CTRN: Class-Temporal Relational Network for Action Detection

Understand

Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos.

• There are many real-world challenges in those datasets, such as composite action, co-occurring action, and high temporal variation of instance duration.
• For handling these challenges, we propose to explore both the class and temporal relations of detected actions.
• In this work, we introduce an end-to-end network: Class-Temporal Relational Network (CTRN).