Knowledge Commons of Institute of Automation,CAS
Compact Representation and Reliable Classification Learning for Point-Level Weakly-Supervised Action Localization | |
Fu, Jie1,2; Gao, Junyu2,3![]() ![]() | |
发表期刊 | IEEE Transactions on Image Processing
![]() |
2022 | |
卷号 | 31页码:7363 - 7377 |
摘要 | Point-level weakly-supervised temporal action localization (P-WSTAL) aims to localize temporal extents of action instances and identify the corresponding categories with only a single point label for each action instance for training. Due to the sparse frame-level annotations, most existing models are in the localization-by-classification pipeline. However, there exist two major issues in this pipeline: large intra-action variation due to task gap between classification and localization and noisy classification learning caused by unreliable pseudo training samples. In this paper, we propose a novel framework CRRC-Net, which introduces a co-supervised feature learning module and a probabilistic pseudo label mining module, to simultaneously address the above two issues. Specifically, the co-supervised feature learning module is applied to exploit the complementary information in different modalities for learning more compact feature representations. Furthermore, the probabilistic pseudo label mining module utilizes the feature distances from action prototypes to estimate the likelihood of pseudo samples and rectify their corresponding labels for more reliable classification learning. Comprehensive experiments are conducted on different benchmarks and the experimental results show that our method achieves favorable performance with the state-of-the-art. |
其他摘要 |
|
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 小样本高噪声数据学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51520 |
专题 | 多模态人工智能系统全国重点实验室 |
作者单位 | 1.School of Computer and Artificial Intelligence, Zhengzhou University 2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.Peng Cheng Laboratory |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Fu, Jie,Gao, Junyu,Xu, Changsheng. Compact Representation and Reliable Classification Learning for Point-Level Weakly-Supervised Action Localization[J]. IEEE Transactions on Image Processing,2022,31:7363 - 7377. |
APA | Fu, Jie,Gao, Junyu,&Xu, Changsheng.(2022).Compact Representation and Reliable Classification Learning for Point-Level Weakly-Supervised Action Localization.IEEE Transactions on Image Processing,31,7363 - 7377. |
MLA | Fu, Jie,et al."Compact Representation and Reliable Classification Learning for Point-Level Weakly-Supervised Action Localization".IEEE Transactions on Image Processing 31(2022):7363 - 7377. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论