Ruitao Hou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ruitao Hou has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Teng Huang
Guangzhou University
3 shared publications - Hongyang Yan
School of Artificial Intelligence, Guangzhou University, Guangzhou, China
2 shared publications - Xianmin Wang
Guangzhou University
2 shared publications - Anli Yan
Guangzhou University
1 shared publication Chuangwei Zhu
School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China
1 shared publicationGuang Kou
Artificial Intelligence Research Center Defense Innovation Institute Beijing China
1 shared publication
Latest Publications
- Open Access
- 13 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (8) , 1-17
Boundary Attention-Guided Sparse Feature Learning for Underwater Object Tracking in Edge Computing
Underwater visual object tracking is crucial for marine resource exploration and military security. However, due to the effect of insufficient light and turbid background in underwater scenes, efficient and accurate target tracking cannot be realized on underwater edge devices with limited computing resources. To address this problem, we design an underwater object tracking network, namely DBSF, for edge computing devices based on sparse confidence feature learning guided by differential boundary attention. Specifically, we propose a differential boundary attention distribution model to compute the object edge distribution state to enhance the accurate perception of the underwater object edge structure. Then, the differential boundary attention-guided object tracking network learns to perceive the highly discriminative sparse features on the object structure, and computes the object sparse confidence matrix, which reduces the constraints of the edge devices with limited computational resources and ensures the tracking performance. Extensive experiments demonstrate that the DBSF network achieves accurate underwater target recognition and outperforms related advanced methods.
- 13 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (8) , 1-17
Open AccessBoundary Attention-Guided Sparse Feature Learning for Underwater Object Tracking in Edge Computing
Underwater visual object tracking is crucial for marine resource exploration and military security. However, due to the effect of insufficient light and turbid background in underwater scenes, efficient and accurate target tracking cannot be realized on underwater edge devices with limited computing resources. To address this problem, we design an underwater object tracking network, namely DBSF, for edge computing devices based on sparse confidence feature learning guided by differential boundary attention. Specifically, we propose a differential boundary attention distribution model to compute the object edge distribution state to enhance the accurate perception of the underwater object edge structure. Then, the differential boundary attention-guided object tracking network learns to perceive the highly discriminative sparse features on the object structure, and computes the object sparse confidence matrix, which reduces the constraints of the edge devices with limited computational resources and ensures the tracking performance. Extensive experiments demonstrate that the DBSF network achieves accurate underwater target recognition and outperforms related advanced methods.
- 6 June 2024
- Published by Elsevier in Information Sciences
- Vol. 677
Exploring the vulnerability of self-supervised monocular depth estimation models
- 6 June 2024
- Published by Elsevier in Information Sciences
- Vol. 677
Exploring the vulnerability of self-supervised monocular depth estimation models
- 5 April 2024
- Published by Springer Nature in Wireless Networks
- Vol. 30 (9) , 7569-7579
Bag of tricks for backdoor learning
- 5 April 2024
- Published by Springer Nature in Wireless Networks
- Vol. 30 (9) , 7569-7579
Bag of tricks for backdoor learning
- 10 May 2023
- Published by Springer Nature in World Wide Web
- Vol. 26 (5) , 2767-2783
A stealthy and robust backdoor attack via frequency domain transform
- 10 May 2023
- Published by Springer Nature in World Wide Web
- Vol. 26 (5) , 2767-2783
A stealthy and robust backdoor attack via frequency domain transform
- 2 March 2023
- Published by Elsevier in Information Sciences
- Vol. 642, 118724
Transfer subspace learning via label release and contribution degree distinction
- 2 March 2023
- Published by Elsevier in Information Sciences
- Vol. 642, 118724
Transfer subspace learning via label release and contribution degree distinction
- 19 August 2022
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (11) , 9373-9389
An effective and practical gradient inversion attack
- 19 August 2022
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (11) , 9373-9389
An effective and practical gradient inversion attack
- Open Access
A Universal Detection Method for Adversarial Examples and Fake Images
Deep-learning technologies have shown impressive performance on many tasks in recent years. However, there are multiple serious security risks when using deep-learning technologies. For examples, state-of-the-art deep-learning technologies are vulnerable to adversarial examples that make the model’s predictions wrong due to some specific subtle perturbation, and these technologies can be abused for the tampering with and forgery of multimedia, i.e., deep forgery. In this paper, we propose a universal detection framework for adversarial examples and fake images. We observe some differences in the distribution of model outputs for normal and adversarial examples (fake images) and train the detector to learn the differences. We perform extensive experiments on the CIFAR10 and CIFAR100 datasets. Experimental results show that the proposed framework has good feasibility and effectiveness in detecting adversarial examples or fake images. Moreover, the proposed framework has good generalizability for the different datasets and model structures.
Open AccessA Universal Detection Method for Adversarial Examples and Fake Images
Deep-learning technologies have shown impressive performance on many tasks in recent years. However, there are multiple serious security risks when using deep-learning technologies. For examples, state-of-the-art deep-learning technologies are vulnerable to adversarial examples that make the model’s predictions wrong due to some specific subtle perturbation, and these technologies can be abused for the tampering with and forgery of multimedia, i.e., deep forgery. In this paper, we propose a universal detection framework for adversarial examples and fake images. We observe some differences in the distribution of model outputs for normal and adversarial examples (fake images) and train the detector to learn the differences. We perform extensive experiments on the CIFAR10 and CIFAR100 datasets. Experimental results show that the proposed framework has good feasibility and effectiveness in detecting adversarial examples or fake images. Moreover, the proposed framework has good generalizability for the different datasets and model structures.
- 19 September 2021
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (12) , 10598-10620
ELAA: An efficient local adversarial attack using model interpreters
- 19 September 2021
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (12) , 10598-10620
ELAA: An efficient local adversarial attack using model interpreters