首页> 外文OA文献 >Procedural Generation of Videos to Train Deep Action Recognition Networks
【2h】

Procedural Generation of Videos to Train Deep Action Recognition Networks

机译:程序生成视频以训练深度行动识别   网络

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。
获取外文期刊封面目录资料

摘要

Deep learning for human action recognition in videos is making significantprogress, but is slowed down by its dependency on expensive manual labeling oflarge video collections. In this work, we investigate the generation ofsynthetic training data for action recognition, as it has recently shownpromising results for a variety of other computer vision tasks. We propose aninterpretable parametric generative model of human action videos that relies onprocedural generation and other computer graphics techniques of modern gameengines. We generate a diverse, realistic, and physically plausible dataset ofhuman action videos, called PHAV for "Procedural Human Action Videos". Itcontains a total of 39,982 videos, with more than 1,000 examples for eachaction of 35 categories. Our approach is not limited to existing motion capturesequences, and we procedurally define 14 synthetic actions. We introduce a deepmulti-task representation learning architecture to mix synthetic and realvideos, even if the action categories differ. Our experiments on the UCF101 andHMDB51 benchmarks suggest that combining our large set of synthetic videos withsmall real-world datasets can boost recognition performance, significantlyoutperforming fine-tuning state-of-the-art unsupervised generative models ofvideos.
机译:用于视频中人类动作识别的深度学习取得了长足的进步,但由于其依赖于昂贵的大型视频收藏的手动标签而减慢了学习速度。在这项工作中,我们调查了用于动作识别的综合训练数据的生成,因为它最近显示了对其他各种计算机视觉任务的有希望的结果。我们提出了一种人类动作视频的可解释参数生成模型,该模型依赖于过程生成和现代游戏引擎的其他计算机图形技术。我们生成了人类动作视频的多样化,现实且在物理上合理的数据集,称为“程序性人类动作视频” PHAV。它总共包含39,982个视频,其中35个类别的每个动作都包含1,000多个示例。我们的方法不仅限于现有的动作捕捉序列,而且我们在程序上定义了14个合成动作。我们引入了一种深多任务表示学习架构,即使动作类别不同,也可以将合成视频和真实视频混合使用。我们在UCF101和HMDB51基准上进行的实验表明,将我们的大量合成视频与少量真实世界的数据集结合在一起,可以提高识别性能,大大优于微调的最新无监督生成视频模型。

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