[Colloquium] Reminder: Pervaiz/MS Presentation/Apr 26, 2019

[Margaret Jaffey]

This is a reminder about Ahsan Pervaiz's MS Presentation tomorrow.
Please note that it will be held in Ry 277.

------------------------------------------------------------------------------
Date:  Friday, April 26, 2019

Time:  3:00 PM

Place:  Ryerson 277

M.S. Candidate:  Ahsan Pervaiz

M.S. Paper Title: DDS: Analytics-Oriented Video Streaming Stack

Abstract:
As deep learning becomes the de-facto approach to live video
analytics, we are seeing a surge in efforts to develop distributed
analytics pipelines that leverage the cloud resources to run deep
neural networks (DNNs) on live videos from edge cameras. Most work has
so far focused on offloading computation from the edge devices to the
cloud. This paper highlights a crucial yet missing piece in the
distributed video analytics pipeline – a custom video streaming stack
to balance the inference accuracy and bandwidth usage between cameras
and analytics servers. Through empirical studies, we have found
unexploited opportunities to customize today’s video streaming stack
for video analytics. Inspired by the findings, we present DDS , a
video streaming stack that caters to distributed video analytics.
Unlike previous video streaming mechanisms designed to meet user
experience or bandwidth budget, DDS is built on a novel DNN-driven
workflow that relies on server-side DNN logic to explicitly balance
the video analytics accuracy and bandwidth savings. At the core of DDS
is an interactive streaming protocol built on the active learning
framework to make DNN-driven workflow practical. We implement DDS as
an underlying video streaming layer which could be combined with a
wide variety of distributed video analytics pipelines. Through
intensive evaluation on real-world video datasets, we find that DDS
reduces the bandwidth consumption by 2-20x compared to other video
analytics pipelines with minimal accuracy drop.

Ahsan's advisor is Prof. Henry Hoffmann

Login to the Computer Science Department website for details:
 https://newtraell.cs.uchicago.edu/phd/ms_announcements#ahsanp

=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Margaret P. Jaffey            margaret at cs.uchicago.edu
Department of Computer Science
Student Support Rep (Ry 156)               (773) 702-6011
The University of Chicago      http://www.cs.uchicago.edu
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=