# Video coding for machines _by Fabien Racapé - 2023.10.26_ ###### tags: `VAADER` `Seminar` ![](https://hackmd.io/_uploads/rJSoCaq1T.jpg) ## Abstract With the rise of machine learning technologies for vision applications in domains like intelligent transportations, smart cities, and intelligent content management, the share of videos and images consumed by machines is rapidly increasing. These vision tasks demand heavy computations and sometimes need to be performed at the network or on cloud systems, rather than on the limited devices capturing the source content. The overhead of transmitting the video content when assessing the need of offloading these computations. Like for traditional video transmission pipelines, the amount of source data requires performant compression to fit physical bandwidths and storage capacities. Currently deployed methods rely on existing image and video codecs which were designed for human consumption. However, machine vision algorithms are not sensitive to the same artifacts when applying lossy compression. This presentation reviews current research and standardization efforts in this domain.