Modeling Multi-Label Action Dependencies for Temporal Action Localization

TL;DR

This paper introduces an attention-based model that captures both co-occurrence and temporal dependencies between actions to improve the accuracy of localizing multiple actions in untrimmed videos.

Contribution

It proposes a novel Multi-Label Action Dependency (MLAD) layer with two branches to explicitly model action dependencies at different time scales.

Findings

Improved f-mAP on MultiTHUMOS and Charades datasets.

New metrics effectively measure action dependency modeling.

State-of-the-art performance achieved.

Abstract

Real-world videos contain many complex actions with inherent relationships between action classes. In this work, we propose an attention-based architecture that models these action relationships for the task of temporal action localization in untrimmed videos. As opposed to previous works that leverage video-level co-occurrence of actions, we distinguish the relationships between actions that occur at the same time-step and actions that occur at different time-steps (i.e. those which precede or follow each other). We define these distinct relationships as action dependencies. We propose to improve action localization performance by modeling these action dependencies in a novel attention-based Multi-Label Action Dependency (MLAD)layer. The MLAD layer consists of two branches: a Co-occurrence Dependency Branch and a Temporal Dependency Branch to model co-occurrence action dependencies and temporal action dependencies, respectively. We observe that existing metrics used for multi-label classification do not explicitly measure how well action dependencies are modeled, therefore, we propose novel metrics that consider both co-occurrence and temporal dependencies between action classes. Through empirical evaluation and extensive analysis, we show improved performance over state-of-the-art methods on multi-label action localization benchmarks(MultiTHUMOS and Charades) in terms of f-mAP and our proposed metric.