Logo: University of Southern California

Events Calendar

Select a calendar:

Filter October Events by Event Type:

Events for October 11, 2018

  • Multimodal Emotion Recognition: Quantifying Dynamics and Structure in Audio-Visual Expressive Speech

    Thu, Oct 11, 2018 @ 02:00 PM - 04:00 PM

    Ming Hsieh Department of Electrical Engineering

    Conferences, Lectures, & Seminars

    Speaker: Yelin (Lynn) Kim, Ph.D., Assistant Professor, University at Albany, SUNY

    Talk Title: Multimodal Emotion Recognition: Quantifying Dynamics and Structure in Audio-Visual Expressive Speech

    Abstract: The rise of AI assistant systems, including Google Home, Apple Siri, and Amazon Echo, brings the urgent need for increased and deeper understanding of users. In this talk, I will present algorithmic and statistical methods for analyzing audio-visual human behavior, particularly focusing on emotional and social signals inferred from speech and facial expressions. These methods can provide emotional intelligence to AI systems. However, developing automatic emotion recognition systems is challenging since emotional expressions are complex, dynamic, inherently multimodal, and are entangled with other factors of modulation (e.g. speech generation and emphasis). I will present several algorithms to address these fundamental challenges in emotion recognition: (i) cross-modal modeling methods that capture and control for interactions between individual facial regions and speech using the Minimum Description Length (MDL) principle-based segmentation; (ii) localization and prediction of events with salient emotional behaviors using a max-margin optimization and dynamic programming; and (iii) temporal modeling methods to learn co-occurrence patterns between emotional behaviors and emotion label noise. These algorithms have enabled advancements in the modeling of audio-visual emotion recognition systems and increased the understanding of the underlying dynamic and multimodal structure of affective communication (e.g., cross-modal interaction, temporal structure, and inherent perceptual ambiguity).

    Biography: Yelin Kim http://yelinkim.com is an Assistant Professor in the Department of Electrical and Computer Engineering at the University at Albany, State University of New York (SUNY). She received her M.S. and Ph.D. in Electrical and Computer Engineering from the University of Michigan, Ann Arbor in 2013 and 2016, respectively, and her B.S. in Electrical and Computer Engineering from Seoul National University, South Korea in 2011. Her main research interests are in human-centered and affective computing, multimodal (audio-visual) modeling, and computational behavior analysis. Her work was recognized by several awards, including a Google Faculty Research Award (2018), a SUNY-A Faculty Research Award (2017), and the Best Student Paper Award at ACM Multimedia (2014).

    Host: Dr. Shrikanth Narayanan

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132

    Audiences: Everyone Is Invited

    Posted By: Tanya Acevedo-Lam/EE-Systems

  • Auto-Tuned Threading for OLDI Microservices

    Thu, Oct 11, 2018 @ 02:00 PM - 03:00 PM

    Ming Hsieh Department of Electrical Engineering

    Conferences, Lectures, & Seminars

    Speaker: Akshitha Sriraman, University of Michigan

    Talk Title: Auto-Tuned Threading for OLDI Microservices

    Abstract: Modern On-Line Data Intensive (OLDI) applications have evolved from monolithic systems to instead comprise numerous, distributed microservices interacting via Remote Procedure Calls (RPCs). Microservices face sub-ms RPC latency goals, much tighter than their monolithic ancestors that must meet >=100ms latency targets. Sub-ms-scale threading and on currency design effects as well as OS and network overheads that were once insignificant for such monoliths, can now come to dominate in the sub-ms-scale microservice regime. It is therefore vital to characterize the influence of threading design, OS, and network effects on microservices. Unfortunately, widely used academic data center benchmark suites are unsuitable to aid this characterization as they use monolithic rather than microservice architectures.

    We first investigate how OS/network overheads impact microservice tail latency by developing a complete suite of microservices called mSuite that we use to facilitate our study. Our characterization reveals that the relationship between optimal OS/network parameters and service load is complex. Our primary finding is that non-optimal OS scheduler decisions can degrade microservice tail latency by up to ~87%.

    Secondly, we investigate how threading design critically impacts microservice tail latency by developing a taxonomy of threading models -“ a structured understanding of the implications of how microservices manage concurrency and interact with RPC interfaces under wide-ranging loads. We develop mTune, a system that has two features: (1) a novel framework that abstracts threading model implementation from application code, and (2) a novel automatic load adaptation system that curtails microservice tail latency by exploiting inherent latency trade-offs revealed in our taxonomy to transition among threading models. We study mTune in the context of mSuite to demonstrate up to 1.9x tail latency improvements over static threading choices and state-of-the-art adaptation techniques.

    Biography: Akshitha is a fourth year Ph.D. student at the University of Michigan, where she is advised by Dr. Thomas F. Wenisch. Her primary research interests are in software systems and computer architecture. Her research focuses on developing software and hardware optimizations to improve the performance of large-scale distributed data center system.

    Host: Xuehai Qian, xuehai.qian@usc.edu

    More Information: 18.10.11 Akshitha Sriraman_CENG.pdf

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

    Audiences: Everyone Is Invited

    Posted By: Brienne Moore

  • BME seminars

    Thu, Oct 11, 2018 @ 03:00 PM - 04:00 PM

    Biomedical Engineering

    Conferences, Lectures, & Seminars

    Abstract: Over the past decade we have been working to develop functional and molecular imaging technologies for a variety of applications. A current focus is technologies capable of functional imaging of picometer scale vibrations in the ear. This collaboration with researchers in otolaryngology has led to several recent papers that contribute new understandings of inner ear function. These were enabled by our development of Optical Coherence Tomography (OCT) as a highly sensitive spatially resolved vibrometer. Building on this approach, we have begun to develop devices to fill unmet clinical needs for diagnosis and therapeutic guidance in humans. The first of those devices (cochleoscope) is an endoscopic OCT system designed to traverse the human ear canal and peer into the inner ear through the round window. This device would be used clinically to identify endolymphatic hydrops, anomalous vibratory response, and ischemia of the inner ear. We recently demonstrated this device in a porcine model and have IRB approval for a first-in-human trial at USC. A second device attaches to the standard operating microscopes in the hearing clinic, enabling noninvasive imaging of middle ear morphology and function. In vivo human testing of this device has shown that we can achieve a sensitivity to vibrations of of

    More Information: Brian E. Applegate Flyer.pdf

    Location: 145a

    Audiences: Everyone Is Invited

    Posted By: Mischalgrace Diasanta

  • Resume Lab - Bring your Laptop!

    Thu, Oct 11, 2018 @ 04:00 PM - 05:00 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions

    Labs are an activity where you can work on your resume in the presence of a career advisor to get tips on the spot.

    Bring your Laptop!

    For more information about Labs & Open Forums, please visit viterbicareers.usc.edu/workshops.

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132

    Audiences: Everyone Is Invited

    Posted By: RTH 218 Viterbi Career Connections

  • Discover USC - Shanghai

    Thu, Oct 11, 2018 @ 07:00 PM - 09:00 PM

    Viterbi School of Engineering Undergraduate Admission

    Receptions & Special Events

    Join the USC Admission Office at the Discover USC admission program in Shanghai.

    This program provides high school seniors and their families with an opportunity to meet admission counselors, alumni, and other prospective students and their parents.

    RSVP for Discover USC

    Location: Hotel Westin Bund Center

    Audiences: Prospective Freshmen & Family Members

    Posted By: Viterbi Admission