Jiachen Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiachen Li has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Gang Li
Qilu University of Technology (Shandong Academy of Sciences)
5 shared publications - Delong Han
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
4 shared publications - Mingle Zhou
Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Key Laboratory of Computing Power Network and Information Security Qilu University of Technology (Shandong Academy of Sciences) Jinan China
4 shared publications - Jin Wan
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
3 shared publications - Min Li
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
3 shared publications - Jinghui He
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong Province, China
2 shared publications
Latest Publications
- 6 October 2026
- Published by Wiley in Computer Graphics Forum
- p. e70522
UniGRe‐3D: Unified Geometric Reconstruction for Multi‐category 3D Anomaly Detection
3D anomaly detection has shown strong promise for industrial quality inspection. However, most existing methods rely on category‐specific training, resulting in high computational and storage costs as well as limited cross‐category generalization. Therefore, unified modeling is more attractive for practical deployment, especially in industrial scenarios where multiple product categories need to be inspected within the same pipeline. Nevertheless, unified modeling remains challenging, as it must jointly support cross‐category shared representation learning and accurate normal pattern reconstruction. To this end, we propose UniGRe‐3D, a unified geometric reconstruction framework for multi‐category 3D anomaly detection. Specifically, to learn unified representations across different categories, we design a geometry encoder that incorporates positional embeddings, multi‐scale feature interaction, and local‐global feature interaction, thereby improving the discriminative ability of the learned features for geometric anomalies. To enhance normal pattern reconstruction, we further introduce a reconstruction decoder that employs position‐guided decoding and hierarchical progressive reconstruction, thereby enabling more accurate localization of anomalous regions via reconstruction discrepancies. We conducted experiments on multiple datasets, in particular, UniGRe‐3D surpasses prior unified methods by 6.9% in object‐level AUROC and 4.0% in point‐level AUROC on Anomaly‐ShapeNet.
- 6 October 2026
- Published by Wiley in Computer Graphics Forum
- p. e70522
UniGRe‐3D: Unified Geometric Reconstruction for Multi‐category 3D Anomaly Detection
3D anomaly detection has shown strong promise for industrial quality inspection. However, most existing methods rely on category‐specific training, resulting in high computational and storage costs as well as limited cross‐category generalization. Therefore, unified modeling is more attractive for practical deployment, especially in industrial scenarios where multiple product categories need to be inspected within the same pipeline. Nevertheless, unified modeling remains challenging, as it must jointly support cross‐category shared representation learning and accurate normal pattern reconstruction. To this end, we propose UniGRe‐3D, a unified geometric reconstruction framework for multi‐category 3D anomaly detection. Specifically, to learn unified representations across different categories, we design a geometry encoder that incorporates positional embeddings, multi‐scale feature interaction, and local‐global feature interaction, thereby improving the discriminative ability of the learned features for geometric anomalies. To enhance normal pattern reconstruction, we further introduce a reconstruction decoder that employs position‐guided decoding and hierarchical progressive reconstruction, thereby enabling more accurate localization of anomalous regions via reconstruction discrepancies. We conducted experiments on multiple datasets, in particular, UniGRe‐3D surpasses prior unified methods by 6.9% in object‐level AUROC and 4.0% in point‐level AUROC on Anomaly‐ShapeNet.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5538-5546
Unsupervised Dual-Domain Memory Model for Time Series Anomaly Detection
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5538-5546
Open AccessUnsupervised Dual-Domain Memory Model for Time Series Anomaly Detection
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1023-1031
HGCF: Hierarchical Geometry-Color Fusion for Multimodal Industrial Anomaly Detection
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1023-1031
Open AccessHGCF: Hierarchical Geometry-Color Fusion for Multimodal Industrial Anomaly Detection
- 25 September 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 298
Enhancing mixture-of-experts model with prior knowledge for infrared and visible image fusion in complex degraded environments
- 25 September 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 298
Enhancing mixture-of-experts model with prior knowledge for infrared and visible image fusion in complex degraded environments
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (3) , 2854-2866
Multimodal Industrial Anomaly Detection via Geometric Prior
The purpose of multimodal industrial anomaly detection is to detect complex geometric shape defects such as subtle surface deformations and irregular contours that are difficult to detect in 2D-based methods. However, current multimodal industrial anomaly detection lacks the effective use of crucial geometric information like surface normal vectors and 3D shape topology, resulting in low detection accuracy. In this paper, we propose a novel Geometric Prior-based Anomaly Detection network (GPAD). Firstly, we propose a point cloud expert model to perform fine-grained geometric feature extraction, employing differential normal vector computation to enhance the geometric details of the extracted features and generate geometric prior. Secondly, we propose a two-stage fusion strategy to efficiently leverage the complementarity of multimodal data as well as the geometric prior inherent in 3D points. We further propose attention fusion and anomaly regions segmentation based on geometric prior, which enhance the model’s ability to perceive geometric defects. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the State-of-the-art (SOTA) methods in detection accuracy on both MVTec-3D AD and Eyecandies datasets.
