← Search

Daniel M Bear

2 accepted papers

2024

Understanding Physical Dynamics with Counterfactual World Modeling

ECCV 2024poster

"The ability to understand physical dynamics is critical for agents to act in the world. Here, we use Counterfactual World Modeling (CWM) to extract vision structures for dynamics understanding. CWM uses a temporally-factored masking policy for masked prediction of video data without annotations. Th…

2022

Unsupervised Segmentation in Real-World Images via Spelke Object Inference

ECCV 2022poster

"Self-supervised, category-agnostic segmentation of real-world images is a challenging open problem in computer vision. Here, we show how to learn static grouping priors from motion self-supervision by building on the cognitive science concept of a Spelke Object: a set of physical stuff that moves t…