Bibliographic Details
| Title: |
Pseudo label refining for semi-supervised temporal action localization. |
| Authors: |
Meng, Lingwen1 (AUTHOR) menglingwen_gpg@163.com, Ban, Guobang1 (AUTHOR), Xi, Guanghui1 (AUTHOR), Guo, Siqi1 (AUTHOR) |
| Source: |
PLoS ONE. 2/5/2025, Vol. 20 Issue 2, p1-19. 19p. |
| Subject Terms: |
*TEMPORAL lobe, *LEARNING strategies, *DETECTORS, *ANNOTATIONS, *TEACHERS, *LOCALIZATION (Mathematics) |
| Abstract: |
The training of temporal action localization models relies heavily on a large amount of manually annotated data. Video annotation is more tedious and time-consuming compared with image annotation. Therefore, the semi-supervised method that combines labeled and unlabeled data for joint training has attracted increasing attention from academics and industry. This study proposes a method called pseudo-label refining (PLR) based on the teacher-student framework, which consists of three key components. First, we propose pseudo-label self-refinement which features in a temporal region interesting pooling to improve the boundary accuracy of TAL pseudo label. Second, we design a module named boundary synthesis to further refined temporal interval in pseudo label with multiple inference. Finally, an adaptive weight learning strategy is tailored for progressively learning pseudo labels with different qualities. The method proposed in this study uses ActionFormer and BMN as the detector and achieves significant improvement on the THUMOS14 and ActivityNet v1.3 datasets. The experimental results show that the proposed method significantly improve the localization accuracy compared to other advanced SSTAL methods at a label rate of 10% to 60%. Further ablation experiments show the effectiveness of each module, proving that the PLR method can improve the accuracy of pseudo-labels obtained by teacher model reasoning. [ABSTRACT FROM AUTHOR] |
|
Copyright of PLoS ONE is the property of Public Library of Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Academic Search Complete |
|
Full text is not displayed to guests. |
Login for full access.
|