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (3) , 2854-2866
Multimodal Industrial Anomaly Detection via Geometric Prior
The purpose of multimodal industrial anomaly detection is to detect complex geometric shape defects such as subtle surface deformations and irregular contours that are difficult to detect in 2D-based methods. However, current multimodal industrial anomaly detection lacks the effective use of crucial geometric information like surface normal vectors and 3D shape topology, resulting in low detection accuracy. In this paper, we propose a novel Geometric Prior-based Anomaly Detection network (GPAD). Firstly, we propose a point cloud expert model to perform fine-grained geometric feature extraction, employing differential normal vector computation to enhance the geometric details of the extracted features and generate geometric prior. Secondly, we propose a two-stage fusion strategy to efficiently leverage the complementarity of multimodal data as well as the geometric prior inherent in 3D points. We further propose attention fusion and anomaly regions segmentation based on geometric prior, which enhance the model’s ability to perceive geometric defects. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the State-of-the-art (SOTA) methods in detection accuracy on both MVTec-3D AD and Eyecandies datasets.
- 17 September 2025
- Published by Elsevier in Computers & Graphics
- Vol. 133
DualPhys-GS: Dual physically-guided 3D Gaussian splatting for underwater scene reconstruction
- 17 September 2025
- Published by Elsevier in Computers & Graphics
- Vol. 133
DualPhys-GS: Dual physically-guided 3D Gaussian splatting for underwater scene reconstruction
- 15 July 2025
- Published by Elsevier in Neurocomputing
- Vol. 650
PFRNet: Progressive multi-scale feature fusion and refinement for RGB-D salient object detection
- 15 July 2025
- Published by Elsevier in Neurocomputing
- Vol. 650
PFRNet: Progressive multi-scale feature fusion and refinement for RGB-D salient object detection
- 13 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (8) , 6274-6283
Few-Shot Photovoltaic Film Defect Detection With Contextual Ensemble Language-Image Multimodal Network
The automatic detection of defects in industrial photovoltaic film is crucial for ensuring the reliability of photovoltaic modules. Key challenges include limited defect samples, interclass feature similarities, and interference from complex backgrounds. Existing deep learning-based methods require large-scale datasets and focus solely on visual data, which limits their effectiveness in few-shot defect detection (FSDD). To address these challenges, we propose Contextual Ensemble Language-Image multimodal Network (CELIN), which enhances FSDD in photovoltaic films by incorporating textual information through prompt tuning. Unlike traditional language-image models that rely on single fixed text prompts, CELIN employs a position-aware context ensemble strategy to integrate position-specific prompt vectors, enabling the model to capture global contextual information and reduce background interference. In addition, a cross class mask method is introduced to differentiate between similar defect categories by blocking interclass interactions during attention computation, thereby minimizing misclassification. Extensive experiments on our own few-shot photovoltaic film defect dataset and various public benchmarks demonstrates that CELIN significantly outperforms existing methods.
- 13 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (8) , 6274-6283
Few-Shot Photovoltaic Film Defect Detection With Contextual Ensemble Language-Image Multimodal Network
The automatic detection of defects in industrial photovoltaic film is crucial for ensuring the reliability of photovoltaic modules. Key challenges include limited defect samples, interclass feature similarities, and interference from complex backgrounds. Existing deep learning-based methods require large-scale datasets and focus solely on visual data, which limits their effectiveness in few-shot defect detection (FSDD). To address these challenges, we propose Contextual Ensemble Language-Image multimodal Network (CELIN), which enhances FSDD in photovoltaic films by incorporating textual information through prompt tuning. Unlike traditional language-image models that rely on single fixed text prompts, CELIN employs a position-aware context ensemble strategy to integrate position-specific prompt vectors, enabling the model to capture global contextual information and reduce background interference. In addition, a cross class mask method is introduced to differentiate between similar defect categories by blocking interclass interactions during attention computation, thereby minimizing misclassification. Extensive experiments on our own few-shot photovoltaic film defect dataset and various public benchmarks demonstrates that CELIN significantly outperforms existing methods.
