Abstract Human Action Recognition (HAR) is a challenging task used in sports such as
volleyball, basketball, soccer, and tennis to detect players and recognize their actions and …

Action recognition is a major branch of computer vision research. As a widely used
technology, action recognition has been applied to human–computer interaction, intelligent …

Exploring large-scale pretrained foundation models is of significant interest in computer
vision because these models can be quickly transferred to many downstream tasks. This …

Building models that can be rapidly adapted to novel tasks using only a handful of annotated
examples is an open challenge for multimodal machine learning research. We introduce …

Large pretrained (eg," foundation") models exhibit distinct capabilities depending on the
domain of data they are trained on. While these domains are generic, they may only barely …

A central goal of machine learning is the development of systems that can solve many
problems in as many data domains as possible. Current architectures, however, cannot be …

The canonical approach to video-and-language learning (eg, video question answering)
dictates a neural model to learn from offline-extracted dense video features from vision …

Denoising diffusion probabilistic models are a promising new class of generative models
that mark a milestone in high-quality image generation. This paper showcases their ability to …

What makes a video task uniquely suited for videos, beyond what can be understood from a
single image? Building on recent progress in self-supervised image-language models, we …

Recently, open-domain text-to-video (T2V) generation models have made remarkable
progress. However, the promising results are mainly shown by the qualitative cases of …