Files in this item



application/pdfGOYAL-THESIS-2021.pdf (26MB)Restricted to U of Illinois
(no description provided)PDF


Title:Inferring object states and articulation modes from egocentric videos
Author(s):Goyal, Rishabh
Advisor(s):Gupta, Saurabh
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Computer Vision
Machine Learning
Feature Learning
Object Understanding
Abstract:We develop algorithms for understanding objects from the point of view of interacting with them. There are two key aspects to obtaining such an understanding. First, objects can occur in different states and we need features that are sensitive to such states. Second, different objects can be articulated in different ways and we need to understand how to correctly infer their modes of articulation. We propose self and weakly supervised techniques to obtain such an understanding of objects purely through observation of how humans interact with the world around them through their hands. Our experiments on the challenging EPIC- KITCHENS dataset show the merits of using human hands as a probe for understanding objects.
Issue Date:2021-04-28
Rights Information:Copyright 2021 Rishabh Goyal
Date Available in IDEALS:2021-09-17
Date Deposited:2021-05

This item appears in the following Collection(s)

Item Statistics