首页> 外文OA文献 >SubUNets: End-to-end Hand Shape and Continuous Sign Language Recognition
【2h】

SubUNets: End-to-end Hand Shape and Continuous Sign Language Recognition

机译:子类:端到端手形和连续手语识别

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

We propose a novel deep learning approach to solveudsimultaneous alignment and recognition problems (referredudto as “Sequence-to-sequence” learning). We decompose theudproblem into a series of specialised expert systems referredudto as SubUNets. The spatio-temporal relationships betweenudthese SubUNets are then modelled to solve the task, whileudremaining trainable end-to-end.udThe approach mimics human learning and educationaludtechniques, and has a number of significant advantages. SubUNetsudallow us to inject domain-specific expert knowledgeudinto the system regarding suitable intermediate representations.udThey also allow us to implicitly perform transferudlearning between different interrelated tasks, which also allowsudus to exploit a wider range of more varied data sources.udIn our experiments we demonstrate that each of these propertiesudserves to significantly improve the performance of theudoverarching recognition system, by better constraining theudlearning problem.udThe proposed techniques are demonstrated in the challenginguddomain of sign language recognition. We demonstrateudstate-of-the-art performance on hand-shape recognition (outperformingudprevious techniques by more than 30%). Furthermore,udwe are able to obtain comparable sign recognitionudrates to previous research, without the need for an alignmentudstep to segment out the signs for recognition.
机译:我们提出了一种新颖的深度学习方法来解决同时对齐和识别问题(被称为“序列到序列”学习)。我们将“问题”分解为一系列称为“子UNets”的专业专家系统。然后, subSubets之间的时空关系被建模以解决任务,同时 u n保持可训练的端到端。 ud此方法模仿了人类的学习和教育 udtechniques,具有许多重要的优点。 SubUNets 允许我们将有关特定中间表示的领域特定专家知识 udin注入系统。 ud它们还允许我们隐式执行不同相互关联任务之间的转移 udlearning,这也允许 udus利用范围更广的各种数据 ud在我们的实验中我们证明,通过更好地约束 udlearning问题,这些属性中的每一个都有助于显着提高 udoverarching识别系统的性能。 ud提议的技术在手语识别的具有挑战性的 uddomain中得到了证明。我们展示了手形状识别方面的最先进的性能(优于上乘的技术超过30%)。此外, udwe能够获得与以前的研究相当的符号识别 udrate,而无需对齐 udstep来分割识别符号。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号