arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.08191cs.CVcs.LG
收藏

端到端学习是否足以用于健身活动识别?

Is end-to-end learning enough for fitness activity recognition?

Twenty Billion Neurons GmbH(二百亿神经元有限公司);Qualcomm AI Research(高通人工智能研究院)

Antoine Mercier, Guillaume Berger, Sunny Panchal, Florian Letsch, Cornelius Boehm, Nahua Kang, Ingo Bax, Roland Memisevic

AI总结:

本研究提出一个完全标注的健身视频数据集,证明端到端学习在原始像素上能与基于姿态估计的最先进动作识别流程竞争,并支持实时重复计数等细粒度任务。

摘要:

端到端学习已在许多计算机视觉任务中占据主导地位,尤其是与静态图像相关的任务,通过任务特定的优化实现了非常强的性能。然而,以人为中心的动作识别仍然主要由手工设计的流程主导,只有个别组件被神经网络替代,这些网络通常处理单个帧。为了研究此类流程的相关性,我们提出了一个新的、完全标注的健身活动视频数据集。该领域的任何识别能力几乎完全取决于人体姿态及其时间动态,因此基于姿态的解决方案应该表现良好。我们表明,利用这些标注数据,基于原始像素的端到端学习可以与基于姿态估计的最先进动作识别流程竞争。我们还表明,端到端学习可以支持时间上细粒度的任务,如实时重复计数。

英文摘要:

End-to-end learning has taken hold of many computer vision tasks, in particular, related to still images, with task-specific optimization yielding very strong performance. Nevertheless, human-centric action recognition is still largely dominated by hand-crafted pipelines, and only individual components are replaced by neural networks that typically operate on individual frames. As a testbed to study the relevance of such pipelines, we present a new fully annotated video dataset of fitness activities. Any recognition capabilities in this domain are almost exclusively a function of human poses and their temporal dynamics, so pose-based solutions should perform well. We show that, with this labelled data, end-to-end learning on raw pixels can compete with state-of-the-art action recognition pipelines based on pose estimation. We also show that end-to-end learning can support temporally fine-grained tasks such as real-time repetition counting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