Objects from motion

<p>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 i...

Fuld beskrivelse

Bibliografiske detaljer
Hovedforfatter: Thewlis, J
Andre forfattere: Vedaldi, A
Format: Thesis
Udgivet: 2018