Spatio-temporal features extraction that measure the stabilty. The proposed method is based on a compression algorithm named Run Length Encoding. The workflow of the method is presented bellow.

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

Trying to detect generic from several episodes of series to delete them automatically, using perceptual hash...

Get a simple HTTP (REST) API with only this simple decorator : @bonapity !

Reimplementing cool papers in PyTorch...