Semantic segmentation aims at classifying image pixels according to given categories. Deep learning approaches have proven to be very effective for this task. However, extensions to video content are more challenging, typically requiring more complex architectures, given the temporal constraints and the additional data that video introduces. At the same time, video application tend to necessitate real-time, or at least interactive performances: self-driving cars, industrial applications, or live broadcasting to name a few, imposing even stronger constraints to video methods. In recent years, considerable efforts have been made in addressing these somewhat opposing challenges. In this survey, we explore the solutions proposed to improve the quality and accuracy of video segmentation, as well as the different techniques that can be employed to improve the efficiency of such approaches, in particular in terms of inference time. Finally, we briefly describe the datasets related to the semantic video segmentation task and the challenges involved.

中文翻译：

---

快速密集视频分割技术综述

语义分割旨在根据给定类别对图像像素进行分类。事实证明，深度学习方法对于这项任务非常有效。然而，考虑到时间限制和视频引入的附加数据，视频内容的扩展更具挑战性，通常需要更复杂的架构。同时，视频应用往往需要实时的，或者至少是交互式的表演：自动驾驶汽车、工业应用或直播等等，这对视频方式提出了更强的限制。近年来，人们为解决这些有些相反的挑战做出了巨大的努力。在本次调查中，我们探讨了为提高视频分割的质量和准确性而提出的解决方案，以及可用于提高此类方法效率的不同技术，特别是在推理时间方面。最后，我们简要描述了与语义视频分割任务相关的数据集以及所涉及的挑战。