CTRN: Class Temporal Relational Network For Action Detection - 3IA Côte d’Azur – Interdisciplinary Institute for Artificial Intelligence Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

CTRN: Class Temporal Relational Network For Action Detection

Résumé

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.
Fichier principal
Vignette du fichier
CTRN_Rui.pdf (1.4 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03383140 , version 1 (18-10-2021)
hal-03383140 , version 2 (18-10-2021)
hal-03383140 , version 3 (03-11-2021)

Identifiants

  • HAL Id : hal-03383140 , version 3

Citer

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⟩
129 Consultations
202 Téléchargements

Partager

Gmail Facebook X LinkedIn More