Juan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Juan Wang has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Bing Li
CASIA
11 shared publications - Weiming Hu
CASIA
11 shared publications - Zewen Chen
CASIA
7 shared publications - Chunfeng Yuan
Chinese Academy of Sciences
6 shared publications - Haina Qin
CASIA
3 shared publications Jian Guo
Beijing Union University
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12679-12687
GroDePrompt: Grounded Degradation Prompting for Retinal Fundus Image Enhancement
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12679-12687
Open AccessGroDePrompt: Grounded Degradation Prompting for Retinal Fundus Image Enhancement
- 7 August 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (8) , 385
Scalable Image Restoration and Enhancement towards Diverse Downstream Applications
- 7 August 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (8) , 385
Scalable Image Restoration and Enhancement towards Diverse Downstream Applications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 10713-10728
Towards Region-Level No-Reference Image Quality Assessment
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 10713-10728
Towards Region-Level No-Reference Image Quality Assessment
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (4) , 4114-4131
Reinforcement Learning-Based Sequential Parameter Tuning for Image Signal Processing
Hardware image signal processing (ISP) transforms RAW inputs into high-quality RGB images through a series of processing modules, each with numerous tunable parameters. Traditionally, these parameters are manually tuned by imaging experts, a time-consuming and subjective process. Recent deep learning approaches predict ISP parameters, but often treat the process as a black box and overlook the intrinsic relationships among ISP modules. To address these fundamental issues, we introduce a novel ISP parameter optimization model based on single-agent reinforcement learning (RL) (i.e., SARL-ISP), formulating the hardware ISP parameter tuning as a sequential optimization problem. During the optimization process, the agent updates ISP parameter tuning strategies for different tasks through interaction with the environment. In order to explore the influence of the sequential structure of hardware ISP modules and the coupling relationships among ISP parameters on the tuning process, we further propose a sequential ISP framework based on collaborative multi-agent RL (i.e., MARL-ISP). Specifically, the serialized parameter tuning module (SPTM) realistically simulates the process of manual prediction and module pipeline. Additionally, the feature selection module (FSM) facilitates the transmission and fusion of agent features, thereby selecting more appropriate feature inputs for downstream tasks. Extensive experiments across various tasks (e.g., object detection, instance segmentation) validate the effectiveness and efficiency of our models. Even with minimal training data, our models also outperform current state-of-the-art methods in both quantitative metrics and qualitative evaluations.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (4) , 4114-4131
Reinforcement Learning-Based Sequential Parameter Tuning for Image Signal Processing
Hardware image signal processing (ISP) transforms RAW inputs into high-quality RGB images through a series of processing modules, each with numerous tunable parameters. Traditionally, these parameters are manually tuned by imaging experts, a time-consuming and subjective process. Recent deep learning approaches predict ISP parameters, but often treat the process as a black box and overlook the intrinsic relationships among ISP modules. To address these fundamental issues, we introduce a novel ISP parameter optimization model based on single-agent reinforcement learning (RL) (i.e., SARL-ISP), formulating the hardware ISP parameter tuning as a sequential optimization problem. During the optimization process, the agent updates ISP parameter tuning strategies for different tasks through interaction with the environment. In order to explore the influence of the sequential structure of hardware ISP modules and the coupling relationships among ISP parameters on the tuning process, we further propose a sequential ISP framework based on collaborative multi-agent RL (i.e., MARL-ISP). Specifically, the serialized parameter tuning module (SPTM) realistically simulates the process of manual prediction and module pipeline. Additionally, the feature selection module (FSM) facilitates the transmission and fusion of agent features, thereby selecting more appropriate feature inputs for downstream tasks. Extensive experiments across various tasks (e.g., object detection, instance segmentation) validate the effectiveness and efficiency of our models. Even with minimal training data, our models also outperform current state-of-the-art methods in both quantitative metrics and qualitative evaluations.
- Open Access
- 1 July 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (13) , 2262
Loss Adaptive Curriculum Learning for Ground-Based Cloud Detection
While deep learning has advanced object detection through hierarchical feature learning and end-to-end optimization, conventional random sampling paradigms exhibit critical limitations in addressing hyperspectral ambiguity and low-distinguishability challenges in ground-based cloud detection. To overcome these limitations, we propose CurriCloud, a loss-adaptive curriculum framework featuring three key innovations: (1) real-time sample evaluation via Unified Batch Loss (UBL) for difficulty measurement, (2) stabilized training monitoring through a sliding window queue mechanism, and (3) progressive sample selection aligned with model capability using meteorology-guided phase-wise threshold scheduling. Extensive experiments on the ALPACLOUD benchmark demonstrate CurriCloud’s effectiveness across diverse architectures (YOLOv10s, SSD, and RT-DETR-R50), achieving consistent improvements of +3.1% to +11.4% mAP50 over both random sampling baselines and existing curriculum learning methods.
