Enhancing Class-semantics Features' Locating Performance for Temporal Action Localization

2021 ◽  
Author(s):  
Jianmin Zhang ◽  
Jianqin Yin
Keyword(s):  
Action Localization ◽  
Temporal Action

I2Net: Mining Intra-video and Inter-video Attention for Temporal Action Localization

2021 ◽  
Author(s):  
Wei Zhang ◽  
Binglu Wang ◽  
Songhui Ma ◽  
Yani Zhang ◽  
Yongqiang Zhao
Keyword(s):  
Action Localization ◽  
Temporal Action

Multi-Hierarchical Category Supervision for Weakly-Supervised Temporal Action Localization

2021 ◽  
pp. 1-1
Author(s):  
Guozhang Li ◽  
Jie Li ◽  
Nannan Wang ◽  
Xinpeng Ding ◽  
Zhifeng Li ◽  
...  
Keyword(s):  
Action Localization ◽  
Weakly Supervised ◽  
Temporal Action

Spatio-Temporal Action Localization for Pedestrian Action Detection

2020 ◽  
pp. 1337-1341
Author(s):  
Linchao He ◽  
Jiong Mu ◽  
Mengting Luo ◽  
Yunlu Lu ◽  
Xuefeng Tan ◽  
...  
Keyword(s):  
Action Detection ◽  
Action Localization ◽  
Spatio Temporal ◽  
Temporal Action

Frame Segmentation Networks for Temporal Action Localization

2018 ◽  
pp. 242-252
Author(s):  
Ke Yang ◽  
Peng Qiao ◽  
Qiang Wang ◽  
Shijie Li ◽  
Xin Niu ◽  
...  
Keyword(s):  
Action Localization ◽  
Temporal Action

scholarly journals Relational Prototypical Network for Weakly Supervised Temporal Action Localization

2020 ◽  
Vol 34 (07) ◽  
pp. 11053-11060
Author(s):  
Linjiang Huang ◽  
Yan Huang ◽  
Wanli Ouyang ◽  
Liang Wang
Keyword(s):  
State Of The Art ◽  
Previous Method ◽  
The State ◽  
Localization Method ◽  
Action Localization ◽  
Art Methods ◽  
Prototype Learning ◽  
Weakly Supervised ◽  
Temporal Action

In this paper, we propose a weakly supervised temporal action localization method on untrimmed videos based on prototypical networks. We observe two challenges posed by weakly supervision, namely action-background separation and action relation construction. Unlike the previous method, we propose to achieve action-background separation only by the original videos. To achieve this, a clustering loss is adopted to separate actions from backgrounds and learn intra-compact features, which helps in detecting complete action instances. Besides, a similarity weighting module is devised to further separate actions from backgrounds. To effectively identify actions, we propose to construct relations among actions for prototype learning. A GCN-based prototype embedding module is introduced to generate relational prototypes. Experiments on THUMOS14 and ActivityNet1.2 datasets show that our method outperforms the state-of-the-art methods.

scholarly journals Bottom-Up Temporal Action Localization with Mutual Regularization

2020 ◽  
pp. 539-555
Author(s):  
Peisen Zhao ◽  
Lingxi Xie ◽  
Chen Ju ◽  
Ya Zhang ◽  
Yanfeng Wang ◽  
...  
Keyword(s):  
Bottom Up ◽  
Action Localization ◽  
Temporal Action
Sign in / Sign up

Export Citation Format

Share Document