In this paper we tackle the problem of self-supervised video alignment and activity progress
prediction using in-the-wild videos. Our proposed self-supervised representation learning …

Three-dimensional convolutional neural networks (3D-CNNs) and full connection long short-
term memory networks (FC-LSTMs) have been demonstrated as a kind of powerful non …

The collection and annotation of large-scale video data pose significant challenges,
prompting the exploration of few-shot models to recognize unseen actions with limited …

3-D action recognition become a fast-pacing field in recent years. However, traditional
approaches have limitations. They either focus on modeling overly detailed yet redundant …

Recently, there have been efforts to improve the performance in sign language recognition
by designing self-supervised learning methods. However, these methods capture limited …

As a hot topic in the field of computer vision, video action recognition has great application
potential, such as intelligent monitoring, data recommendation and virtual reality. However …

Video self-supervised learning (VideoSSL) offers significant potential for reducing
annotation costs and enhancing a wide range of downstream tasks in video understanding …

Group activity recognition (GAR) is a significant and challenging task that has attracted
considerable attention in video analysis. However, most of the existing models directly …

The collection and annotation of large-scale video data pose significant challenges,
prompting the exploration of few-shot learning models capable of recognizing unseen …