It is a challenging task to learn discriminative representation from images and videos, due to
large local redundancy and complex global dependency in these visual data. Convolution …

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 …

Abstract We propose Anticipative Video Transformer (AVT), an end-to-end attention-based
video modeling architecture that attends to the previously observed video in order to …

Human action recognition is an important field in computer vision that has attracted
remarkable attention from researchers. This survey aims to provide a comprehensive …

Abstract We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm
for online action detection, which employs a long-and short-term memory mechanism to …

Transformer architectures have brought about fundamental changes to computational
linguistic field, which had been dominated by recurrent neural networks for many years. Its …

Contrastive learning has revolutionized the self-supervised image representation learning
field and recently been adapted to the video domain. One of the greatest advantages of …

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for
training deep neural networks on videos. It is based on the finding that gradients from …

Deep learning has become a popular tool across various fields and is increasingly being
integrated into real-world applications such as autonomous driving cars and surveillance …

Spatiotemporal modeling in an unified architecture is key for video action recognition. This
paper proposes a Shrinking Temporal Attention Transformer (STAT), which efficiently builts …