BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal iCal API//EN
X-WR-CALNAME:Events items teaser
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
DTSTART:20180311T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20171105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69b2453257394
DTSTART;TZID=America/Toronto:20180629T100000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20180629T100000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/phd-defence-c
 omputer-vision-web-pages-study-man-made-images
LOCATION:DC - William G. Davis Computer Research Centre 200 University Aven
 ue West 2310 Waterloo ON N2L 3G1 Canada
SUMMARY:PhD Defence: Computer Vision on Web Pages: A Study of Man-Made Imag
 es
CLASS:PUBLIC
DESCRIPTION:Michael Cormier\, PhD candidate\n\nThis thesis is focused on th
 e development of computer vision\ntechniques for parsing web pages using a
 n image of the rendered page\nas evidence\, and on understanding this unde
 r-explored class of images\nfrom the perspective of computer vision. This 
 project is divided into\ntwo tracks — applied and theoretical — which 
 complement each\nother. Our practical motivation is the application of imp
 roved web\npage parsing to assistive technology\, such as screenreaders fo
 r\nvisually impaired users or the ability to declutter the presentation\no
 f a web page for those with cognitive deficit. From a more\ntheoretical st
 andpoint\, images of rendered web pages have interesting\nproperties from 
 a computer vision perspective\; in particular\,\nlow-level assumptions can
  be made in this domain\, but the most\nimportant cues are often subtle an
 d can be highly non-local. The\nparsing system developed in this thesis is
  a principled Bayesian\nsegmentation-classification pipeline\, using innov
 ative techniques to\nproduce valuable results in this challenging domain. 
 The thesis\nincludes both implementation and evaluation solutions.
DTSTAMP:20260312T044642Z
END:VEVENT
END:VCALENDAR