BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20220313T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221106T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20221011T174030Z
UID:4B1DEBAF-9CED-416B-B7D1-563B2C0A3A79
DTSTART;TZID=America/Chicago:20221010T110000
DTEND;TZID=America/Chicago:20221010T120000
DESCRIPTION:With the proliferation of surveillance cameras\, society needs 
 means to identify people from the images these cameras provide. Crime-solv
 ing websites are replete with imagery of criminals who are often disguised
  and/or at low resolution\; terrorist attacks yield more imagery. We notic
 ed this many years ago and were the first to develop systems that aimed to
  recognize people by their gait and their style of walking.\n\nThis talk w
 ill describe some of the earlier approaches and their motivation\, togethe
 r with the recent works on deep learning. More recently we have moved to r
 ecognize from human descriptions\, consistent with eyewitness statements a
 nd the limited spatial and temporal resolution of surveillance imagery\, a
 nd the chance of disguise. We have shown that human descriptions can be us
 ed for recognition and retrieval and formulated ways to make these descrip
 tions more effective. We have so far used descriptions of the face\, the b
 ody\, and the clothing\, and our current work shows how the labels can be 
 derived by computer vision and explore the new information available by th
 e interface between semantic description and automated recognition. This t
 alk thus surveys these areas\, describing progress in gait and in soft bio
 metrics.\n\nSpeaker(s): Prof Nixon\, \n\nVirtual: https://events.vtools.ie
 ee.org/m/324472
LOCATION:Virtual: https://events.vtools.ieee.org/m/324472
ORGANIZER:ztaqvi@gmail.com
SEQUENCE:2
SUMMARY:IEEE-DAY\," Gait and Soft Biometrics"\; GBS BIOMETRIC AND SYSTEMS W
 EEK\, WEBINAR #1 of 4
URL;VALUE=URI:https://events.vtools.ieee.org/m/324472
X-ALT-DESC:Description: <br /><p>With the proliferation of surveillance cam
 eras\, society needs means to identify people from the images these camera
 s provide. Crime-solving websites are replete with imagery of criminals wh
 o are often disguised and/or at low resolution\; terrorist attacks yield m
 ore imagery. We noticed this many years ago and were the first to develop 
 systems that aimed to recognize people by their gait and their style of wa
 lking.</p>\n<p>This talk will describe some of the earlier approaches and 
 their motivation\, together with the recent works on deep learning. More r
 ecently we have moved to recognize from human descriptions\, consistent wi
 th eyewitness statements and the limited spatial and temporal resolution o
 f surveillance imagery\, and the chance of disguise. We have shown that hu
 man descriptions can be used for recognition and retrieval and formulated 
 ways to make these descriptions more effective. We have so far used descri
 ptions of the face\, the body\, and the clothing\, and our current work sh
 ows how the labels can be derived by computer vision and explore the new i
 nformation available by the interface between semantic description and aut
 omated recognition. This talk thus surveys these areas\, describing progre
 ss in gait and in soft biometrics.</p>
END:VEVENT
END:VCALENDAR