Deep learning approaches to anomaly detection (AD) have recently improved the state of
the art in detection performance on complex data sets, such as large collections of images or …

The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

We present Imagen Video, a text-conditional video generation system based on a cascade
of video diffusion models. Given a text prompt, Imagen Video generates high definition …

This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to
spatiotemporal representation learning from videos. We randomly mask out spacetime …

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It
offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household …

Abstract From CNN, RNN, to ViT, we have witnessed remarkable advancements in video
prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated …

Videos show continuous events, yet most--if not all--video synthesis frameworks treat them
discretely in time. In this work, we think of videos of what they should be--time-continuous …

Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from
given low-resolution (LR) images. It is an ill-posed problem because one LR image …

Several recent work on speech synthesis have employed generative adversarial networks
(GANs) to produce raw waveforms. Although such methods improve the sampling efficiency …

Anomaly detection, aka outlier detection or novelty detection, has been a lasting yet active
research area in various research communities for several decades. There are still some …