nl-uiuc AT lists.cs.illinois.edu

Subject: Natural language research announcements

List archive

[nl-uiuc] AIIS: Mohammad Rastegari - Friday Sept 27 @ 4pm

From: Yonatan Bisk <bisk1 AT illinois.edu>
To: nl-uiuc <nl-uiuc AT cs.uiuc.edu>, AIVR <aivr AT cs.uiuc.edu>, Vision List <vision AT cs.uiuc.edu>, Eyal Amir <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>, "Lee, Soo Min" <lee203 AT illinois.edu>, Jana Diesner <jdiesner AT illinois.edu>, "Raginsky, Maxim" <maxim AT illinois.edu>
Subject: [nl-uiuc] AIIS: Mohammad Rastegari - Friday Sept 27 @ 4pm
Date: Thu, 26 Sep 2013 10:22:30 -0500
List-archive: <http://lists.cs.uiuc.edu/pipermail/nl-uiuc/>
List-id: Natural language research announcements <nl-uiuc.cs.uiuc.edu>

When: This Friday (Tomorrow) @ 4pm - Sept 27

Where: 3405 SC
Speaker: Mohammad Rastegari ( http://www.umiacs.umd.edu/~mrastega/ )

Title: Predictability and its Applications

Abstract: Representing visual data with binary codes has been receiving great amount of attention recently. Binary codes not only enables fast search and retrieval, but also they boost the performance in recognition tasks. In this talk I will present the new notion of predictable binary codes that leads to the state-of-the-art object category retrieval. These binary codes can be seen as visual attributes in image domain. We extended the notion of predictability over textual domain and designed a dual-view model for learning the binary codes. These visual attributes are used to expand visual coverage of training set by adding images from a large pool of unlabeled images when one suffers from lack of training data in some categories.

Bio: Student of Ali Farhadi's at UWashington

[nl-uiuc] AIIS: Mohammad Rastegari - Friday Sept 27 @ 4pm, Yonatan Bisk, 09/26/2013