Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling

06/20/2021
by   Xiang Wang, et al.
0

Weakly-Supervised Temporal Action Localization (WS-TAL) task aims to recognize and localize temporal starts and ends of action instances in an untrimmed video with only video-level label supervision. Due to lack of negative samples of background category, it is difficult for the network to separate foreground and background, resulting in poor detection performance. In this report, we present our 2021 HACS Challenge - Weakly-supervised Learning Track solution that based on BaSNet to address above problem. Specifically, we first adopt pre-trained CSN, Slowfast, TDN, and ViViT as feature extractors to get feature sequences. Then our proposed Local-Global Background Modeling Network (LGBM-Net) is trained to localize instances by using only video-level labels based on Multi-Instance Learning (MIL). Finally, we ensemble multiple models to get the final detection results and reach 22.45

READ FULL TEXT
research
06/22/2022

Weakly-supervised Action Localization via Hierarchical Mining

Weakly-supervised action localization aims to localize and classify acti...
research
03/30/2023

JCDNet: Joint of Common and Definite phases Network for Weakly Supervised Temporal Action Localization

Weakly-supervised temporal action localization aims to localize action i...
research
07/09/2018

Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector

Weakly supervised temporal action detection is a Herculean task in under...
research
08/19/2023

Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling

Weakly-supervised action localization aims to recognize and localize act...
research
03/24/2021

The Blessings of Unlabeled Background in Untrimmed Videos

Weakly-supervised Temporal Action Localization (WTAL) aims to detect the...
research
06/24/2021

Exploring Stronger Feature for Temporal Action Localization

Temporal action localization aims to localize starting and ending time w...
research
08/25/2022

Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream

Detecting actions in videos have been widely applied in on-device applic...

Please sign up or login with your details

Forgot password? Click here to reset