Anticipating outcomes is the root of intelligence. This thesis investigates Predictive Vision with the goal to develop robust methods that anticipate the next events that may happen in images or videos. Importantly, we develop methods for eciently scaling learning algorithms to learn an extensive set of rules that enable richer visual understanding. While large annotated datasets fuel progress in object recognition, the knowledge required for event understanding is vast and potentially ambiguous. To tackle this challenge, we develop predictive vision algorithms that instead learn these rules directly from large amounts of raw, unlabeled data. Capitalizing on millions of natural videos, this work develops algorithms that learn to anticipate the visual future, forecast human actions, and recognize ambient sounds.
Predictive vision
2017
106 pages
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 95-106).
Hochschulschrift
Elektronische Ressource
Englisch
Predictive Landing Guidance in Synthetic Vision Displays
AIAA | 2009
|Predictive Maintenance Apparatus based on Vision Inspection
Europäisches Patentamt | 2022
Predictive Maintenance Apparatus based on Vision Inspection
Europäisches Patentamt | 2022
|Predictive Euler CFD - Resolution of NASA Vision 2030
AIAA | 2022
|Model Predictive Control for Vision-Based Platooning Utilizing Road Topography
BASE | 2021
|