appearance-features

[ECCV 2020] XingGAN for Person Image Generation

Paper Detecting anomalous events in videos by learning deep representations of appearance and motion on python, opencv and tensorflow. This paper uses the stacked denoising autoencoder for the the feature training on the appearance and motion flow features as input for different window size and using multiple SVM as a single c

A python package to estimate visual features about the aesthetic appearance of still images.