Hongdou Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hongdou Yao has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Yansheng Qiu
Wuhan University
5 shared publications - Zheng Wang
Wuhan University
5 shared publications - Jun Chen
National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan 430072, China
4 shared publications - Pengfei Han
School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xian, China
4 shared publications - Xiaoyu Chai
Wuhan University
4 shared publications - Dongshu Xu
Wuhan University
2 shared publications
Latest Publications
- 3 April 2026
- Published by Elsevier in Information Fusion
- Vol. 134
Unlocking insights: Bridging modality-specific grounding to advance monocular 3D visual grounding
- 3 April 2026
- Published by Elsevier in Information Fusion
- Vol. 134
Unlocking insights: Bridging modality-specific grounding to advance monocular 3D visual grounding
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 73 (1) , 41-48
An Adaptive Optimization Regulation Method for Neutron Spectrum Based on Reinforcement Learning
The regulation and control of neutron transport behavior is crucial to the design and development of nuclear energy systems and the application of nuclear technology. The accurate and efficient regulation of neutrons to satisfy the specific needs of neutron experimental environments is an urgent challenge to be solved. The traditional forward neutron spectrum regulation method based on artificial designing could hardly meet the demands of high accuracy and high efficiency at the same time. In this research, an adaptive optimization regulation method for neutron spectrum based on reinforcement learning was developed. The proposed method designed different types of standardized response modules and calibrated it with their corresponding multi-dimensional response matrix calculated by the Monte Carlo program. Through the proximal policy optimization (PPO) algorithm outputs the selection and layout of the response module, and generates the optimal scheme that conforms to the target neutron spectrum by the process of continuous interaction with the environment and self-game. The 14MeV single-energy neutron source was used to verify the regulated results of the proposed method on the tritium breeder blanket of a fusion reactor (ITER) whose results showed that the accuracy of the proposed method was improved by 39.31% compared to the forward manual experiment.
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 73 (1) , 41-48
An Adaptive Optimization Regulation Method for Neutron Spectrum Based on Reinforcement Learning
The regulation and control of neutron transport behavior is crucial to the design and development of nuclear energy systems and the application of nuclear technology. The accurate and efficient regulation of neutrons to satisfy the specific needs of neutron experimental environments is an urgent challenge to be solved. The traditional forward neutron spectrum regulation method based on artificial designing could hardly meet the demands of high accuracy and high efficiency at the same time. In this research, an adaptive optimization regulation method for neutron spectrum based on reinforcement learning was developed. The proposed method designed different types of standardized response modules and calibrated it with their corresponding multi-dimensional response matrix calculated by the Monte Carlo program. Through the proximal policy optimization (PPO) algorithm outputs the selection and layout of the response module, and generates the optimal scheme that conforms to the target neutron spectrum by the process of continuous interaction with the environment and self-game. The 14MeV single-energy neutron source was used to verify the regulated results of the proposed method on the tritium breeder blanket of a fusion reactor (ITER) whose results showed that the accuracy of the proposed method was improved by 39.31% compared to the forward manual experiment.
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (10) , 19068-19080
MonOri: Orientation-Guided PnP for Monocular 3-D Object Detection
Monocular 3-D object detection is a challenging task in the field of autonomous driving and has made great progress. However, current monocular image methods tend to incorporate additional information such as pseudolabels to improve algorithm performance while overlooking the geometric relationship between the object's keypoints, resulting in low performance for occluded object detection. To address this issue, we find that introducing the orientation information of objects in the 3-D detection pipeline can help improve the detection performance of occluded objects. An orientation-guided perspective-n-point (PnP) for monocular 3-D object detection method named MonOri is presented in this article, which uses object's orientation to guide keypoints' optimization. Considering the existence of different deformation objects in the scene, we design the feature aggregation detection module (FADM), which consists of the feature focus fusion module (FFFM) and CondConv detection module (CCDM). First, FFFM can highlight signals from irregularly occluded objects, effectively modeling features of elongated and small-sized objects. This module enhances the model's ability to recognize elongated and small-sized objects in complex scenes. Then, the CCDM is designed to improve the network's ability to estimate object keypoints' location regression under occlusion conditions and minimize the network computational overhead. Finally, considering that the unoccluded portions of occluded objects are closely related to the orientation of the objects, an orientation-guided keypoints' selection module (OGKSM) is proposed to enhance the accuracy of objected optimization for keypoint positions and spatial location inference of the object. Experimental results indicate that the MonOri method achieves competitive results; it is also demonstrated that the orientation information is introduced in the PnP algorithm to estimate the object's spatial position that can mitigate the impact of occlusion on object detection, thus improving the recognition rate of occluded objects. Our code is available at https://github.com/DL-YHD/MonOri.
