Ho-Su Lee

PRISM: Predictive Recomposition via Semantic Latent Decomposition for View-invariant Video Representation Learning

This work decomposes video into view-invariant and view-variant latents and recompose them under language supervision encouraging clean decomposition of the two streams, and proposes PRISM, that achieves state-of-the-art results on EgoExo4D, EgoExoLearn, AE2, even surpassing in-domain models under zero-shot setting.