Jianing Sun

Dr. Jianing Sun


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 December 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
JLJun Liu
Jun Liu
RLRyan Wen Liu
Ryan Wen Liu
JSJianing Sun
Jianing Sun
TZTieyong ZENG
Tieyong ZENG
Scene recovery is a fundamental imaging task with several practical applications, including video surveillance and autonomous vehicles, etc. In this paper, we provide a new real-time scene recovery framework to restore degraded images under different weather/imaging conditions, such as underwater, sand dust and haze. A degraded image can actually be seen as a superimposition of a clear image with the same color imaging environment (underwater, sand or haze, etc.). Mathematically, we can introduce a rank-one matrix to characterize this phenomenon, i.e., rank-one prior (ROP). Using the prior, a direct method with the complexity $O(N)$ is derived for real-time recovery. For general cases, we develop ROP $^+$ to further improve the recovery performance. Comprehensive experiments of the scene recovery illustrate that our method outperforms competitively several state-of-the-art imaging methods in terms of efficiency and robustness.

8 May 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
XYXifan Yi
Xifan Yi
JSJianing Sun
Jianing Sun
XWXiaopeng Wu
Xiaopeng Wu
The level of difficulty of mathematical test items is a critical aspect for evaluating test quality and educational outcomes. Accurately predicting item difficulty during test creation is thus significantly important for producing effective test papers. This study used more than ten years of content and score data from China’s Henan Provincial College Entrance Examination in Mathematics as an evaluation criterion for test difficulty, and all data were obtained from the Henan Provincial Department of Education. Based on the framework established by the National Center for Education Statistics (NCES) for test item assessment methodology, this paper proposes a new framework containing eight features considering the uniqueness of mathematics. Next, this paper proposes an XGBoost-based SHAP model for analyzing the difficulty of mathematics tests. By coupling the XGBoost method with the SHAP method, the model not only evaluates the difficulty of mathematics tests but also analyzes the contribution of specific features to item difficulty, thereby increasing transparency and mitigating the “black box” nature of machine learning models. The model has a high prediction accuracy of 0.99 for the training set and 0.806 for the test set. With the model, we found that parameter-level features and reasoning-level features are significant factors influencing the difficulty of subjective items in the exam. In addition, we divided senior secondary mathematics knowledge into nine units based on Chinese curriculum standards and found significant differences in the distribution of the eight features across these different knowledge units, which can help teachers place different emphasis on different units during the teaching process. In summary, our proposed approach significantly improves the accuracy of item difficulty prediction, which is crucial for intelligent educational applications such as knowledge tracking, automatic test item generation, and intelligent paper generation. These results provide tools that are better aligned with and responsive to students’ learning needs, thus effectively informing educational practice.

30 June 2023 in Science Advances
Verified
Journal Article
Open access
FZFeiran Zhang
Feiran Zhang
JXJiajun Xu
Jiajun Xu
YYYing Yue
Ying Yue
YWYajun Wang
Yajun Wang
JSJianing Sun
Jianing Sun
BYBai Yang
Bai Yang
Tissue diagnosis is important during surgical excision of solid tumors for margin evaluation. Conventional histopathologic methods rely heavily on image-based visual diagnosis by specialized pathologists, which can be time-consuming and subjective. We report a three-dimensional (3D) histological electrophoresis system for rapid labeling and separation of the proteins within tissue sections, providing a more precise assessment of tumor-positive margin in surgically resected tissues. The 3D histological electrophoresis system uses a tumor-seeking dye labeling strategy to visualize the distribution of tumor-specific proteins within sections and a tumor finder that automatically predicts the tumor contour. We successfully demonstrated the system’s capability to predict the tumor contours from five murine xenograft models and distinguish the tumor-invaded region of sentinel lymph nodes. Specifically, we used the system to accurately assess tumor-positive margins from 14 patients with cancer. Our 3D histological electrophoresis system serves as an intraoperative tissue assessment technology for more accurate and automatic pathologic diagnosis.

14 October 2025 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
PCPengyu Chen
Pengyu Chen
LCLibo Cheng
Libo Cheng
Liang-Jian DengLiang-Jian Deng
Liang-Jian Deng
JLJun Liu
Jun Liu
JSJianing Sun
Jianing Sun
TZTieyong Zeng
Tieyong Zeng
Multispectral pansharpening aims to produce high-resolution multispectral (HRMS) images by fusing a low-resolution multispectral (LRMS) image with a corresponding panchromatic (PAN) image. While the rise of diffusion models has marked significant progress in this field, existing methods often struggle by directly feeding the PAN and LRMS images into the network, an operation that fails to provide sufficient guidance for generating high-quality HRMS images. To tackle this problem, we propose a novel multi-stage diffusion-driven model for pansharpening (MSDP) in this paper. Our method involves a three-stage conditional fusion mechanism where effective cross-modal prior fusion is achieved through a novel sparse attention module, with dynamic integration of PAN image shearlet coefficients to achieve multi-scale frequency enhancement. These conditions are injected into the model network via two modulation modules, ensuring the exceptional preservation of both spatial sharpness and spectral fidelity. Furthermore, a lightweight physical model is developed to accelerate the training process. Experimental evaluations on pansharpening datasets show that our proposed method achieves superior results compared to recent state-of-the-art (SOTA) techniques, highlighting its potential to advance the field of pansharpening.

11 July 2024 in Information Sciences
Verified
Journal Article
Closed access
YWYumo Wu
Yumo Wu
JSJianing Sun
Jianing Sun
JYJunping Yin
Junping Yin

12 February 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
PCPengyu Chen
Pengyu Chen
ZCZihan Cao
Zihan Cao
LDLiang-Jian Deng
Liang-Jian Deng
JLJun Liu
Jun Liu
JSJianing Sun
Jianing Sun
TZTieyong Zeng
Tieyong Zeng
Multispectral pansharpening aims to produce high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) images with a panchromatic (PAN) image. Although recent Transformer-based generative models have shown strong performance in multispectral pansharpening, they face two parallel challenges. On one hand, the neglect of inherent token redundancy and reliance on black-box fusion impede effective spectral–spatial disentanglement. On the other hand, the heavy computational burden of iterative sampling makes fast inference unattainable. To address these limitations, we introduce TOPan, a fast pansharpening method inspired by the orthogonal projection.TOPan utilizes a MeanFlow-accelerated framework that characterizes the velocity flow field using average velocity, enabling efficient one-step generation while preserving high reconstruction quality. Specifically, TOPan employs a novel token-wise orthogonal projector (TOP), which is a mathematically driven module. It exploits token redundancy and the low-rank structure of the channel space to explicitly construct spectral and spatial subspaces for disentangling shared and modality-specific representations. Furthermore, we leverage this disentangled representation through a highly efficient alternating injection scheme and incorporate a cross-channel dispersive loss to enhance generalization and training stability. Extensive experiments demonstrate that TOPan achieves superior performance, surpassing state-of-the-art (SOTA) methods in both reconstruction quality and inference efficiency.