Michael Maynord — accepted AI-conference papers

2023

Mid-Vision Feedback

Michael Maynord, Eadom T Dessalene, Cornelia Fermuller, Yiannis Aloimonos

ICLR 2023poster

Feedback plays a prominent role in biological vision, where perception is modulated based on agents' evolving expectations and world model. We introduce a novel mechanism which modulates perception based on high level categorical expectations: Mid-Vision Feedback (MVF). MVF associates high level con…

Cited by 3 Source ↗PDF ↗Scholar ↗

2023

Therbligs in Action: Video Understanding Through Motion Primitives

Eadom Dessalene, Michael Maynord, Cornelia Fermüller, Yiannis Aloimonos

CVPR 2023poster

In this paper we introduce a rule-based, compositional, and hierarchical modeling of action using Therbligs as our atoms. Introducing these atoms provides us with a consistent, expressive, contact-centered representation of action. Over the atoms we introduce a differentiable method of rule-based re…

Cited by 17 Source ↗PDF ↗Scholar ↗