FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation

Zijia Lu, Ehsan Elhamifar

Abstract:

We study supervised action segmentation, whose goal is
to predict framewise action labels of a video. To capture temporal dependencies over long horizons, prior works either
improve framewise features with transformer or refine framewise predictions with learned action features. However, they
are computationally costly and ignore that frame and action
features contain complimentary information, which can be
leveraged to enhance both features and improve temporal
modeling. Therefore, we propose an efficient Frame-Action
Cross-attention Temporal modeling (FACT) framework that
performs temporal modeling with frame and action features
in parallel and leverage this parallelism to achieve iterative
bidirectional information transfer between the features and
refine them. FACT network contains (i) a frame branch to
learn frame-level information with convolutions and frame
features, (ii) an action branch to learn action-level dependencies with transformers and action tokens and (iii) crossattentions to allow communication between the two branches.
We also propose a new matching loss to ensure each action token uniquely encodes an action segment, thus better captures
its semantics. Thanks to our architecture, we can also leverage textual transcripts of videos to help action segmentation.
We evaluate FACT on four video datasets (two egocentric and
two third-person) for action segmentation with and without
transcripts, showing that it significantly improves the stateof-the-art accuracy while enjoys lower computational cost
(3 times faster) than existing transformer-based methods.