Abstract: In recent years, owing to the advancement of intelligent devices, a substantial volume of videos are provided to machines for analysis instead of humans. To improve the performance of video compression for machine vision analysis tasks, a video coding for machines (VCM) standard working group was established to promote standardization procedures. In this paper, we present recent advances of video coding for machine standards, and give a comprehensive introduction about the use cases, requirements, evaluation framework and corresponding metrics of the VCM standard. Then we present the existing methods, introducing the existing proposals by category and the research progress of the latest VCM conference. Finally, we give conclusions.
Keywords: video coding for machines; VCM; video compression