MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language Recognition

TL;DR

MASA introduces a self-supervised learning framework for sign language recognition that explicitly models motion cues and aligns global semantic information, significantly improving representation capabilities and achieving state-of-the-art results.

Contribution

The paper proposes a novel MASA framework combining motion-aware masked autoencoding and semantic alignment for enhanced sign language recognition.

Findings

Achieves state-of-the-art performance on four benchmarks.

Effectively models dynamic motion cues in sign sequences.

Enhances global semantic understanding in sign language recognition.

Abstract

Sign language recognition (SLR) has long been plagued by insufficient model representation capabilities. Although current pre-training approaches have alleviated this dilemma to some extent and yielded promising performance by employing various pretext tasks on sign pose data, these methods still suffer from two primary limitations: 1) Explicit motion information is usually disregarded in previous pretext tasks, leading to partial information loss and limited representation capability. 2) Previous methods focus on the local context of a sign pose sequence, without incorporating the guidance of the global meaning of lexical signs. To this end, we propose a Motion-Aware masked autoencoder with Semantic Alignment (MASA) that integrates rich motion cues and global semantic information in a self-supervised learning paradigm for SLR. Our framework contains two crucial components, i.e., a motion-aware masked autoencoder (MA) and a momentum semantic alignment module (SA). Specifically, in MA, we introduce an autoencoder architecture with a motion-aware masked strategy to reconstruct motion residuals of masked frames, thereby explicitly exploring dynamic motion cues among sign pose sequences. Moreover, in SA, we embed our framework with global semantic awareness by aligning the embeddings of different augmented samples from the input sequence in the shared latent space. In this way, our framework can simultaneously learn local motion cues and global semantic features for comprehensive sign language representation. Furthermore, we conduct extensive experiments to validate the effectiveness of our method, achieving new state-of-the-art performance on four public benchmarks.