Attentioned Convolutional LSTM Inpaintingv Network for Anomaly Detection in Videos

Image credit: Unsplash


We propose a semi supervised model for detecting anomalies in videos inspiredby the Video Pixel Network [van den Oord et al., 2016]. Our model extends the Convolutional LSTM video encoder part of the VPN with a novel convolutional based attention mechanism. We also modify the Pixel CNN decoder part of the VPN to a frame inpainting task where a partially masked version of the frame to predict is given as input. Our model is shown to be effective in detecting anomalies in videos. This approachcould be a component in applications requiring visual common sense.

NIPS 2018 Workshop on Systems for ML
Ravid Shwartz-Ziv
Ravid Shwartz-Ziv
Assistant Professor and Faculty Fellow