and back.

To learn more about BEARS 2009 and register: http://www.eecs.berkeley.edu/IPRO/BEARS/

Abstract:

When interaction concerns the physical world, interfaces should do their best to search for information using direct observation. This is true both for interaction between robots and human users, and for information search using mobile devices. Image-based interfaces have been tried in the past, but generally required visually simple objects--uniform color, etc.--or presumed that barcodes could be affixed to each viewed object or surface. Recent advances in computer vision and content-based image retrieval have enabled fast and robust indexing from images of individual objects--CD covers, book jackets, magazine advertisements, etc.--even on relatively low-power platforms such as camera-equipped mobile phones, and category-level recognition is rapidly improving. I'll review the relevant algorithms and design of such systems, and discuss what types of image recognition interfaces are feasible in the near term. I'll describe very recent work on multimodal question answering interfaces, which combine image and text query matching with human-in-the-loop interaction. I'll close with a discussion of the anticipated future progress on category-level visual recognition, and what classes of interfaces it may enable.

 
Copyright © 2005 International Computer Science Institute. All Rights Reserved.