Learning Temporal Regularity in Video Sequences

Abstract

Perceiving meaningful activities in a long video sequence is a challenging problem due to ambiguous definition of 'meaningfulness' as well as clutters in the scene. We approach this problem by learning a generative model for regular motion patterns (termed as regularity) using multiple sources with very limited supervision. Specifically, we propose two methods that are built upon the autoencoders for their ability to work with little to no supervision. We first leverage the conventional handcrafted spatio-temporal local features and learn a fully connected autoencoder on them. Second, we build a fully convolutional feed-forward autoencoder to learn both the local features and the classifiers as an end-to-end learning framework. Our model can capture the regularities from multiple datasets. We evaluate our methods in both qualitative and quantitative ways - showing the learned regularity of videos in various aspects and demonstrating competitive performance on anomaly detection datasets as an application.

DOI: 10.1109/CVPR.2016.86

Extracted Key Phrases

13 Figures and Tables

0204020162017
Citations per Year

Citation Velocity: 11

Averaging 11 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@article{Hasan2016LearningTR, title={Learning Temporal Regularity in Video Sequences}, author={Mahmudul Hasan and Jonghyun Choi and Jan Neumann and Amit K. Roy-Chowdhury and Larry S. Davis}, journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2016}, pages={733-742} }