Skip to Main content Skip to Navigation
New interface
Conference papers

CTRN: Class Temporal Relational Network For Action Detection

Abstract : 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 a 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.
Document type :
Conference papers
Complete list of metadata
Contributor : Rui DAI Connect in order to contact the contributor
Submitted on : Wednesday, November 3, 2021 - 3:34:09 PM
Last modification on : Friday, November 18, 2022 - 9:23:20 AM


Files produced by the author(s)


  • HAL Id : hal-03383140, version 3


Rui Dai, Srijan Das, Francois F Bremond. CTRN: Class Temporal Relational Network For Action Detection. BMVC 2021 - The British Machine Vision Conference, Nov 2021, Virtual, United Kingdom. ⟨hal-03383140v3⟩



Record views


Files downloads