Abstract: Modeling complex correlations on multiview data is still challenging, especially for high-dimensional features with possible noise. To address this issue, we propose a novel unsupervised ...

Abstract: A video autoencoder is proposed for learning disentangled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, ...

MST-VAE is an unsupervised learning approach for anomaly detection in multivariate time series. Inspired by InterFusion paper, we propose a simple yet effective multi-scale convolution kernels applied ...