ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization

7 Apr 2021  ·  Sanqing Qu, Guang Chen, Zhijun Li, Lijun Zhang, Fan Lu, Alois Knoll ·

Weakly-supervised temporal action localization aims to localize action instances temporal boundary and identify the corresponding action category with only video-level labels. Traditional methods mainly focus on foreground and background frames separation with only a single attention branch and class activation sequence. However, we argue that apart from the distinctive foreground and background frames there are plenty of semantically ambiguous action context frames. It does not make sense to group those context frames to the same background class since they are semantically related to a specific action category. Consequently, it is challenging to suppress action context frames with only a single class activation sequence. To address this issue, in this paper, we propose an action-context modeling network termed ACM-Net, which integrates a three-branch attention module to measure the likelihood of each temporal point being action instance, context, or non-action background, simultaneously. Then based on the obtained three-branch attention values, we construct three-branch class activation sequences to represent the action instances, contexts, and non-action backgrounds, individually. To evaluate the effectiveness of our ACM-Net, we conduct extensive experiments on two benchmark datasets, THUMOS-14 and ActivityNet-1.3. The experiments show that our method can outperform current state-of-the-art methods, and even achieve comparable performance with fully-supervised methods. Code can be found at

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Weakly Supervised Action Localization ActivityNet-1.3 ACM-Net mAP@0.5 40.1 # 7
mAP@0.5:0.95 24.6 # 7
Weakly Supervised Action Localization THUMOS14 ACM-Net avg-mAP (0.1-0.5) 53.2 # 5
avg-mAP (0.3-0.7) 33.4 # 5
avg-mAP (0.1:0.7) 42.6 # 5
Weakly Supervised Action Localization THUMOS’14 ACM-Net mAP@0.5 34.6 # 5
Weakly Supervised Action Localization THUMOS 2014 ACM-Net mAP@0.5 34.6 # 10
mAP@0.1:0.7 42.6 # 11
mAP@0.1:0.5 53.2 # 9


No methods listed for this paper. Add relevant methods here