.png){kind=icon}
返回
Dual relation network for temporal action localization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108725.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
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.
Keyword:
Temporal action localization
Relation reasoning
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
查看更多机构
引用论文
Learning motion representation for real-time spatio-temporal action localization实时时空动作定位的运动表示学习.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Domain learning joint with semantic adaptation for human action recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Deep snippet selective network for weakly supervised temporal action localizationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Temporally smooth online action detection using cycle-consistent future anticipationPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏分享收藏Weakly-supervised action localization via embedding-modeling iterative optimizationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏 没有更多内容