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

TL;DR

This paper introduces UAAN, a novel network that combines appearance and motion features with uncertainty guidance to improve out-of-distribution action detection in videos, outperforming existing methods.

Contribution

The paper proposes a new UAAN model that integrates appearance and motion features with spatial-temporal reasoning and attention mechanisms for more effective OOD action detection.

Findings

UAAN significantly outperforms state-of-the-art methods on two datasets.

The model effectively reasons inter-object interactions using spatial-temporal graphs.

Fusion of appearance and motion features enhances detection accuracy.

Abstract

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-the-art methods by a significant margin, illustrating its effectiveness.