paper-with-me

홈 › Papers

ADAT: Time-Series-Aware Adaptive Transformer Architecture for Sign Language Translation

2025-04-16 · Nada Shahin, Leila Ismail

Current sign language machine translation systems rely on recognizing hand movements, facial expressions and body postures, and natural language processing, to convert signs into text. Recent approaches use Transformer architectures to model long-range dependencies via positional encoding. However, they lack accuracy in recognizing fine-grained, short-range temporal dependencies between gestures captured at high frame rates. Moreover, their high computational complexity leads to inefficient training. To mitigate these issues, we propose an Adaptive Transformer (ADAT), which incorporates components for enhanced feature extraction and adaptive feature weighting through a gating mechanism to emphasize contextually relevant features while reducing training overhead and maintaining translation accuracy. To evaluate ADAT, we introduce MedASL, the first public medical American Sign Language dataset. In sign-to-gloss-to-text experiments, ADAT outperforms the encoder-decoder transformer, improving BLEU-4 accuracy by 0.1% while reducing training time by 14.33% on PHOENIX14T and 3.24% on MedASL. In sign-to-text experiments, it improves accuracy by 8.7% and reduces training time by 2.8% on PHOENIX14T and achieves 4.7% higher accuracy and 7.17% faster training on MedASL. Compared to encoder-only and decoder-only baselines in sign-to-text, ADAT is at least 6.8% more accurate despite being up to 12.1% slower due to its dual-stream structure.

📄 PDF Abstract BibTeX arXiv:2504.11942

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationSign Language TranslationTime SeriesTranslation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
American 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Metadata Matters for Time Series: Informative Forecasting with Transformers

2024-10-04 · Jiaxiang Dong, Haixu Wu, Yuxuan Wang, Li Zhang 외

Time series forecasting is prevalent in extensive real-world applications, such as financial analysis and energy planning. Previous studies primarily focus on time series modality, endeavoring to capture the intricate va…

Financial AnalysisTime SeriesTime Series Forecasting

SST: Multi-Scale Hybrid Mamba-Transformer Experts for Long-Short Range Time Series Forecasting

2024-04-23 · Xiongxiao Xu, Canyu Chen, Yueqing Liang, Baixiang Huang 외

Despite significant progress in time series forecasting, existing forecasters often overlook the heterogeneity between long-range and short-range time series, leading to performance degradation in practical applications.…

MambaTime SeriesTime Series ForecastingWeather Forecasting

Towards a Unified Generative Model for Scarce Time Series with Domain Experts

2026-06-13 · Zihao Yao, Qi Zheng, Jiankai Zuo, Yaying Zhang arxiv

Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios. Despite recent progress, most existing methods are trained under the assumption of abundant training data, …

Degradation-Aware Self-Attention Based Transformer for Blind Image Super-Resolution

2023-10-06 · Qingguo Liu, Pan Gao, Kang Han, Ningzhong Liu 외

Compared to CNN-based methods, Transformer-based methods achieve impressive image restoration outcomes due to their abilities to model remote dependencies. However, how to apply Transformer-based methods to the field of …

Blind Super-ResolutionContrastive LearningImage RestorationImage Super-Resolution+1

Learning Frequency-Aware Dynamic Transformers for All-In-One Image Restoration

2024-06-30 · Zenglin Shi, Tong Su, Pei Liu, Yunpeng Wu 외

This work aims to tackle the all-in-one image restoration task, which seeks to handle multiple types of degradation with a single model. The primary challenge is to extract degradation representations from the input degr…

AllDeblurringDenoisingImage Restoration+1