论文标题
人类和机器的可扩展视频编码
Scalable Video Coding for Humans and Machines
论文作者
论文摘要
视频内容不仅是人类观看的，而且越来越多地被机器观看。例如，机器学习模型分析监视视频，以进行安全性和流量监控，通过YouTube视频搜索不适当的内容，等等。在本文中，我们提出了一个可扩展的视频编码框架，该框架通过其基础层bitstream和人类视觉通过其增强层的bitstream来支持机器视觉（特别是对象检测）。所提出的框架包括传统和深神经网络（DNN）的视频编码的组件。结果表明，与最先进的视频编解码器相比，在对象检测中，提议的框架可节省13-19％的位，同时在人类视觉任务上保持竞争力。
Video content is watched not only by humans, but increasingly also by machines. For example, machine learning models analyze surveillance video for security and traffic monitoring, search through YouTube videos for inappropriate content, and so on. In this paper, we propose a scalable video coding framework that supports machine vision (specifically, object detection) through its base layer bitstream and human vision via its enhancement layer bitstream. The proposed framework includes components from both conventional and Deep Neural Network (DNN)-based video coding. The results show that on object detection, the proposed framework achieves 13-19% bit savings compared to state-of-the-art video codecs, while remaining competitive in terms of MS-SSIM on the human vision task.
