PRISM: Predictive Recomposition via Semantic Latent Decomposition for View-invariant Video Representation Learning
TL;DR
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.
Abstract
Cross-view video representation learning aims to capture viewpoint-invariant action semantics despite substantial appearance changes across egocentric and exocentric videos. However, existing methods encode each video as a unified embedding, where view-invariant and view-variant semantics inevitably entangle under co-occurrences - a failure mode we show persists even in cross-view methods explicitly trained for view-invariance. Our key insight is that a view-invariant feature is truly disentangled when it can be sufficiently recomposed with an arbitrary view-variant feature while preserving their independent semantics. Building on this, we propose PRISM, that decomposes video into view-invariant and view-variant latents and recompose them under language supervision encouraging clean decomposition of the two streams. PRISM achieves state-of-the-art results on EgoExo4D, EgoExoLearn, AE2, even surpassing in-domain models under zero-shot setting. Code is available at https://github.com/litcoderr/prism.
