Thesis icon

Thesis

Objects from motion

Abstract:

This thesis tackles the challenge of learning the abstract structure of object categories without manual supervision. We show that we can learn useful representations based on the motion of objects in videos and even from collections of static images through the use of synthetic warps. An important contribution of this work is the notion of an Object Frame, an object-centric frame of reference which can be learned from motion. Objects that appear in images can be affected by compl...

Expand abstract

Actions


Access Document


Files:

Authors


James Thewlis More by this author

Contributors

Role:
Supervisor
Type of award:
DPhil
Level of award:
Doctoral
Awarding institution:
University of Oxford

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP