BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IEM Distinguished Lecturers Seminar: Artificial Intelligence for P
 erceptually-Enabled Task Assistants
DTSTART:20240308T131500
DTEND:20240308T140000
DTSTAMP:20260510T111843Z
UID:a1720b1e9cf6026e0173286db443403a2f907a1513228ff7465becc1
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Ehsan Elhamifar\,\nComputer Science at Northeastern Univ
 ersity\, Boston\, USA\n\n \nThe seminar will take place in ELA 1 and by z
 oom.\nExceptionally\, no broadcast will be available on the Neuchâtel cam
 pus.\n\nCoffee and cookies will be served from 13:00.\n\n\nAbstract\nHuman
 s perform a wide range of complex activities\, such as cooking hour-long r
 ecipes\, assembling and repairing devices and performing surgeries. Many o
 f these activities are procedural: they consist of sequences of steps that
  must be followed to achieve the desired goals. Learning complex procedure
 s from videos of humans performing them allows us to design intelligent ta
 sk assistants\, robots and coaching platforms that perform or guide peopl
 e through tasks. In this talk\, we present new neural architectures as wel
 l as learning and inference frameworks to understand complex activity vide
 os\, addressing the following challenges: i) Procedural videos are long\, 
 uncurated and contain many task-irrelevant activities\, with different vid
 eos showing different ways of performing the same task. ii) Gathering fram
 ewise video annotation is costly and not scalable to many videos and tasks
 . ii) At inference time\, we must accurately recognize actions as data arr
 ive in real-time\, especially with only a few frames.\n\nBio\nEhsan Elhami
 far is an Associate Professor in the Khoury College of Computer Sciences\,
  the director of the Mathematical Data Science (MCADS) Lab and the Directo
 r of MS in AI at Northeastern University. He has broad research interests 
 in computer vision\, machine learning and AI. The overarching goal of his 
 research is to develop AI that learns from and makes inferences about data
  analogous to humans. He is a recipient of the DARPA Young Faculty Award. 
 Prior to Northeastern\, he was a postdoctoral scholar in the EECS departme
 nt at UC Berkeley. He obtained his PhD in ECE at the Johns Hopkins Univers
 ity (JHU) and received two Masters degrees\, one in EE from Sharif Univers
 ity of Technology in Iran and another in Applied Mathematics and Statistic
 s from JHU.\n 
LOCATION:ELA 1 https://plan.epfl.ch/?room==ELA%201 https://epfl.zoom.us/j/
 67317987786
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR