Video prediction models based on convolutional networks, recurrent networks, and their
combinations often result in blurry predictions. We identify an important contributing factor for …

Generating human videos based on single images entails the challenging simultaneous
generation of realistic and visual appealing appearance and motion. In this context, we …

We propose a sequential variational autoencoder to learn disentangled representations of
sequential data (eg, videos and audios) under self-supervision. Specifically, we exploit the …

Existing implicit neural representation (INR) methods do not fully exploit spatiotemporal
redundancies in videos. Index-based INRs ignore the content-specific spatial features and …

Deep Convolutional Neural Networks (CNNs) are powerful models that have achieved
excellent performance on difficult computer vision tasks. Although CNNs perform well …

Existing video prediction methods mainly rely on observing multiple historical frames or
focus on predicting the next one-frame. In this work, we study the problem of generating …

Generative models that can model and predict sequences of future events can, in principle,
learn to capture complex real-world phenomena, such as physical interactions. In particular …

Classical semi-supervised video anomaly detection assumes that only normal data are
available in the training set because of the rare and unbounded nature of anomalies. It is …

Unsupervised pre-training methods utilizing large and diverse datasets have achieved
tremendous success across a range of domains. Recent work has investigated such …

Much of recent research has been devoted to video prediction and generation, yet most of
the previous works have demonstrated only limited success in generating videos on short …