BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//BioMedIA - ECPv6.15.11//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:BioMedIA
X-ORIGINAL-URL:https://biomedia.doc.ic.ac.uk
X-WR-CALDESC:Events for BioMedIA
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20160101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20170328T113000
DTEND;TZID=UTC:20170328T123000
DTSTAMP:20260418T144327
CREATED:20170324T121905Z
LAST-MODIFIED:20170324T121905Z
UID:3375-1490700600-1490704200@biomedia.doc.ic.ac.uk
SUMMARY:BioMedIA Talk: Wenzhe Shi (Twitter)
DESCRIPTION:Neural network’s for super resolution\n  \nAbstract\nThe most important parts for using neural network’s for super resolution are data\, network architecture and the objective functions. In this talk we will discuss our innovation in network architecture to make our algorithms running real time on mobile devices as well as how we achieved a new level of perceived qualities for super resolved images by redefining the object functions. Finally we will close the talk by showing what’s the best practice when extending image super resolution techniques to videos.
URL:https://biomedia.doc.ic.ac.uk/event/biomedia-talk-wenzhe-shi-twitter/
LOCATION:Huxley 218
END:VEVENT
END:VCALENDAR