Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates

Human‑JEPA is a human‑centric vision model trained on video that uses anchored forecasting to prevent silent collapse of dense perception. By replacing block masks with a pure past‑to‑future split, it avoids action‑tax and re‑identification collapse, enabling strong performance on pose and person re‑identification with far fewer parameters. The released predictor head uniquely preserves anticipation capability, allowing a single model to handle both perception and anticipation of humans.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.