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (10) , 19068-19080
MonOri: Orientation-Guided PnP for Monocular 3-D Object Detection
Monocular 3-D object detection is a challenging task in the field of autonomous driving and has made great progress. However, current monocular image methods tend to incorporate additional information such as pseudolabels to improve algorithm performance while overlooking the geometric relationship between the object's keypoints, resulting in low performance for occluded object detection. To address this issue, we find that introducing the orientation information of objects in the 3-D detection pipeline can help improve the detection performance of occluded objects. An orientation-guided perspective-n-point (PnP) for monocular 3-D object detection method named MonOri is presented in this article, which uses object's orientation to guide keypoints' optimization. Considering the existence of different deformation objects in the scene, we design the feature aggregation detection module (FADM), which consists of the feature focus fusion module (FFFM) and CondConv detection module (CCDM). First, FFFM can highlight signals from irregularly occluded objects, effectively modeling features of elongated and small-sized objects. This module enhances the model's ability to recognize elongated and small-sized objects in complex scenes. Then, the CCDM is designed to improve the network's ability to estimate object keypoints' location regression under occlusion conditions and minimize the network computational overhead. Finally, considering that the unoccluded portions of occluded objects are closely related to the orientation of the objects, an orientation-guided keypoints' selection module (OGKSM) is proposed to enhance the accuracy of objected optimization for keypoint positions and spatial location inference of the object. Experimental results indicate that the MonOri method achieves competitive results; it is also demonstrated that the orientation information is introduced in the PnP algorithm to estimate the object's spatial position that can mitigate the impact of occlusion on object detection, thus improving the recognition rate of occluded objects. Our code is available at https://github.com/DL-YHD/MonOri.
- 5 April 2025
- Published by Elsevier in Optics & Laser Technology
- Vol. 188
Super-resolution via hierarchical attention and detail enhancement transformer network
- 5 April 2025
- Published by Elsevier in Optics & Laser Technology
- Vol. 188
Super-resolution via hierarchical attention and detail enhancement transformer network
- 7 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (5) , 2194-2205
Does Adding a Modality Really Make Positive Impacts in Incomplete Multi-Modal Brain Tumor Segmentation?
Previous incomplete multi-modal brain tumor segmentation technologies, while effective in integrating diverse modalities, commonly deliver under-expected performance gains. The reason lies in that the new modality may cause confused predictions due to uncertain and inconsistent patterns and quality in some positions, where the direct fusion consequently raises the negative gain for the final decision. In this paper, considering the potentially negative impacts within a modality, we propose multi-modal Positive-Negative impact region Double Calibration pipeline, called PNDC, to mitigate misinformation transfer of modality fusion. Concretely, PNDC involves two elaborate pipelines, Reverse Audit and Forward Checksum. The former is to identify negative regions impacts of each modality. The latter calibrates whether the fusion prediction is reliable in these regions by integrating the positive impacts regions of each modality. Finally, the negative impacts region from each modality and miss-match reliable fusion predictions are utilized to enhance the learning of individual modalities and fusion process. It is noted that PNDC adopts the standard training strategy without specific architectural choices and does not introduce any learning parameters, and thus can be easily plugged into existing network training for incomplete multi-modal brain tumor segmentation. Extensive experiments confirm that our PNDC greatly alleviates the performance degradation of current state-of-the-art incomplete medical multi-modal methods, arising from overlooking the positive/negative impacts regions of the modality. The code is released at PNDC.
- 7 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (5) , 2194-2205
Does Adding a Modality Really Make Positive Impacts in Incomplete Multi-Modal Brain Tumor Segmentation?
Previous incomplete multi-modal brain tumor segmentation technologies, while effective in integrating diverse modalities, commonly deliver under-expected performance gains. The reason lies in that the new modality may cause confused predictions due to uncertain and inconsistent patterns and quality in some positions, where the direct fusion consequently raises the negative gain for the final decision. In this paper, considering the potentially negative impacts within a modality, we propose multi-modal Positive-Negative impact region Double Calibration pipeline, called PNDC, to mitigate misinformation transfer of modality fusion. Concretely, PNDC involves two elaborate pipelines, Reverse Audit and Forward Checksum. The former is to identify negative regions impacts of each modality. The latter calibrates whether the fusion prediction is reliable in these regions by integrating the positive impacts regions of each modality. Finally, the negative impacts region from each modality and miss-match reliable fusion predictions are utilized to enhance the learning of individual modalities and fusion process. It is noted that PNDC adopts the standard training strategy without specific architectural choices and does not introduce any learning parameters, and thus can be easily plugged into existing network training for incomplete multi-modal brain tumor segmentation. Extensive experiments confirm that our PNDC greatly alleviates the performance degradation of current state-of-the-art incomplete medical multi-modal methods, arising from overlooking the positive/negative impacts regions of the modality. The code is released at PNDC.
