CAR-DCGAN: A Deep Convolutional Generative Adversarial Network for Compression Artifact Removal in Video Surveillance Systems Topics: Deep Learning for Visual Understanding ; Image and Video Coding and Compression; Image Enhancement and Restoration In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: VISAPP, 455-464, 2021