专栏首页arxiv.org翻译专栏人体运动预测的多任务非自回归模型(CS)
原创

人体运动预测的多任务非自回归模型(CS)

人体运动预测是一个典型的序列到序列的问题,旨在根据给定的过去人体骨骼来预测未来的人体骨骼。因此,在探索不同的基于RNN的编码器-解码器体系结构上学术界已进行了大量的努力。然而,以先前生成的姿势为条件来生成的目标产物的模型容易带来诸如错误累积方面的问题。在本文中,我们认为这类问题主要是由于采用自回归方式引起的。因此,本文提出了一种新型非自回归模型(NAT),其具有完整的非自回归解码方案、上下文编码器和位置编码模块。具体来说,上下文编码器负责从时间和空间角度嵌入给定的姿势,帧解码器负责独立预测每个未来姿势,位置编码模块负责将位置信号注入模型以指示时间顺序。此外,我们提出了一种用于低级人体骨骼预测和高级人体动作识别的多任务训练范例,从而使预测任务的改进更加可信。在Human3.6M和CMU-Mocap的基准上评估这些方法后发现了它们比最领先的自回归方法要更佳。

原文题目:Multitask Non-Autoregressive Model for Human Motion Prediction

原文: Human motion prediction, which aims at predicting future human skeletons given the past ones, is a typical sequence-to-sequence problem. Therefore, extensive efforts have been continued on exploring different RNN-based encoder-decoder architectures. However, by generating target poses conditioned on the previously generated ones, these models are prone to bringing issues such as error accumulation problem. In this paper, we argue that such issue is mainly caused by adopting autoregressive manner. Hence, a novel Non-auToregressive Model (NAT) is proposed with a complete non-autoregressive decoding scheme, as well as a context encoder and a positional encoding module. More specifically, the context encoder embeds the given poses from temporal and spatial perspectives. The frame decoder is responsible for predicting each future pose independently. The positional encoding module injects positional signal into the model to indicate temporal order. Moreover, a multitask training paradigm is presented for both low-level human skeleton prediction and high-level human action recognition, resulting in the convincing improvement for the prediction task. Our approach is evaluated on Human3.6M and CMU-Mocap benchmarks and outperforms state-of-the-art autoregressive methods.

原文作者:Bin Li, Jian Tian, Zhongfei Zhang, Hailin Feng, Xi Li

原文地址:https://arxiv.org/abs/2007.06426

原创声明,本文系作者授权云+社区发表,未经许可,不得转载。

如有侵权,请联系 yunjia_community@tencent.com 删除。

我来说两句

0 条评论
登录 后参与评论

相关文章

  • 通过复制进行神经网络验证(CS)

    本文提出了一种基于系统识别的神经网络模型复制方法,并说明了模型复制在基本单层隐藏神经网络系统验证中的应用。文中提出的方法可解决部分仅在灰盒访问已实现的网络时,来...

    Pamela_Lin
  • IIT 坎普尔咨询集团:将机器学习和管理咨询的方法应用到社会公益中(CS)

    IIT坎普尔咨询集团(IIT Kanpur Consulting Group)是印度的先驱研究机构之一,他们致力于研究机器学习和策略咨询在社会公益中的应用。该集...

    Pamela_Lin
  • 社会选择优化(CS)

    社会选择是从个人意见、偏好、利益或福利出发的集体决定社会福利的理论。在某种程度上,社会福利计算领域的研究近来才在人工智能社区中兴起并获得关注的。传统文献中对单峰...

    Pamela_Lin
  • [Repost]The care and maintenance of your adviser

    Published online  26 January 2011This article was originally published in the jo...

    昊楠Hacking
  • Python Tips, Tricks, and Hacks

    一、快速技巧 1.1、4 种引号 '  '''  "  """  print """I wish that I'd never heard him say...

    用户1177713
  • PVT, RC Variation & OCV

    PVT is abbreviation for Process, Voltage and Temperature. In order to make our c...

    白山头
  • 基于tensorflow 1.0的图像叙事功能测试(model/im2txt)

    作为多模态数据处理的经典,图像自动打标签(图像叙事功能)一直是一项非常前沿的技术,涉及到机器视觉,自然语言处理等模块。 幸运的是,谷歌基于tensorflow将...

    sparkexpert
  • Capturing Documents Service System Use Cases

    程序你好
  • Springsecurity之Authentication

       Authentication是个接口,如下图1所示,此图来自于《Pro Spring Security》,建议读者阅读原书:

    克虏伯
  • 【CodeForces 621C】Wet Shark and Flowers

    There are n sharks who grow flowers for Wet Shark. They are all sitting around t...

    饶文津

扫码关注云+社区

领取腾讯云代金券