Astounding results from Transformer models on natural language tasks have intrigued the
vision community to study their application to computer vision problems. Among their salient …

Human Action Recognition (HAR) aims to understand human behavior and assign a label to
each action. It has a wide range of applications, and therefore has been attracting increasing …

The" Roaring 20s" of visual recognition began with the introduction of Vision Transformers
(ViTs), which quickly superseded ConvNets as the state-of-the-art image classification …

Driven by improved architectures and better representation learning frameworks, the field of
visual recognition has enjoyed rapid modernization and performance boost in the early …

Pre-training video transformers on extra large-scale datasets is generally required to
achieve premier performance on relatively small datasets. In this paper, we show that video …

We explore the plain, non-hierarchical Vision Transformer (ViT) as a backbone network for
object detection. This design enables the original ViT architecture to be fine-tuned for object …

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure
Transformer architectures have attained top accuracy on the major video recognition …

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

Transformer, first applied to the field of natural language processing, is a type of deep neural
network mainly based on the self-attention mechanism. Thanks to its strong representation …

Abstract We present CSWin Transformer, an efficient and effective Transformer-based
backbone for general-purpose vision tasks. A challenging issue in Transformer design is …