.png){kind=icon}
Return
Dual relation network for temporal action localization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108725.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Temporal action localization is a challenging task for video understanding. Most previous methods process each proposal independently and neglect the reasoning of proposal-proposal and proposal-context relations. We argue that the supplementary information obtained by exploiting these relations can enhance the proposal representation and further boost the action localization. To this end, we propose a dual relation network to model both proposal-proposal and proposal-context relations. Concretely, a proposal-proposal relation module is leveraged to learn discriminative supplementary information from relevant proposals, which allows the network to model their interaction based on appearance and geometric similarities. Meanwhile, a proposal-context relation module is employed to mine contextual clues by adaptively learning from the global context outside of region-based proposals. They effectively leverage the inherent correlation between actions and the long-term dependency with videos for high-quality proposal refinement. As a result, the proposed framework enables the model to distinguish similar action instances and locate temporal boundaries more precisely. Extensive experiments on the THUMOS14 dataset and ActivityNet v1.3 dataset demonstrate that the proposed method significantly outperforms recent state-of-the-art methods. (C) 2022 Elsevier Ltd. All rights reserved.
Keywords:
Temporal action localization
Relation reasoning
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
View more organizations
Cited Papers
Learning motion representation for real-time spatio-temporal action localization.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveDomain learning joint with semantic adaptation for human action recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveDeep snippet selective network for weakly supervised temporal action localizationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveTemporally smooth online action detection using cycle-consistent future anticipationPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveShareSaveShareSaveWeakly-supervised action localization via embedding-modeling iterative optimizationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave no more