nl-uiuc AT lists.cs.illinois.edu

Subject: Natural language research announcements

List archive

[nl-uiuc] AIIS talk by Ian Endres on Feb 4

From: Rajhans Samdani <rsamdan2 AT illinois.edu>
To: nl-uiuc AT cs.uiuc.edu, aivr AT cs.uiuc.edu, dais AT cs.uiuc.edu, cogcomp AT cs.uiuc.edu, vision AT cs.uiuc.edu, eyal AT cs.uiuc.edu, aiis AT cs.uiuc.edu, aistudents AT cs.uiuc.edu, "Girju, Corina R" <girju AT illinois.edu>, "Catherine Blake" <clblake AT illinois.edu>, "Efron, Miles James" <mefron AT illinois.edu>
Subject: [nl-uiuc] AIIS talk by Ian Endres on Feb 4
Date: Wed, 2 Feb 2011 12:15:36 -0600 (CST)
List-archive: <http://lists.cs.uiuc.edu/pipermail/nl-uiuc>
List-id: Natural language research announcements <nl-uiuc.cs.uiuc.edu>

Hi all,

This week in AIIS we have Ian Endres who is going to present his work with
Derek
Hoeim. Ian works in computer vision.

When: Friday, February the 4'th. 2pm.

Where: 3405, Siebel Center.

Title: Category Independent Object Proposals

Abstract:
In this work, we propose a category-independent method to produce a bag of
regions
and rank them, such that top-ranked regions are likely to be good
segmentations of
different objects. Our key objectives are completeness and diversity: every
object
should have at least one good proposed region, and a diverse set should be
top-
ranked. Our approach is to generate a set of segmentations by performing
graph cuts
based on a seed region and a learned affinity function. Then, the regions are
ranked
using structured learning based on various cues. Our experiments on BSDS and
PASCAL VOC 2008 demonstrate our ability to find most objects within a small
bag of
proposed regions.

I will also introduce upcoming work that leverages structured models to
jointly
represent objects and their parts across a range of categories.

Be there!
Thanks,
Rajhans

Rajhans Samdani,
Graduate Student,
Dept. of Computer Science,
University of Illinois at Urbana-Champaign.

[nl-uiuc] AIIS talk by Ian Endres on Feb 4, Rajhans Samdani, 02/02/2011