Attentioned Convolutional LSTM InpaintingNetwork for Anomaly Detection in Videos

Itamar Ben-Ari; Ravid Shwartz-Ziv

Attentioned Convolutional LSTM InpaintingNetwork for Anomaly Detection in Videos

Computer Vision and Pattern Recognition 2018-11-27 v1

Authors: Itamar Ben-Ari , Ravid Shwartz-Ziv

Abstract

We propose a semi-supervised model for detecting anomalies in videos inspiredby the Video Pixel Network [van den Oord et al., 2016]. VPN is a probabilisticgenerative model based on a deep neural network that estimates the discrete jointdistribution of raw pixels in video frames. Our model extends the Convolutional-LSTM video encoder part of the VPN with a novel convolutional based attentionmechanism. We also modify the Pixel-CNN decoder part of the VPN to a frameinpainting task where a partially masked version of the frame to predict is given asinput. The frame reconstruction error is used as an anomaly indicator. We test ourmodel on a modified version of the moving mnist dataset [Srivastava et al., 2015]. Our model is shown to be effective in detecting anomalies in videos. This approachcould be a component in applications requiring visual common sense.

Keywords

anomaly detection video inpainting convolutional lstm attention mechanism video pixel network semi-supervised model

Cite

@article{arxiv.1811.10228,
  title  = {Attentioned Convolutional LSTM InpaintingNetwork for Anomaly Detection in Videos},
  author = {Itamar Ben-Ari and Ravid Shwartz-Ziv},
  journal= {arXiv preprint arXiv:1811.10228},
  year   = {2018}
}

Attentioned Convolutional LSTM InpaintingNetwork for Anomaly Detection in Videos

Abstract

Keywords

Cite

Related papers