- 30 October 2023
- Published by Wiley in Computer Graphics Forum
- Vol. 42 (7)
3D Object Tracking for Rough Models
Visual monocular 6D pose tracking methods for textureless or weakly‐textured objects heavily rely on contour constraints established by the precise 3D model. However, precise models are not always available in reality, and rough models can potentially degrade tracking performance and impede the widespread usage of 3D object tracking. To address this new problem, we propose a novel tracking method that handles rough models. We reshape the rough contour through the probability map, which can avoid explicitly processing the 3D rough model itself. We further emphasize the inner region information of the object, where the points are sampled to provide color constrains. To sufficiently satisfy the assumption of small displacement between frames, the 2D translation of the object is pre‐searched for a better initial pose. Finally, we combine constraints from both the contour and inner region to optimize the object pose. Experimental results demonstrate that the proposed method achieves state‐of‐the‐art performance on both roughly and precisely modeled objects. Particularly for the highly rough model, the accuracy is significantly improved (40.4% v.s. 16.9%).
- 30 October 2023
- Published by Wiley in Computer Graphics Forum
- Vol. 42 (7)
3D Object Tracking for Rough Models
Visual monocular 6D pose tracking methods for textureless or weakly‐textured objects heavily rely on contour constraints established by the precise 3D model. However, precise models are not always available in reality, and rough models can potentially degrade tracking performance and impede the widespread usage of 3D object tracking. To address this new problem, we propose a novel tracking method that handles rough models. We reshape the rough contour through the probability map, which can avoid explicitly processing the 3D rough model itself. We further emphasize the inner region information of the object, where the points are sampled to provide color constrains. To sufficiently satisfy the assumption of small displacement between frames, the 2D translation of the object is pre‐searched for a better initial pose. Finally, we combine constraints from both the contour and inner region to optimize the object pose. Experimental results demonstrate that the proposed method achieves state‐of‐the‐art performance on both roughly and precisely modeled objects. Particularly for the highly rough model, the accuracy is significantly improved (40.4% v.s. 16.9%).
- 7 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1515-1520
An Improved Maximum Power Point Tracking Method Under Partial Shading Condition
Since the photovoltaic characteristic curve of photovoltaic panels presents multi-peak characteristics under partial shading conditions (PSC), the maximum power point tracking (MPPT) method is used in the photovoltaic power generation system to track the photovoltaic maximum power point (MPP) under PSC. An improved method was proposed to track the global maximum power point (GMPP) of photovoltaic (PV) in this paper. According to the optimal voltage distribution discipline, the initial position of particle swarm particles is introduced to normal uniform distribution for enhancing the global optimization ability of the method. According to the number of particle swarm iterations, this method adjusts the particle swarm optimization (PSO) learning factor and inertia weight synchronously during the optimization process. Finally, the performance of proposed method under uniform irradiance condition (UIC) and PSC are verified in the simulation model. The results demonstrate that this method have a rapid tracking speed, low sampling rate and steady-state performance.
- 7 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1515-1520
An Improved Maximum Power Point Tracking Method Under Partial Shading Condition
Since the photovoltaic characteristic curve of photovoltaic panels presents multi-peak characteristics under partial shading conditions (PSC), the maximum power point tracking (MPPT) method is used in the photovoltaic power generation system to track the photovoltaic maximum power point (MPP) under PSC. An improved method was proposed to track the global maximum power point (GMPP) of photovoltaic (PV) in this paper. According to the optimal voltage distribution discipline, the initial position of particle swarm particles is introduced to normal uniform distribution for enhancing the global optimization ability of the method. According to the number of particle swarm iterations, this method adjusts the particle swarm optimization (PSO) learning factor and inertia weight synchronously during the optimization process. Finally, the performance of proposed method under uniform irradiance condition (UIC) and PSC are verified in the simulation model. The results demonstrate that this method have a rapid tracking speed, low sampling rate and steady-state performance.