- 1 July 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (13) , 2262
Open AccessLoss Adaptive Curriculum Learning for Ground-Based Cloud Detection
While deep learning has advanced object detection through hierarchical feature learning and end-to-end optimization, conventional random sampling paradigms exhibit critical limitations in addressing hyperspectral ambiguity and low-distinguishability challenges in ground-based cloud detection. To overcome these limitations, we propose CurriCloud, a loss-adaptive curriculum framework featuring three key innovations: (1) real-time sample evaluation via Unified Batch Loss (UBL) for difficulty measurement, (2) stabilized training monitoring through a sliding window queue mechanism, and (3) progressive sample selection aligned with model capability using meteorology-guided phase-wise threshold scheduling. Extensive experiments on the ALPACLOUD benchmark demonstrate CurriCloud’s effectiveness across diverse architectures (YOLOv10s, SSD, and RT-DETR-R50), achieving consistent improvements of +3.1% to +11.4% mAP50 over both random sampling baselines and existing curriculum learning methods.
- 30 September 2024
- Published by Springer Nature
- p. 247-264
PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts
- 30 September 2024
- Published by Springer Nature
- p. 247-264
PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts
- Open Access
MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillation
With the rising demand for high-resolution (HR) images, No-Reference Image Quality Assessment (NR-IQA) gains more attention, as it can ecaluate image quality in real-time on mobile devices and enhance user experience. However, existing NR-IQA methods often resize or crop the HR images into small resolution, which leads to a loss of important details. And most of them are of high computational complexity, which hinders their application on mobile devices due to limited computational resources. To address these challenges, we propose MobileIQA, a novel approach that utilizes lightweight backbones to efficiently assess image quality while preserving image details through high-resolution input. MobileIQA employs the proposed multi-view attention learning (MAL) module to capture diverse opinions, simulating subjective opinions provided by different annotators during the dataset annotation process. The model uses a teacher model to guide the learning of a student model through knowledge distillation. This method significantly reduces computational complexity while maintaining high performance. Experiments demonstrate that MobileIQA outperforms novel IQA methods on evaluation metrics and computational efficiency. The code is available at https://github.com/chencn2020/MobileIQA.
Open AccessMobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillation
With the rising demand for high-resolution (HR) images, No-Reference Image Quality Assessment (NR-IQA) gains more attention, as it can ecaluate image quality in real-time on mobile devices and enhance user experience. However, existing NR-IQA methods often resize or crop the HR images into small resolution, which leads to a loss of important details. And most of them are of high computational complexity, which hinders their application on mobile devices due to limited computational resources. To address these challenges, we propose MobileIQA, a novel approach that utilizes lightweight backbones to efficiently assess image quality while preserving image details through high-resolution input. MobileIQA employs the proposed multi-view attention learning (MAL) module to capture diverse opinions, simulating subjective opinions provided by different annotators during the dataset annotation process. The model uses a teacher model to guide the learning of a student model through knowledge distillation. This method significantly reduces computational complexity while maintaining high performance. Experiments demonstrate that MobileIQA outperforms novel IQA methods on evaluation metrics and computational efficiency. The code is available at https://github.com/chencn2020/MobileIQA.
- Open Access
PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts
Due to the diversity of assessment requirements in various application scenarios for the IQA task, existing IQA methods struggle to directly adapt to these varied requirements after training. Thus, when facing new requirements, a typical approach is fine-tuning these models on datasets specifically created for those requirements. However, it is time-consuming to establish IQA datasets. In this work, we propose a Prompt-based IQA (PromptIQA) that can directly adapt to new requirements without fine-tuning after training. On one hand, it utilizes a short sequence of Image-Score Pairs (ISP) as prompts for targeted predictions, which significantly reduces the dependency on the data requirements. On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements. Experiments indicate that the PromptIQA outperforms SOTA methods with higher performance and better generalization. The code will be available.
Open AccessPromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts
Due to the diversity of assessment requirements in various application scenarios for the IQA task, existing IQA methods struggle to directly adapt to these varied requirements after training. Thus, when facing new requirements, a typical approach is fine-tuning these models on datasets specifically created for those requirements. However, it is time-consuming to establish IQA datasets. In this work, we propose a Prompt-based IQA (PromptIQA) that can directly adapt to new requirements without fine-tuning after training. On one hand, it utilizes a short sequence of Image-Score Pairs (ISP) as prompts for targeted predictions, which significantly reduces the dependency on the data requirements. On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements. Experiments indicate that the PromptIQA outperforms SOTA methods with higher performance and better generalization. The code will be available.
- 2 October 2023
- Published by Elsevier in Journal of English for Academic Purposes
- Vol. 66, 101304
Classroom gesture instruction on second language learners' academic presentations: Evidence from Chinese intermediate English learners
- 2 October 2023
- Published by Elsevier in Journal of English for Academic Purposes
- Vol. 66, 101304
Classroom gesture instruction on second language learners' academic presentations: Evidence from Chinese intermediate English learners