Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization

TL;DR

This paper introduces CO2-Net, a novel cross-modal consensus network that enhances weakly supervised temporal action localization by using attention mechanisms and mutual learning to produce more representative features, achieving state-of-the-art results.

Contribution

The paper proposes a cross-modal consensus network with attention modules and mutual learning for improved feature calibration in weakly supervised temporal action localization.

Findings

Achieves state-of-the-art results on THUMOS14 and ActivityNet1.2 datasets.

The cross-modal consensus module effectively filters task-irrelevant information.

Mutual learning between modules maintains prediction consistency.

Abstract

Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. Both appearance and motion features are used in previous works, while they do not utilize them in a proper way but apply simple concatenation or score-level fusion. In this work, we argue that the features extracted from the pretrained extractor, e.g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant information redundancy. Therefore, we propose a cross-modal consensus network (CO2-Net) to tackle this problem. In CO2-Net, we mainly introduce two identical proposed cross-modal consensus modules (CCM) that design a cross-modal attention mechanism to filter out the task-irrelevant information redundancy using the global information from the main modality and the cross-modal local information of the auxiliary modality. Moreover, we treat the attention weights derived from each CCMas the pseudo targets of the attention weights derived from another CCM to maintain the consistency between the predictions derived from two CCMs, forming a mutual learning manner. Finally, we conduct extensive experiments on two common used temporal action localization datasets, THUMOS14 and ActivityNet1.2, to verify our method and achieve the state-of-the-art results. The experimental results show that our proposed cross-modal consensus module can produce more representative features for temporal action localization.