3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization

Temporal action localization is a challenging computer vision problem with numerous real-world applications. Most existing methods require laborious frame-level supervision to train action localization models. In this work, we propose a framework, called 3C-Net, which only requires video-level supervision (weak supervision) in the form of action category labels and the corresponding count. We introduce a novel formulation to learn discriminative action features with enhanced localization capabilities. Our joint formulation has three terms: a classification term to ensure the separability of learned action features, an adapted multi-label center loss term to enhance the action feature discriminability and a counting loss term to delineate adjacent action sequences, leading to improved localization. Comprehensive experiments are performed on two challenging benchmarks: THUMOS14 and ActivityNet 1.2. Our approach sets a new state-of-the-art for weakly-supervised temporal action localization on both datasets. On the THUMOS14 dataset, the proposed method achieves an absolute gain of 4.6% in terms of mean average precision (mAP), compared to the state-of-the-art. Source code is available at https://github.com/naraysa/3c-net.

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Weakly Supervised Action Localization ActivityNet-1.2 3C-Net mAP@0.5 37.2 # 10
Mean mAP 21.7 # 9
Action Classification ActivityNet-1.2 3C-Net mAP 92.4 # 2
Action Classification THUMOS'14 3C-Net mAP 86.9 # 1
Action Classification THUMOS’14 3C-Net mAP 86.9 # 1
Weakly Supervised Action Localization THUMOS’14 3C-Net mAP@0.5 26.6 # 12
Weakly Supervised Action Localization THUMOS 2014 3C-Net mAP@0.5 26.6 # 15


No methods listed for this paper. Add relevant methods here