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

Abstract

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.

arXiv commentTo appear in ICCV 2019

References in corpus (2)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• The THUMOS Challenge on Action Recognition for Videos "in the Wild"

Cited by in corpus (6)

• Action Unit Memory Network for Weakly Supervised Temporal Action Localization
• PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
• WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos
• Towards Train-Test Consistency for Semi-supervised Temporal Action Localization
• Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
• Weakly Supervised Action Selection Learning in Video