Select a calendar:
Filter April Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for April 18, 2013
-
Human Motion Analysis in the Interplay of Multimodality, Representation and Learning
Thu, Apr 18, 2013 @ 01:30 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Ferda Ofli, University of California - Berkeley
Talk Title: Human Motion Analysis in the Interplay of Multimodality, Representation and Learning
Abstract: Human motion analysis is one of the most challenging research areas in computer vision in which one can seek to perform better by fusing information from multi-sensory data, by proposing richer feature representations, and by developing more efficient learning algorithms. In this talk, I will first describe the Berkeley MHAD, recently released comprehensive multimodal human action database, and present action recognition results for individual modalities as well as combinations of different modalities using state-of-the-art feature representations together with kernel-based methods. Then, I will introduce a new skeletal representation of human actions based on orderings of the most informative joints and demonstrate on multiple datasets that the new representation is discriminative for human action recognition and performs better than state-of-the-art feature representations. Finally, I will talk about a multimodal analysis framework for learning and synthesis of human body motions in the context of dance performances.
Biography: Ferda Ofli received B.Sc. degrees both in Electrical and Electronics Engineering and Computer Engineering, and the Ph.D. degree in Electrical Engineering from Koc University, Istanbul, Turkey, in 2005 and 2010, respectively. He is currently a postdoctoral researcher in the Teleimmersion Lab at the University of California at Berkeley, Berkeley, CA. His research interests span the areas of multimedia signal processing, computer vision, pattern recognition and machine learning. He received Graduate Studies Excellence award in 2010 for outstanding academic achievement at Koc University. http://www.eecs.berkeley.edu/~fofli/
Host: Prof. Shrikanth Narayanan
Location: Ronald Tutor Hall of Engineering (RTH) - 320
Audiences: Everyone Is Invited
Contact: Mary Francis
-
Focused on parallel and distributed computingThu, Apr 18, 2013 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: TBA, TBA
Talk Title: TBA
Series: EE598 Seminar Course
Abstract: Weekly seminars given by researchers in academia and industry including senior doctoral students in EE, CS and ISI covering current research related to parallel and distributed computation including parallel algorithms, high performance computing, scientific computation, application specific architectures, multi-core and many-core architectures and algorithms, application acceleration, reconfigurable computing systems, data intensive systems, Big Data and cloud computing.
Biography: Prerequisite: Students are expected to be familiar with basic concepts at the level of graduate level courses in Computer Engineering and Computer Science in some of these topic areas above. Ph.D. students in Electrical Engineering, Computer Engineering and Computer Science can automatically enroll. M.S. students can enroll only with permission of the instructor. To request permission send a brief mail to the instructor in text format with the subject field ââ¬ÅEE 598ââ¬Â. The body of the mail (in text format) should include name, degree objective, courses taken at USC and grades obtained, prior educational background, and relevant research background, if any.
Requirements for CR:
1. Attending at least 10 seminars during the semester
There will be a sign-in sheet and a sign-out sheet at every seminar. All students must sign-in (before 2:00pm) and sign-out (after 3:00pm). The sign-in sheet will not be available after 2:00pm, and the sign-out sheet will not be available before 3:00pm.
2. Submitting a written report for at least 5 seminars
The written report for each seminar must be 1-page single line spaced format with font size of 12 (Times) or 11 (Arial) without any figures, tables, or graphs. The report must be submitted no later than 1 week after the corresponding seminar, and must be handed only to the instructor either on the seminar times or during office hours. Late reports will not be considered.
The report must summarize studentââ¬â¢s own understanding of the seminar, and should contain the following:
- Your name and submission date [1 line]
- Title of the seminar, name of the speaker, and seminar date [1 line]
- Background of the work (e.g., applications, prior research, etc.) [1 paragraph]
- Highlights of the approaches presented in the seminar [1-2 paragraphs]
- Main results presented in the seminar [1-2 paragraphs]
- Conclusion (your own conclusion and not what was given by the speaker) [1 paragraph]
Reviewing papers related to the topic of the seminar, and incorporating relevant findings in the
reports (e.g., in the conclusion section) is encouraged. In such cases, make sure to clearly indicate
the reference(s) used to derive these conclusions.
Host: Professor Viktor K. Prasanna
More Information: Course Announcement_EE598_Focused on parallel and distributed computing_(Spring 2013).pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) -
Audiences: Everyone Is Invited
Contact: Janice Thompson
-
EE 598: ELECTRICAL ENGINEERING RESEARCH SEMINAR COURSE #13
Thu, Apr 18, 2013 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Farnoush Banaei-Kashani, PhD, Computer Science, USC Viterbi School of Engineering
Talk Title: Indexes for Efficient Spatial Query Processing on Cloud
Series: EE598 Seminar Course
Abstract: With exclusive access to geospatial data and the hardware platform to develop and serve data-rich geospatial applications, large IT companies have created a monopoly on development of these applications; hence, hindering healthy competition and economic growth. We argue that introduction of cloud computing has recently opened the door to break this monopoly by providing open access to both data and hardware platform, and consequently, enabled any interested entity to develop cloud-based geospatial services and applications. Accordingly as a means to facilitate this transition, we investigate, design and develop Geo-SaaS (short for Geospatial Software-as-a-Service), a framework for geospatial service/SaaS development on cloud platforms. Geo-SaaS provides the programming environment and the query re-writing toolset required for porting the existing geospatial queries and access methods to the parallel platform of cloud. Practitioners (e.g., various businesses) can use the geospatial services developed based on GeoSaaS to implement their cloud-based geospatial applications, and academics can extend the toolsets provided by GeoSaaS by developing their own geospatial services. In this talk, I start by further motivating Geo-SaaS, and then review sample results from our prior work as well as our ongoing work.
Biography: Farnoush Banaei-Kashani is a Research Associate and Associate Director of Research at NSF's Integrated Media Systems Center (IMSC) at the University of Southern California. He received his B.S. in Computer Engineering from Sharif University of Technology in 1996, and his M.S. and Ph.D. Degrees in Computer Networks and Computer Science from the University of Southern California in 2002 and 2006, respectively. His research is focused on fundamental and applied data management with special interest in Data-driven Decision-making Systems (DDSs), i.e., systems that automate the process of decision-making based on data. Toward this end, his research objective is to introduce novel solutions for all components of the DDS data management cycle (namely, data collection, transfer, preprocessing, storage for querying, analysis and mining, visualization, and actuation) under various combinations of the Big Data V3 challenges relevant for the desired DDS applications. Dr. Banaei-Kashani has authored more than forty research articles in the areas of Sensor and Peer-to-Peer Databases, Distributed Databases, and Spatial Databases, Data Streams, Cloud Computing, and Social Network Analysis. He regularly serves on the program committee of various database conferences.
Host: Professor Viktor K. Prasanna
More Information: Course Announcement_EE598_Focused on parallel and distributed computing_(Spring 2013) 2.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Janice Thompson
