Jackknife: A Reliable Recognizer with Few Samples and Many Modalities

Jackknife: A Reliable Recognizer with Few Samples and Many Modalities
复制标题

Jackknife:一种样本少、模态多的可靠识别器

DOI:
10.1145/3025453.3026002
复制
发表时间:
2017
期刊:
2017 CHI Conference on Human Factors in Computing Systems
影响因子:
--
通讯作者:
LaViola Jr., Joseph J.
LaViola Jr., Joseph J.
中科院分区:
--
文献类型:
--
作者:
Taranta II, Eugene M.;Samiei, Amirreza;Maghoumi, Mehran;Khaloo, Pooya;Pittman, Corey R.;LaViola Jr., Joseph J.

文献摘要

参考文献

被引文献

相似文献

尽管经过了数十年的研究,但目前还没有一种通用的动态手势快速原型识别器,可以用很少的样本进行训练,使用连续的数据,并实现高精度,也是模态不可知的。为了开始解决这个问题,我们描述了一个小套件的访问技术,我们统称为刀切手势识别器。我们的动态时间扭曲为基础的方法分割和连续的数据被设计成一个强大的,去的方法,手势识别在各种形式,只使用有限的训练样本。我们评估笔和触摸,Wii Remote,Kinect,Leap Motion和声音感应手势数据集,并使用连续数据进行测试。在所有的情况下,我们表明,我们的方法是能够实现高精度,这表明刀切是一个有能力的识别器和良好的首选许多努力。
Despite decades of research, there is yet no general rapid prototyping recognizer for dynamic gestures that can be trained with few samples, work with continuous data, and achieve high accuracy that is also modality-agnostic. To begin to solve this problem, we describe a small suite of accessible techniques that we collectively refer to as the Jackknife gesture recognizer. Our dynamic time warping based approach for both segmented and continuous data is designed to be a robust, go-to method for gesture recognition across a variety of modalities using only limited training samples. We evaluate pen and touch, Wii Remote, Kinect, Leap Motion, and sound-sensed gesture datasets as well as conduct tests with continuous data. Across all scenarios we show that our approach is able to achieve high accuracy, suggesting that Jackknife is a capable recognizer and good first choice for many endeavors.
采样率对基于模板的手势识别器性能的影响
DOI: --
发表时间: 2011
期刊: International Conference on Multimodal Interaction
影响因子: --
作者:
Radu
通讯作者: Radu
DOI: --
发表时间: 2013
期刊: --
影响因子: --
作者:
Cliff R. Chan;Seyed Sepehr Mirfakhraei
通讯作者: Cliff R. Chan;Seyed Sepehr Mirfakhraei
Penny Pincher 简化且准确的手势识别
DOI: --
发表时间: 2016
期刊: Computers & graphics
影响因子: --
作者:
E. Taranta;Andrés N. Vargas;J. Laviola
通讯作者: J. Laviola
基于HMM的活动识别系统拒绝无意义的活动
DOI: --
发表时间: 2010
影响因子: 4.7
作者:
Xiaohui Liu;C. Chua
通讯作者: C. Chua
准确的实时窗口时间扭曲
DOI: --
发表时间: 2010
期刊: International Society for Music Information Retrieval Conference
影响因子: --
作者:
R. Macrae;S. Dixon
通讯作者: S. Dixon