.png){kind=icon}
返回
Temporal Dropout for Weakly Supervised Action Localization
.png){kind=icon}
PRE
AI
DOI：10.1145/3567827.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Weakly supervised action localization is a challenging problem in video understanding and action recognition. Existing models usually formulate the training process as direct classification using video-level supervision. They tend to only locate the most discriminative parts of action instances and produce temporally incomplete detection results. A natural solution for this problem, the adversarial erasing strategy, is to remove such parts from training so that models can attend to complementary parts. Previous works do it in an offline and heuristic way. They adopt a multi-stage pipeline, where discriminative regions are determined and erased under the guidance of detection results from last stage. Such a pipeline can be both ineffective and inefficient, possibly hindering the overall performance. On the contrary, we combine adversarial erasing with dropout mechanism and propose a Temporal Dropout Module that learns where to remove in a data-driven and online manner. This plug-and-play module is trained without iterative stages, which not only simplifies the pipeline but also makes the regularization during training easier and more adaptive. Experiments show that the proposed method outperforms previous erasing-based methods by a large margin. More importantly, it achieves universal improvement when plugged into various direct classification methods and obtains state-of-the-art performance.
Keyword:
Weakly supervised
temporal action localization
adversarial erasing
adaptive dropout
期刊
IF:
6
论文数:
2.0K
被引数:
5.4K
机构
引用论文
.png){kind=icon}
Adaptive Energy Management Strategy Calibration in PHEVs Based on a Sensitivity Study基于灵敏度研究的phev自适应能量管理策略标定
PREAI
分享收藏
查看更多内容