MS-EE-L Archives

October 2015

MS-EE-L@LISTSERV.GMU.EDU

Options: Use Proportional Font
Show HTML Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Jammie Chang <[log in to unmask]>
Reply To:
Jammie Chang <[log in to unmask]>
Date:
Mon, 5 Oct 2015 14:30:02 +0000
Content-Type:
multipart/mixed
Parts/Attachments:
text/plain (3004 bytes) , text/html (9 kB) , Hamed-Pirsiavash-ECE-Talk.pdf (234 kB)
Dear All,


You are invited to the following seminar on the topic of Visual Understanding of Human Actions, which will take place at ENGR 3507 at 11:00 am today. Please see more details below.


Best,

Jammie


Jammie Chang

Academic Program Manager

Department of Electrical and Computer Engineering

George Mason University

4400 University Drive, MSN 1G5

Fairfax, VA 22030

Phone: 703-993-1570

Fax: 703-993-1601

________________________________
From: Houman Homayoun <[log in to unmask]>
Subject: Seminar Announcement: Prof. Hamed Pirsiavash from UMBC - Computer Vision - Monday October 5, 11Am-Noon, VSE 3507


Dear Colleagues,


You are invited to the following seminar on the topic of Visual Understanding of Human Actions.


Please find the seminar details below:


Title: Visual Understanding of Human Actions

Speaker: Prof. Hamed Pirsiavash, University of Maryland, Baltimore County

Date and Location: Monday, October 5, 2015, 11AM- 12 noon, VSE Room 3507



Abstract

The aim of computer vision is to develop algorithms for computers to "see" and understand the world as humans do. Central to this goal is understanding human behavior; for instance, in order for a robot to interact with humans, it should understand our actions to produce the desirable response. As such, my work explores several directions in computationally representing and understanding human actions.

In this talk, I will focus on the problems of detecting actions and judging their quality. First, I will describe simple grammars for modeling long-scale temporal structure in human actions. Real-world videos are typically composed of multiple action instances, where each instance is itself composed of sub-actions with variable durations and orderings. Our grammar models capture such hierarchical structure while admitting efficient, linear-time parsing algorithms for action detection. The second part of the talk will describe our algorithms for going beyond detecting actions to actually judging how well they are performed. Our learning-based framework can both judge and provide feedback to performers to improve the quality of their actions.


Biography

Hamed Pirsiavash is an assistant professor at the University of Maryland Baltimore County (UMBC) since August 2015. Prior to that, he was a postdoctoral research associate at MIT working in Artificial Intelligence Laboratory and with Prof. Antonio Torralba. He obtained his PhD at the University of California Irvine under the supervision of Prof. Deva Ramanan. Hamed research is in the intersection of computer vision and machine learning, more specifically in understanding human actions.


Regards,
Houman


************************************************************
Houman Homayoun
Assistant Professor
Department of Electrical and Computer Engineering
Department of Computer Science (Courtesy Appointment)
George Mason University
Engineering Building, 3223
(949) 943-9639 (cell)
(703) 993-5430 (office)
URL: http://ece.gmu.edu/~hhomayou/
************************************************************



ATOM RSS1 RSS2