Learning Temporal Regularity in Video Sequences

Citations Over TimeTop 1% of 2016 papers

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.

Related Papers

• → Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy data(2017)271 cited
• → Improved autoencoder for unsupervised anomaly detection(2021)119 cited
• → Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencoder(2023)1 cited
• → Generative Model for Person Re-Identification: A Review(2020)
• → TC-VAE: Uncovering Out-of-Distribution Data Generative Factors(2023)