LAC: Latent Action Composition for Skeleton-based Action Segmentation

TL;DR

LAC introduces a self-supervised framework that synthesizes diverse composable skeleton motions in a latent space, significantly improving action segmentation accuracy without extra temporal models.

Contribution

The paper presents a novel latent space generator for synthesizing composable skeleton motions and leverages contrastive learning for enhanced representation in action segmentation.

Findings

Outperforms state-of-the-art on TSU, Charades, PKU-MMD datasets.

Synthesized diverse motions improve representation learning.

End-to-end fine-tuning enhances segmentation accuracy.

Abstract

Skeleton-based action segmentation requires recognizing composable actions in untrimmed videos. Current approaches decouple this problem by first extracting local visual features from skeleton sequences and then processing them by a temporal model to classify frame-wise actions. However, their performances remain limited as the visual features cannot sufficiently express composable actions. In this context, we propose Latent Action Composition (LAC), a novel self-supervised framework aiming at learning from synthesized composable motions for skeleton-based action segmentation. LAC is composed of a novel generation module towards synthesizing new sequences. Specifically, we design a linear latent space in the generator to represent primitive motion. New composed motions can be synthesized by simply performing arithmetic operations on latent representations of multiple input skeleton sequences. LAC leverages such synthesized sequences, which have large diversity and complexity, for learning visual representations of skeletons in both sequence and frame spaces via contrastive learning. The resulting visual encoder has a high expressive power and can be effectively transferred onto action segmentation tasks by end-to-end fine-tuning without the need for additional temporal models. We conduct a study focusing on transfer-learning and we show that representations learned from pre-trained LAC outperform the state-of-the-art by a large margin on TSU, Charades, PKU-MMD datasets.