BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20151025T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20150329T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.7090.field_data.0@www.ugov-ricerca.uniroma1.it
DTSTAMP:20260404T184413Z
CREATED:20150625T111957Z
DESCRIPTION:In this talk\, we introduce a novel incremental and active lear
 ning classification approach that can be used with any local or global set
  of feature descriptors extracted from a segmented video stream. Our syste
 m is nonparametric: it covers the feature space with classifiers that loca
 lly approximate the Bayes optimal classifier. We focus on streaming scenar
 ios\, in which our approach features incremental model updates and on-the-
 fly addition of new classes. Moreover\, predictions are computed in time l
 ogarithmic in the model's size (which is typically fairly small)\, and act
 ive learning is used to save labeling costs. A ``constant budget'' variant
  is also presented to limit the grow of model size over time\, as an appea
 ling feature in real-time applications. We apply this methodology to human
  activity recognition tasks. Experiments on standard benchmarks show that 
 our approach is competitive with state-of-the-art non-incremental methods\
 , and outperforms the existing active incremental baselines.
DTSTART;TZID=Europe/Paris:20150702T143000
DTEND;TZID=Europe/Paris:20150702T143000
LAST-MODIFIED:20150701T132159Z
LOCATION:room B101
SUMMARY:Action Recognition in Streaming Videos via Incremental Active Learn
 ing - Dr. Rocco De Rosa
URL;TYPE=URI:http://www.ugov-ricerca.uniroma1.it/node/7090
END:VEVENT
END:VCALENDAR