BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20180325T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20171029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260424T143108Z
UID:5a8452e01a2dd518814394@ist.ac.at
DTSTART:20180227T113000
DTEND:20180227T123000
DESCRIPTION:Speaker: Vittorio Ferrari\nhosted by Christoph Lampert\nAbstrac
 t: Overview of papers by my team recently accepted to CVPR 2018:(1) We rev
 isit knowledge transfer for training object detectors on target classes fr
 om weakly supervised training images\, helped by source classes with bound
 ing-box annotations. We explore knowledge transfer functions ranging from 
 class-specific to class-generic\, demonstrate large improvements over weak
 ly supervised baselines\, and also carry out across-dataset transfer exper
 iments.(2) We introduce Intelligent Annotation Dialogs: we train an agent 
 to automatically choose a sequence of actions for a human annotator to pro
 duce a bounding box in a minimal amount of time. We introduce a model-base
 d agent and an reinforcement learning agent and demonstrate that both agen
 ts can adapt to image difficulty\, detector strength\, and desired box qua
 lity.(3) Semantic classes can be either things (e.g. car) or stuff (e.g. g
 rass). To understand stuff and things in context we enhance the complete C
 OCO dataset (164K images) with stuff annotations and carry out a wide rang
 e of analysis.(4) We present a semantic part detection model that leverage
 s various types of object information as context\, all integrated in a neu
 ral network. This leads to considerably higher performance compared to usi
 ng part appearance alone.
LOCATION:Mondi Seminar Room 3\, Central Building\, ISTA
ORGANIZER:abonvent@ist.ac.at
SUMMARY:Vittorio Ferrari: All our CVPR 2018 papers: knowledge transfer\, an
 notation dialogs\, COCO-Stuff\, and semantic part detection
URL:https://talks-calendar.ista.ac.at/events/1121
END:VEVENT
END:VCALENDAR