ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization

12/21/2021
by   Zichen Yang, et al.
0

Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available. Existing approaches typically leverage off-the-shelf segment-level features, which suffer from spatial incompleteness and temporal incoherence, thus limiting their performance. In this paper, we tackle this problem from a new perspective by enhancing segment-level representations with a simple yet effective graph convolutional network, namely action complement graph network (ACGNet). It facilitates the current video segment to perceive spatial-temporal dependencies from others that potentially convey complementary clues, implicitly mitigating the negative effects caused by the two issues above. By this means, the segment-level features are more discriminative and robust to spatial-temporal variations, contributing to higher localization accuracies. More importantly, the proposed ACGNet works as a universal module that can be flexibly plugged into different WTAL frameworks, while maintaining the end-to-end training fashion. Extensive experiments are conducted on the THUMOS'14 and ActivityNet1.2 benchmarks, where the state-of-the-art results clearly demonstrate the superiority of the proposed approach.

READ FULL TEXT
research
01/21/2020

Weakly Supervised Temporal Action Localization Using Deep Metric Learning

Temporal action localization is an important step towards video understa...
research
02/14/2019

Exploring Frame Segmentation Networks for Temporal Action Localization

Temporal action localization is an important task of computer vision. Th...
research
07/31/2023

DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization

Weakly-supervised temporal action localization (WTAL) is a practical yet...
research
05/10/2021

Action Shuffling for Weakly Supervised Temporal Localization

Weakly supervised action localization is a challenging task with extensi...
research
02/14/2022

Adaptive graph convolutional networks for weakly supervised anomaly detection in videos

For the weakly supervised anomaly detection task, most existing work is ...
research
05/21/2019

Marginalized Average Attentional Network for Weakly-Supervised Learning

In weakly-supervised temporal action localization, previous works have f...
research
11/21/2022

Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization

Weakly supervised temporal action localization (WTAL) aims to localize a...

Please sign up or login with your details

Forgot password? Click here to reset