BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://ai.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:35646533-3333-4634-b031-333965326636
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:On Conditional Generative Adversarial Networks: Iterative Gene
 ration and Holistic Evaluation - Graham Taylor\, Associate Professor\, Uni
 versity of Guelph
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20211107T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20191103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20201101T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20190310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20200308T020000
RDATE:20210314T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:4a3de75a-9d97-4597-a494-7dd14c0a66c6
DTSTAMP:20260724T055401Z
CLASS:PUBLIC
CREATED:20191127T202228Z
DESCRIPTION:Abstract: Conditional Generative Adversarial Networks (cGANs) a
 re finding increasingly widespread use in many application domains\, most 
 notably text-to-image synthesis. In this talk\, I will address two outstan
 ding limitations of this paradigm. First\, existing research has primarily
  focused on generating a single image from available conditioning informat
 ion in one step. A practical extension of one-step generation is generatin
 g an image iteratively\, conditioned on ongoing linguistic input or feedba
 ck. I will present a recurrent image generation model which takes into acc
 ount both the generated…
DTSTART;TZID=America/Vancouver:20191206T170000
DTEND;TZID=America/Vancouver:20191206T180000
LAST-MODIFIED:20210611T171100Z
LOCATION:MacLeod (MCLD) - 254\, 2356 Main Mall\, Vancouver\, BC
SUMMARY:On Conditional Generative Adversarial Networks: Iterative Generatio
 n and Holistic Evaluation - Graham Taylor\, Associate Professor\, Universi
 ty of Guelph
TRANSP:OPAQUE
URL:https://ai.ubc.ca/index.php/event/conditional-generative-adversarial-ne
 tworks-iterative-generation-and-holistic-evaluation
END:VEVENT
END:VCALENDAR