Graph Convolutional Networks for Temporal Action Localization

TL;DR

This paper introduces a novel approach using Graph Convolutional Networks to model relationships between action proposals, significantly improving temporal action localization accuracy.

Contribution

It proposes a new method that explicitly models proposal-proposal relations with GCNs for better action localization.

Findings

Outperforms state-of-the-art on THUMOS14 with 49.1% accuracy.

Effective modeling of proposal relations improves localization.

Validated on ActivityNet dataset.

Abstract

Most state-of-the-art action localization systems process each action proposal individually, without explicitly exploiting their relations during learning. However, the relations between proposals actually play an important role in action localization, since a meaningful action always consists of multiple proposals in a video. In this paper, we propose to exploit the proposal-proposal relations using Graph Convolutional Networks (GCNs). First, we construct an action proposal graph, where each proposal is represented as a node and their relations between two proposals as an edge. Here, we use two types of relations, one for capturing the context information for each proposal and the other one for characterizing the correlations between distinct actions. Then we apply the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization. Experimental results show that our approach significantly outperforms the state-of-the-art on THUMOS14 (49.1% versus 42.8%). Moreover, augmentation experiments on ActivityNet also verify the efficacy of modeling action proposal relationships. Codes are available at https://github.com/Alvin-Zeng/PGCN.