- 29 December 2023
- Published by Springer Nature
- p. 27-39
Multi-image 3D Face Reconstruction via an Adaptive Aggregation Network
- 29 December 2023
- Published by Springer Nature
- p. 27-39
Multi-image 3D Face Reconstruction via an Adaptive Aggregation Network
- 29 December 2023
- Published by Springer Nature
- p. 70-82
An Adaptive-Guidance GAN for Accurate Face Reenactment
- 29 December 2023
- Published by Springer Nature
- p. 70-82
An Adaptive-Guidance GAN for Accurate Face Reenactment
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3228-3239
Modal-aware Visual Prompting for Incomplete Multi-modal Brain Tumor Segmentation
In the realm of medical imaging, distinct magnetic resonance imaging (MRI) modalities can provide complementary medical insights. However, it is not uncommon for one or more modalities to be absent due to image corruption, artifacts, acquisition protocols, allergies to contrast agents, or cost constraints, posing a significant challenge for perceiving the modality-absent state in incomplete modality segmentation.In this work, we introduce a novel incomplete multi-modal segmentation framework called Modal-aware Visual Prompting (MAVP), which draws inspiration from the widely used pre-training and prompt adjustment protocol employed in natural language processing (NLP). In contrast to previous prompts that typically use textual network embeddings, we utilize embeddings as the prompts generated by a modality state classifier that focuses on the missing modality states. Additionally, we integrate modality state prompts into both the extraction stage of each modality and the modality fusion stage to facilitate intra/inter-modal adaptation. Our approach achieves state-of-the-art performance in various modality-incomplete scenarios compared to incomplete modality-specific solutions.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3228-3239
Open AccessModal-aware Visual Prompting for Incomplete Multi-modal Brain Tumor Segmentation
In the realm of medical imaging, distinct magnetic resonance imaging (MRI) modalities can provide complementary medical insights. However, it is not uncommon for one or more modalities to be absent due to image corruption, artifacts, acquisition protocols, allergies to contrast agents, or cost constraints, posing a significant challenge for perceiving the modality-absent state in incomplete modality segmentation.In this work, we introduce a novel incomplete multi-modal segmentation framework called Modal-aware Visual Prompting (MAVP), which draws inspiration from the widely used pre-training and prompt adjustment protocol employed in natural language processing (NLP). In contrast to previous prompts that typically use textual network embeddings, we utilize embeddings as the prompts generated by a modality state classifier that focuses on the missing modality states. Additionally, we integrate modality state prompts into both the extraction stage of each modality and the modality fusion stage to facilitate intra/inter-modal adaptation. Our approach achieves state-of-the-art performance in various modality-incomplete scenarios compared to incomplete modality-specific solutions.
- 18 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (5) , 4593-4605
Occlusion-Aware Plane-Constraints for Monocular 3D Object Detection
The task of 3D object detection poses a significant challenge for 3D scene understanding and is primarily employed in the fields of robot control and autonomous driving. Monocular-based 3D detection methods are more cost-effective and practical than stereo-based or LiDAR-based methods. Monocular image 3D detection methods have garnered considerable attention from researchers. However, the impact of occlusion scenarios of the objects on the keypoints prediction is often overlooked. To address this issue, the present paper proposes a novel 3D monocular object detection method named MonOAPC, which is equipped with occlusion-aware plane-constraints. This method can adaptively utilize partial keypoints to infer the plane location of the object based on the level of occlusion and highlights that the introduction of plane constraints is advantageous for the 3D detection task. First, the plane information of the object in 3D space is beneficial to optimize the keypoints regression, and considering that each plane holds different significance, an adaptive plane location inference module is proposed to enhance the keypoints location regression. Second, a novel co-depth estimation module is proposed to jointly estimate the object’s spatial location through various depth inference methods, thereby improving the generalization of the object depth estimation. Furthermore, the paper demonstrates that the accuracy of 3D object detection can be indirectly improved by introducing plane information to promote keypoints regression, and that plane information is effective for monocular 3D detection. The experimental outcomes show that the MonOAPC method can attain competitive results.
- 18 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (5) , 4593-4605
Occlusion-Aware Plane-Constraints for Monocular 3D Object Detection
The task of 3D object detection poses a significant challenge for 3D scene understanding and is primarily employed in the fields of robot control and autonomous driving. Monocular-based 3D detection methods are more cost-effective and practical than stereo-based or LiDAR-based methods. Monocular image 3D detection methods have garnered considerable attention from researchers. However, the impact of occlusion scenarios of the objects on the keypoints prediction is often overlooked. To address this issue, the present paper proposes a novel 3D monocular object detection method named MonOAPC, which is equipped with occlusion-aware plane-constraints. This method can adaptively utilize partial keypoints to infer the plane location of the object based on the level of occlusion and highlights that the introduction of plane constraints is advantageous for the 3D detection task. First, the plane information of the object in 3D space is beneficial to optimize the keypoints regression, and considering that each plane holds different significance, an adaptive plane location inference module is proposed to enhance the keypoints location regression. Second, a novel co-depth estimation module is proposed to jointly estimate the object’s spatial location through various depth inference methods, thereby improving the generalization of the object depth estimation. Furthermore, the paper demonstrates that the accuracy of 3D object detection can be indirectly improved by introducing plane information to promote keypoints regression, and that plane information is effective for monocular 3D detection. The experimental outcomes show that the MonOAPC method can attain competitive results.