[Theory] NOW: 4/27 TTIC Colloquium: Mubarak Shah, University of Central Florida

[Brandie Jones]

*When:    * Thursday, April 27th at * 2PM CT*



*Where:    *Talk will be given *live, in-person* at

                     TTIC, 6045 S. Kenwood Avenue

                     5th Floor, Room 530


*Virtually:  *  via Panopto* (Livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=002fef14-d192-4af5-bc05-afcf00fac74d>)
*



*Who:       *  Professor Mubarak Shah, University of Central Florida

*Title:         *Beyond Supervised Human Action Recognition: Learning with
Limited Labels and Privacy Preservation

*Abstract:   *Human action recognition is one of the most active areas of
research in Computer Vision. Due to deep learning tremendous progress has
been made and several high-performance methods have been proposed. This
extraordinary success of deep learning methods can be mostly attributed to
advancements in supervised learning algorithms and the availability of
large-scale labeled datasets. However, constructing large, labeled video
datasets for supervised learning tends to be costly and is often
infeasible.

In this talk, I will discuss our recent work on human action recognition
employing learning with limited labels. In particular, I will present our
work employing Semi-supervised learning (SSL), Self-supervised learning and
Zero-short learning. First, I will present our Uncertainty-aware
Pseudo-label Selection (UPS) method for semi-supervised learning, which
improves pseudo labeling accuracy by drastically reducing the amount of
noise encountered in the training process. Next, I will present
self-supervised method, TCLR: Temporal Contrastive Learning for Video
Representations, which is a new temporal contrastive learning framework
consisting of two novel losses to improve upon existing contrastive
self-supervised video representation learning method.   Finally, I will
present two Zero-shot Action Recognition methods: Pairwise-Similarity
Zero-shot Action Recognition (PS-ZAR) and Vita-CIP.  Given a video and a
set of action classes, PS-ZCAR  predicts a set of confidence scores for
each class independently. Vita-CLIP is multimodal prompting-based Video and
text method, that works to balance the supervised and zero-shot performance
under a single unified training.

Advances in action recognition have enabled a wide range of real-world
applications, e.g. video surveillance camera, smart shopping systems,
elderly person monitor systems. Most of these video understanding
applications involve extensive computation, for which a user needs to share
the video data to the cloud computation server, where the user also ends up
sharing the  private visual information like gender, skin color, clothing,
background objects etc. Therefore, there is a pressing need for solutions
to privacy preserving action recognition. I will end this talk by briefly
discuss our recent method SPAct: Self-supervised Privacy Preservation for
Action Recognition.


Bio:    Dr. Mubarak Shah, the UCF Trustee Chair Professor, is the founding
director of Center for Research in Computer Visions at University of
Central Florida (UCF). Dr. Shah is a fellow of ACM, IEEE, NAI, IAPR, AAAS,
AAIA and SPIE; and a member of Academy of Science, Engineering and Medicine
of Florida (ASEMFL). He has published extensively on topics related to
visual surveillance, visual tracking, human activity and action
recognition, object detection and categorization, shape from shading, geo
registration, visual crowd analysis, etc.  He has been ACM and IEEE
Distinguished Visitor Program speaker and is often invited to present
seminars, tutorials and invited talks all over the world.  He is a
recipient of ACM SIGMM Technical Achievement award; ACM SIGMM Test of
Time  Honorable  Mention  Award  for  his paper  in  Proceedings  of  the
14th ACM International Conference on Multimedia, MM 06;  International
Conference  on  Pattern  Recognition (ICPR)   2020  Best  Scientific
Paper  Award; IEEE Outstanding Engineering Educator Award; Harris
Corporation Engineering Achievement Award; an honorable mention for the
ICCV 2005 Where Am I? Challenge Problem; 2013 NGA Best Research Poster
Presentation; 2nd place in Grand Challenge at the ACM Multimedia 2013
conference; and runner up for the best paper award in ACM Multimedia
Conference in 2005 and 2010. At UCF he has received Pegasus Professor
Award; University Distinguished Research Award; Faculty Excellence in
Mentoring Doctoral Students; Scholarship of Teaching and Learning award;
Teaching Incentive Program award; Research Incentive Award.

Hos*t: Matthew Turk <mturk at ttic.edu>*

-- 
*Brandie Jones *
*Executive **Administrative Assistant*
Toyota Technological Institute
6045 S. Kenwood Avenue
Chicago, IL  60637
www.ttic.edu
Working Remotely on Tuesdays
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20230427/b11d7192/attachment.html>