Loading...
Please wait, while we are loading the content...
Similar Documents
ASNet: Auto-Augmented Siamese Neural Network for Action Recognition
Content Provider | MDPI |
---|---|
Author | Zhang, Yujia Po, Lai-Man Xiong, Jingjing Rehman, Yasar Cheung, Kwok-Wai |
Copyright Year | 2021 |
Description | Human action recognition methods in videos based on deep convolutional neural networks usually use random cropping or its variants for data augmentation. However, this traditional data augmentation approach may generate many non-informative samples (video patches covering only a small part of the foreground or only the background) that are not related to a specific action. These samples can be regarded as noisy samples with incorrect labels, which reduces the overall action recognition performance. In this paper, we attempt to mitigate the impact of noisy samples by proposing an Auto-augmented Siamese Neural Network (ASNet). In this framework, we propose backpropagating salient patches and randomly cropped samples in the same iteration to perform gradient compensation to alleviate the adverse gradient effects of non-informative samples. Salient patches refer to the samples containing critical information for human action recognition. The generation of salient patches is formulated as a Markov decision process, and a reinforcement learning agent called SPA (Salient Patch Agent) is introduced to extract patches in a weakly supervised manner without extra labels. Extensive experiments were conducted on two well-known datasets UCF-101 and HMDB-51 to verify the effectiveness of the proposed SPA and ASNet. |
Starting Page | 4720 |
e-ISSN | 14248220 |
DOI | 10.3390/s21144720 |
Journal | Sensors |
Issue Number | 14 |
Volume Number | 21 |
Language | English |
Publisher | MDPI |
Publisher Date | 2021-07-10 |
Access Restriction | Open |
Subject Keyword | Sensors Artificial Intelligence Action Recognition 3d-cnn Deep Reinforcement Learning Data Augmentation |
Content Type | Text |
Resource Type | Article |