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 …

Abstract Human Action Recognition (HAR) involves human activity monitoring task in
different areas of medical, education, entertainment, visual surveillance, video retrieval, as …

While today's video recognition systems parse snapshots or short clips accurately, they
cannot connect the dots and reason across a longer range of time yet. Most existing video …

Temporal modeling still remains challenging for action recognition in videos. To mitigate this
issue, this paper presents a new video architecture, termed as Temporal Difference Network …

Temporal action proposal generation is an challenging and promising task which aims to
locate temporal regions in real-world videos where action or event may occur. Current …

Large-scale labeled data are generally required to train deep neural networks in order to
obtain better performance in visual feature learning from images or videos for computer …

Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling
such visual tempos of different actions facilitates their recognition. Previous works often …

Vision-based sign language recognition aims at helping the hearing-impaired people to
communicate with others. However, most existing sign language datasets are limited to a …

Video self-supervised learning is a challenging task, which requires significant expressive
power from the model to leverage rich spatial-temporal knowledge and generate effective …

With the fast development of various positioning techniques such as Global Position System
(GPS), mobile devices and remote sensing, spatio-temporal data has become increasingly …