OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Yiheng, Liu, Sheng, Feng, Yuan, Xu, Min, Jin, Zhelun, Yang, Xuhua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912269865058304
author Yu, Yiheng
Liu, Sheng
Feng, Yuan
Xu, Min
Jin, Zhelun
Yang, Xuhua
author_facet Yu, Yiheng
Liu, Sheng
Feng, Yuan
Xu, Min
Jin, Zhelun
Yang, Xuhua
contents The primary challenge in continuous sign language recognition (CSLR) mainly stems from the presence of multi-orientational and long-term motions. However, current research overlooks these crucial aspects, significantly impacting accuracy. To tackle these issues, we propose a novel CSLR framework: Orientation-aware Long-term Motion Decoupling (OLMD), which efficiently aggregates long-term motions and decouples multi-orientational signals into easily interpretable components. Specifically, our innovative Long-term Motion Aggregation (LMA) module filters out static redundancy while adaptively capturing abundant features of long-term motions. We further enhance orientation awareness by decoupling complex movements into horizontal and vertical components, allowing for motion purification in both orientations. Additionally, two coupling mechanisms are proposed: stage and cross-stage coupling, which together enrich multi-scale features and improve the generalization capabilities of the model. Experimentally, OLMD shows SOTA performance on three large-scale datasets: PHOENIX14, PHOENIX14-T, and CSL-Daily. Notably, we improved the word error rate (WER) on PHOENIX14 by an absolute 1.6% compared to the previous SOTA
format Preprint
id arxiv_https___arxiv_org_abs_2503_08205
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition
Yu, Yiheng
Liu, Sheng
Feng, Yuan
Xu, Min
Jin, Zhelun
Yang, Xuhua
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
The primary challenge in continuous sign language recognition (CSLR) mainly stems from the presence of multi-orientational and long-term motions. However, current research overlooks these crucial aspects, significantly impacting accuracy. To tackle these issues, we propose a novel CSLR framework: Orientation-aware Long-term Motion Decoupling (OLMD), which efficiently aggregates long-term motions and decouples multi-orientational signals into easily interpretable components. Specifically, our innovative Long-term Motion Aggregation (LMA) module filters out static redundancy while adaptively capturing abundant features of long-term motions. We further enhance orientation awareness by decoupling complex movements into horizontal and vertical components, allowing for motion purification in both orientations. Additionally, two coupling mechanisms are proposed: stage and cross-stage coupling, which together enrich multi-scale features and improve the generalization capabilities of the model. Experimentally, OLMD shows SOTA performance on three large-scale datasets: PHOENIX14, PHOENIX14-T, and CSL-Daily. Notably, we improved the word error rate (WER) on PHOENIX14 by an absolute 1.6% compared to the previous SOTA
title OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2503.08205