It all began with a deceptively casual pitch from creators Seth Rogen and Evan Goldberg: "Yeah, we want to shoot the show with one camera, with one lens, and we want to do everything in one shot," ...

Abstract: Learning high-level image representations using object proposals has achieved remarkable success in multi-label image recognition. However, most object proposals provide merely coarse ...

In this work, we propose SS-StyleGAN, a self-supervised approach for image annotation and classification suitable for extremely small annotated datasets. This novel framework adds self-supervision to ...