BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:327@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20260114T140000
DTEND;TZID=Europe/Paris:20260114T140000
DTSTAMP:20260828T082758Z
URL:https://isdm.umontpellier.fr/events/interpreting-the-contribution-of-s
 ensors-in-blind-source-extraction-by-means-of-shapley-values-2/
SUMMARY:Interpreting the contribution of sensors in blind source extraction
  by means of Shapley values
DESCRIPTION:Room Nadir\, Maison de la Télédétection\, Agropolis campus\n
 \nMachine Learning in Montpellier\, Theory &amp\; Practice - Guilherme Dea
 n Pelegrina (Mackenzie Presbyterian University\, Brazil)\n\nMany applicati
 ons involve estimating a source of interest from mixed signals collected b
 y multiple sensors. While many works focus on optimization task for source
  extraction\, less attention has been given to interpreting how each senso
 r contributes to the result. In this talk\, Guilherme presents a model-agn
 ostic\, game-theoretic approach based on Shapley values to quantify sensor
  contributions and interaction effects\, with experiments on synthetic and
  real data. Eugenio Dias Ribeiro Neto (LIRMM): Title: An improved architec
 ture for part-based animal re-identification through semantic segmentation
  distillation Abstract: Animal re-identification is essential for non-inva
 sive wildlife monitoring but remains challenging due to limited data and h
 igh appearance variability. Eugenio will present PAW-ViT\, a part-aware Vi
 sion Transformer that uses learnable part tokens specialized for anatomica
 l regions. The method achieves state-of-the-art results on animal Re-ID be
 nchmarks\, especially under strong viewpoint changes.\n\nMachine Learning 
 in Montpellier\, Theory &amp\; Practice
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2026/06/ml-mtp-gC78d5.png
CATEGORIES:ML MTP
LOCATION:Room Nadir\, Maison de la Télédétection\, Agropolis Campus\, Mo
 ntpellier\, 34000\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Agropolis Campus\, Montpell
 ier\, 34000\, France;X-APPLE-RADIUS=100;X-TITLE=Room Nadir\, Maison de la 
 Télédétection:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR