We describe the 2020 edition of the DeepMind Kinetics human action dataset, which
replenishes and extends the Kinetics-700 dataset. In this new version, there are at least 700 …

Recent DETR-based video grounding models have made the model directly predict moment
timestamps without any hand-crafted components, such as a pre-defined proposal or non …

The ability to reliably estimate physiological signals from video is a powerful tool in low-cost,
pre-clinical health monitoring. In this work we propose a new approach to remote …

Counting repetitive actions are widely seen in human activities such as physical exercise.
Existing methods focus on performing repetitive action counting in short videos, which is …

I went to the gym today, but how well did I do? And where should I improve? Ah, my back
hurts slightly... User engagement can be sustained and injuries avoided by being able to …

Understanding videos to localize moments with natural language often requires large
expensive annotated video regions paired with language queries. To eliminate the …

From human physiology to environmental evolution, important processes in nature often
exhibit meaningful and strong periodic or quasi-periodic changes. Due to their inherent label …

Online real-time production process monitoring is the basis for intelligent manufacturing
refinement management. This paper proposes a contactless monitoring framework with …

Sequential video understanding, as an emerging video understanding task, has driven lots
of researchers' attention because of its goal-oriented nature. This paper studies weakly …

This paper strives for repetitive activity counting in videos. Different from existing works,
which all analyze the visual video content only, we incorporate for the first time the …