Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection

Résumé

Out-of-distribution (OOD) detection targets to detect and reject test samples with semantic shifts, to prevent models trained on in-distribution (ID) dataset from producing unreliable predictions. Existing works only extract the appearance features on image datasets, and cannot handle dynamic multimedia scenarios with much motion information. Therefore, we target a more realistic and challenging OOD detection task: OOD action detection (ODAD). Given an untrimmed video, ODAD first classifies the ID actions and recognizes the OOD actions, and then localizes ID and OOD actions. To this end, in this paper, we propose a novel Uncertainty-Guided Appearance-Motion Association Network (UAAN), which explores both appearance features and motion contexts to reason spatial-temporal inter-object interaction for ODAD. Firstly, we design separate appearance and motion branches to extract corresponding appearance-oriented and motion-aspect object representations. In each branch, we construct a spatial-temporal graph to reason appearance-guided and motion-driven inter-object interaction. Then, we design an appearance-motion attention module to fuse the appearance and motion features for final action detection. Experimental results on two challenging datasets show that UAAN beats state-of-theart methods by a significant margin, illustrating its effectiveness.

Fichier principal
Vignette du fichier
FEG24.pdf (718.72 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04777048 , version 1 (14-11-2024)

Identifiants

Citer

Xiang Fang, Arvind Easwaran, Blaise Genest. Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection. 2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), 2024, San José (CA), United States. pp.176-182, ⟨10.1109/MIPR62202.2024.00034⟩. ⟨hal-04777048⟩
10 Consultations
6 Téléchargements

Altmetric

Partager

More