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:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20181104T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69c234283c018
DTSTART;TZID=America/Toronto:20190909T100000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20190909T100000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-mlod-multi-view-3d-object
LOCATION:DC - William G. Davis Computer Research Centre 200 University Aven
 ue West 2310 Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: MLOD: A Multi-view 3D Object Detect
 ion\nBased on Robust Feature
CLASS:PUBLIC
DESCRIPTION:JIAN DENG\, MASTER’S CANDIDATE\n_David R. Cheriton School of 
 Computer Science_\n\nThis thesis presents Multi-view Labelling Object Dete
 ctor (MLOD). The\ndetector takes an RGB image and a LIDAR point cloud as i
 nput and\nfollows the two-stage object detection framework\n\\cite{girshic
 k2015fast} \\cite{ren2015faster}. A Region Proposal\nNetwork (RPN) generat
 es 3D proposals in a Bird's Eye View (BEV)\nprojection of the point cloud.
  The second stage projects the 3D\nproposal bounding boxes to the image an
 d BEV feature maps and sends\nthe corresponding map crops to a detection h
 eader for classification\nand bounding-box regression.
DTSTAMP:20260324T065016Z
END:VEVENT
END:VCALENDAR