JFAA: Technical Report for the EPIC-KITCHENS-100 Action Anticipation Challenge at EgoVis 2026

TL;DR

JFAA is a novel action anticipation method for egocentric videos that leverages a frozen encoder and ensemble techniques, achieving top results in the EPIC-KITCHENS-100 challenge.

Contribution

It introduces a JEPA-based approach with a field-aware ensemble, improving robustness and accuracy in action anticipation tasks.

Findings

Achieved first place in the EgoVis 2026 EK-100 Challenge.

Outperformed previous methods on the official challenge server.

Demonstrated robustness through ensemble over epoch predictions.

Abstract

We propose JFAA, a JEPA-based Future Action Anticipation method for the EPIC-KITCHENS-100 (EK-100) Action Anticipation task. Inspired by the representation learning and future prediction ability of V-JEPA 2.1, JFAA uses a frozen encoder and predictor to extract observed context features and near-future latent tokens. A lightweight attentive probe is then trained to predict verb, noun, and action logits with separate task queries. To improve robustness, we further build a field-aware ensemble over selected epoch-level predictions, allowing each output field to benefit from its most reliable candidates. Experimental results on the official challenge server show that JFAA achieves first place in the EgoVis 2026 EK-100 Action Anticipation Challenge. Our code will be released at https://github.com/CorrineQiu/JFAA.