0


从活动到语言:学习认识运动的意义

From activity to language: learning to recognise the meaning of motion
课程网址: http://videolectures.net/gesturerecognition2011_bowden_activity/  
主讲教师: Richard Bowden
开课单位: 萨里大学
开课时间: 2011-08-24
课程语种: 英语
中文简介:
无论任务是识别个体的原子行为或其隐含的活动、手语识别的连续多通道性质或嘴唇上的单词外观,所有方法都可以在最基本的层次上分类为时空模式的学习和识别。问题的复杂性在某种程度上决定了所使用的方法,例如,对于简单的手势和动作,整体描述符可以很好地工作,但不太适合字幕和符号的复杂性。然而,在所有情况下,标签的不准确和维度的诅咒导致我们探索新的学习方法,可以在一个弱监督的环境中操作。这篇演讲将集中在3个领域,涵盖从全身到身体各部位的时空识别,包括活动和手势、手势和表情,最后是唇读。在每一种情况下,都将呈现出既适合问题固有的可变性又适合问题复杂性的特征和学习方法。**//免责声明:/由于口译员不是相关领域的专家,在没有全面准备的情况下进行同声翻译,因此口译可能存在错误或遗漏。**
课程简介: Whether the task is recognising an atomic action of an individual or their implied activity, the continuous multichannel nature of sign language recognition or the appearance of words on the lips, all approaches can be categorised at the most basic level as the learning and recognition of spatio-temporal patterns. The complexity of the problem to some extend dictates the approaches used e.g. for simple gestures and actions, holistic descriptors can work well but are less suitable for the subtitles and complexities of sign. However, in all cases, inaccuracies in labelling and the curse of dimensionality lead us to explore new learning approaches that can operate in a weakly supervised setting. This talk will concentrate on 3 areas covering the spectrum of spatiotemporal recognition from whole body through to subtle motions of body parts covering activity and gesture, sign and expression and finally lip reading. In each case, feature and learning approaches will be presented which are suited to both the inherent variability as well as the complexity of the problem. **//Disclaimer:// There may be mistakes or omissions in the interpretation as the interpreters are not experts in the field of interest and performed a simultaneous translation without comprehensive preparation.**
关 键 词: 活性原子动作; 变异性; 同声翻译
课程来源: 视频讲座网
最后编审: 2019-12-08:lxf
阅读次数: 39