Abstract
Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state. Vision-based action recognition and prediction from videos are such tasks, where action recognition is to infer human actions (present state) based upon complete action executions, and action prediction to predict human actions (future state) based upon incomplete action executions. These two tasks have become particularly prevalent topics recently because of their explosively emerging real-world applications, such as visual surveillance, autonomous driving vehicle, entertainment, and video retrieval, etc. Many attempts have been devoted in the last a few decades in order to build a robust and effective framework for action recognition and prediction. In this paper, we survey the complete state-of-the-art techniques in the action recognition and prediction. Existing models, popular algorithms, technical difficulties, popular action databases, evaluation protocols, and promising future directions are also provided with systematic discussions.
Abstract (translated)
由于计算机视觉和机器学习的快速发展，视频分析任务已经从推断当前状态转变为预测未来状态。视频中基于视觉的动作识别和预测就是这样的任务，其中动作识别是基于完整的动作执行来推断人类动作（当前状态），以及基于不完整动作执行预测人类动作（未来状态）的动作预测。这两个任务最近已成为特别流行的话题，因为它们具有爆炸性的现实世界应用，例如视频监控，自动驾驶车辆，娱乐和视频检索等等。过去几十年来，为了为行动识别和预测建立一个强大而有效的框架。在本文中，我们调查了动作识别和预测中完整的最先进技术。还提供系统讨论的现有模型，流行算法，技术难点，常用行动数据库，评估协议以及有希望的未来方向。
URL
https://arxiv.org/abs/1806.11230
