<div dir="ltr"><div class="gmail_default" style="font-family:georgia,serif;font-size:small"><div style="font-family:Arial,Helvetica,sans-serif"><p style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;line-height:normal;margin:0px"><font face="georgia, serif"><b><font style="vertical-align:inherit"><font style="vertical-align:inherit">When:    </font></font></b><font style="vertical-align:inherit"><font style="vertical-align:inherit"> Thursday, April 27th at <b><font color="#000000" style="background-color:rgb(255,255,0)"> 2PM CT</font></b></font></font><br></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif"> </font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>Where:    </b><span class="gmail_default"><b></b></span><span class="gmail_default">T</span></font></font><span style="color:rgb(0,0,0)">alk will be giv</span><span style="color:rgb(0,0,0)">en </span><font style="color:rgb(0,0,0);font-weight:bold"><u style="background-color:rgb(255,255,0)">live, in-person</u></font><font style="color:rgb(0,0,0);font-weight:bold"> </font><span style="color:rgb(0,0,0)">at</span></font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif">                     TTIC, 6045 S. Kenwood Avenue</font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif">                     5th Floor, Room 530<b> </b></font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"><b><br></b></font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif"><font color="#000000"><span class="gmail_default"><b>Virtually:  </b>  via Panopto<b> (<a href="https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=002fef14-d192-4af5-bc05-afcf00fac74d" target="_blank">Livestream</a>) </b></span></font><font color="#000000"><b><br></b></font></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif"> </font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>Who:      <span class="gmail_default"></span> </b>  Professor Mubarak Shah, </font></font></font><font face="georgia, serif">University of Central Florida</font></p></div><div style="font-family:Arial,Helvetica,sans-serif"><b style="color:rgb(33,33,33)"><font face="georgia, serif"><br></font></b></div><div style="font-family:Arial,Helvetica,sans-serif"><font face="georgia, serif"><b style="color:rgb(33,33,33)">Title:         </b>Beyond Supervised Human Action Recognition: Learning with Limited Labels and Privacy Preservation</font></div><div style="font-family:Arial,Helvetica,sans-serif"><p></p><div><font face="georgia, serif"><b style="color:rgb(33,33,33)">Abstract:   </b><span style="background-color:transparent;color:rgb(0,0,0);white-space:pre-wrap;text-align:justify">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. </span></font></div><div><font face="georgia, serif"><span style="background-color:transparent;color:rgb(0,0,0);white-space:pre-wrap;text-align:justify"><br></span></font></div><font face="georgia, serif"><span id="m_-8998792012026308317m_-954336598833249322m_3827444652348200191gmail-docs-internal-guid-6dcc8b03-7fff-53a9-63f2-3a40928c89ee"><p dir="ltr" style="line-height:1.295;text-align:justify;margin-top:0pt;margin-bottom:8pt"><span style="color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre-wrap">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.</span></p><p dir="ltr" style="line-height:1.295;text-align:justify;margin-top:0pt;margin-bottom:8pt"><span style="color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre-wrap">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.</span></p></span><br></font></div><div style="font-family:Arial,Helvetica,sans-serif"><font face="georgia, serif"><br></font><div><p style="box-sizing:border-box;border-radius:0px;margin:0px 0px 10px"><font face="georgia, serif"><font color="#000000"><span style="box-sizing:border-box;border-radius:0px;font-weight:700">B</span><span style="box-sizing:border-box;border-radius:0px;font-weight:700">io:</span>    </font><span style="text-align:justify;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;color:rgb(0,0,0);vertical-align:baseline;white-space:pre-wrap">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  14</span><span style="text-align:justify;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;color:rgb(0,0,0);vertical-align:baseline;white-space:pre-wrap"><span style="vertical-align:super">th</span></span><span style="text-align:justify;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;color:rgb(0,0,0);vertical-align:baseline;white-space:pre-wrap"> 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</span><span style="text-align:justify;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;color:rgb(0,0,0);font-weight:700;vertical-align:baseline;white-space:pre-wrap">; </span><span style="text-align:justify;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;color:rgb(0,0,0);vertical-align:baseline;white-space:pre-wrap">Scholarship of Teaching and Learning award; Teaching Incentive Program award; Research Incentive Award.</span></font></p><font face="georgia, serif"><br></font></div><div><p style="box-sizing:border-box;border-radius:0px;margin:0px 0px 10px"><font face="georgia, serif"><font color="#000000"><span style="box-sizing:border-box;border-radius:0px;font-weight:700">Hos</span><b><span style="box-sizing:border-box;border-radius:0px">t:</span> <a href="mailto:mturk@ttic.edu" target="_blank">Matthew Turk</a></b></font></font></p></div></div></div><div><br></div><span>-- </span><br><div dir="ltr" data-smartmail="gmail_signature"><div dir="ltr"><b style="background-color:rgb(255,255,255)"><font color="#3d85c6">Brandie Jones </font></b><div><div><div><font color="#3d85c6"><b><i>Executive </i></b></font><b style="color:rgb(61,133,198)"><i>Administrative Assistant</i></b></div></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">Toyota Technological Institute</font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">6045 S. Kenwood Avenue</font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">Chicago, IL  60637</font></span></div></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6"><a href="http://www.ttic.edu" target="_blank">www.ttic.edu</a> </font></span></div><div><font color="#3d85c6"><div style="background-color:rgb(238,238,238)"><div style="color:rgb(32,33,36)"><span style="color:rgb(61,133,198)">Working Remotely on Tuesdays</span></div></div></font></div></div></div></div>