CTRN: Class-Temporal Relational Network for Action Detection
This addresses the problem of detecting actions with composite, co-occurring, and temporally varying instances in videos, which is incremental as it builds on existing relational modeling approaches.
The paper tackled action detection in densely labelled untrimmed videos by proposing the Class-Temporal Relational Network (CTRN) to model class and temporal relations, achieving state-of-the-art performance on three challenging datasets.
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). It contains three key components: (1) The Representation Transform Module filters the class-specific features from the mixed representations to build graph-structured data. (2) The Class-Temporal Module models the class and temporal relations in a sequential manner. (3) G-classifier leverages the privileged knowledge of the snippet-wise co-occurring action pairs to further improve the co-occurring action detection. We evaluate CTRN on three challenging densely labelled datasets and achieve state-of-the-art performance, reflecting the effectiveness and robustness of our method.