We present an approach to reconstruct humans and track them over time. At the core of our
approach, we propose a fully" transformerized" version of a network for human mesh …

In this work we study the benefits of using tracking and 3D poses for action recognition. To
achieve this, we take the Lagrangian view on analysing actions over a trajectory of human …

Recent studies of video action recognition can be classified into two categories: the
appearance-based methods and the pose-based methods. The appearance-based methods …

Action recognition is a hot topic in the field of computer vision. It has been widely used in
human–computer/robot interaction, abnormal behavior monitoring, and medical assistive …

We address the problem of extracting key steps from unlabeled procedural videos,
motivated by the potential of Augmented Reality (AR) headsets to revolutionize job training …

Vision-based human activity recognition (HAR) has emerged as one of the essential
research areas in video analytics. Over the last decade, numerous advanced deep learning …

Human pose analysis has garnered significant attention within both the research community
and practical applications, owing to its expanding array of uses, including gaming, video …

This paper presents a novel spatiotemporal transformer network that introduces several
original components to detect actions in untrimmed videos. First, the multi-feature selective …

Skeleton-based action recognition is a prominent research area that provides a concise
representation of human motion. However, real-world scenarios pose challenges to the …

Exercise is a prevailing topic in modern society as more people are pursuing a healthy
lifestyle. Physical activities provide significant benefits to human well-being from the inside …