Saved in:
Bibliographic Details
Main Authors: Liu, Liangjin, Zheng, Haoyang, Zhu, Zhengzhong, Zhou, Pei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.08661
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Isolated Sign Language Recognition (ISLR) is challenged by gestures that are morphologically similar yet semantically distinct, a problem rooted in the complex interplay between hand shape and motion trajectory. Existing methods, often relying on a single reference frame, struggle to resolve this geometric ambiguity. This paper introduces Dual-SignLanguageNet (DSLNet), a dual-reference, dual-stream architecture that decouples and models gesture morphology and trajectory in separate, complementary coordinate systems. The architecture processes these streams through specialized networks: a topology-aware graph convolution models the view-invariant shape from a wrist-centric frame, while a Finsler geometry-based encoder captures the context-aware trajectory from a facial-centric frame. These features are then integrated via a geometry-driven optimal transport fusion mechanism. DSLNet sets a new state-of-the-art, achieving 93.70%, 89.97%, and 99.79% accuracy on the challenging WLASL-100, WLASL-300, and LSA64 datasets, respectively, with significantly fewer parameters than competing models.