在文字级手语数据集上对视频视觉转换器进行比较分析
Jubayer Ahmed Bhuiyan Shawon1, Md Kamrul Hasan1, Hasan Mahmud1
1Systems and Software Lab (SSL), Department of CSE, Islamic University of Technology (IUT), OIC, Board Bazar, Gazipur, Bangladesh.
PloS one
|February 5, 2026
概括
这项研究为孟加拉手语识别 (BdSLR) 微调了先进的视频转换器模型. 视频MAE实现了高准确度,证明了听力障碍者可访问的沟通工具的潜力.
科学领域:
- 计算机视觉和人工智能的人工智能
- 人与计算机的交互
- 可访问性技术 技术可访问性
背景情况:
- 标语识别 (SLR) 对于改善听力障碍者社区的可访问性至关重要.
- 孟加拉手语 (BdSL) 是孟加拉国许多人的主要沟通方式.
- 现有的SLR方法需要进一步开发,用于像BdSL这样的各种手语.
研究的目的:
- 微调最先进的视频变压器架构 (VideoMAE,ViViT,TimeSformer) 以进行BdSL识别.
- 在小型 (BdSLW60) 和大型 (BdSLW401) BdSL数据集上评估模型性能.
- 将BdSL的认可与已建立的公共数据集 (LSA64,WLASL) 进行比较.
主要方法:
- 将视频标准化为30 FPS,为BdSLW60数据集创建9,307个用户试用剪辑.
- 应用数据增强技术 (随机裁剪,翻转,缩放) 以提高可靠性.
- 使用10倍分层交叉验证和对持有数据的签名者独立评估.
主要成果:
- 视频变压器模型显著优于BdSLR的传统机器和深度学习方法.
- 视频MAE实现了最高的准确性:在BdSLW60上达到96.9%,在BdSLW401上达到81.04%.
- 性能受到数据集大小,签名者外观,率和模型架构的影响.
结论:
- 微调的视频变压器模型显示出可扩展和准确的孟加拉手语识别的巨大潜力.
- 这些发现为开发更有效的基于BdSL的沟通工具铺平了道路.
- 进一步的研究可以通过考虑影响识别性能的因素来优化模型.
相关概念视频
Vision
60.1K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
60.1K
Comparing the Survival Analysis of Two or More Groups
605
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
605
Language
918
Language is a unique communication system that uses words and systematic rules to organize and transmit information. Unlike other forms of communication, which may involve postures, movements, odors, or vocalizations, language relies on symbols and grammar. This makes human communication distinct from that of other species, who also communicate but do not use language in the same way humans do.
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
918
Sign Convention
3.5K
When analyzing a beam subjected to various loads, it is crucial to understand the internal forces and moments generated within the structure. These internal forces can be broadly classified into normal forces, shear forces, and bending moments. To determine these forces and moments, we use the method of sections and apply a specific sign convention based on their direction and the side of the section being analyzed.
The normal force acts perpendicular to the beam's cross-section and can...
The normal force acts perpendicular to the beam's cross-section and can...
3.5K
Signs of Puberty
1.5K
Puberty is a critical phase, typically beginning between the ages of 8 and 13 in girls and 9 and 14 in boys, though timing can vary based on genetics, environmental factors, and overall health. This period is characterized by the development of secondary sexual characteristics and the attainment of reproductive potential. Endocrine changes underpin puberty, with hormonal surges of Luteinizing Hormone (LH) and Follicle-Stimulating Hormone (FSH) instigated by Gonadotropin-Releasing Hormone (GnRH)...
1.5K
Introduction to the Sign Test
1.3K
The sign test is an important tool in nonparametric statistics, offering a straightforward yet effective method for analyzing matched pairs, nominal data, or hypotheses concerning the median of a population. It transforms data points into positive or negative signs, avoiding the need for assumptions about data distribution and instead focusing on the direction of change. It is particularly valuable when data does not conform to the normal distribution requirements of many parametric tests. For...
1.3K


