基于深度学习的视频行为识别技术综述

行为识别（action recognition，AR）是计算机视觉领域的研究热点，在安防监控、自动驾驶、生产安全等领域具有广泛的应用前景。首先，对行为识别的内涵与外延进行了剖析，提出了面临的技术挑战问题。其次，从时间特征提取、高效率优化和长期特征捕获三个角度分析比较了行为识别的工作原理。对近十年43种基准AR方法在UCF101、HMDB51、Something-Something和Kinetics400数据集上的性能表征进行比对，有助于针对不同应用场景选择适合的AR模型。最后指明了行为识别领域的未来发展方向，研究成果可为视频特征提取和视觉内容理解提供理论参考和技术支撑。

Review of video action recognition technology based on deep learning

Action recognition(AR) is a hot research area in computer vision field, and has an extensive application prospect for security monitoring, autopilot, production safety etc. Firstly, this paper analyzed the connotation and denotation of AR and put forward the technical challenges. Secondly, it analyzed and compared the working principles of AR from three aspects: time feature extraction, efficient optimization and long-term feature capture. Thirdly, in order to select suitable AR models for different application scenarios, this paper compared the performance characterization of 43 benchmark AR methods in recent ten years based on UCF101, HMDB51, Something-Something and Kinetics400 datasets. Finally, this paper pointed out the future development direction of AR field. The research results can provide theoretical reference and technical support for video feature extraction and visual content understanding.