Jiazhou Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiazhou Chen has a total of 97 co-authors. Here are the top co-authors by number of shared publications:
Yanghui Xu
Zhejiang University of Technology CHINA
4 shared publications- Xinding Zhu
Zhejiang University of Technology
3 shared publications Guangtao You
Zhejiang University of Technology, Hangzhou, China
2 shared publicationsJiayi Chen
Zhejiang University of Technology, Hangzhou, China
2 shared publicationsKeyu Huang
2 shared publications- Liegang Xia
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16316-16324
HyperSketch: Controllable Video Sketching in a Style Hyperspace
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16316-16324
Open AccessHyperSketch: Controllable Video Sketching in a Style Hyperspace
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11517-11525
TIBR4D: Tracing-Guided Iterative Boundary Refinement for Efficient 4D Gaussian Segmentation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11517-11525
Open AccessTIBR4D: Tracing-Guided Iterative Boundary Refinement for Efficient 4D Gaussian Segmentation
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12727-12735
TCFP-Sight: Ontology-Gated DAIE Reasoning for Auditable Appreciation of Traditional Chinese Figure Painting
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12727-12735
Open AccessTCFP-Sight: Ontology-Gated DAIE Reasoning for Auditable Appreciation of Traditional Chinese Figure Painting
- Open Access
- 8 July 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (14) , 2268
A Parcel-Level Asynchronous SpatioTemporal Framework for Cropping Pattern Classification in Fragmented Agricultural Landscapes
High-accuracy parcel-level agricultural mapping is fundamental to precision agriculture. However, in fragmented agricultural regions of the Yangtze River Delta, identifying cropping patterns at the parcel level faces two compounding challenges: asynchronous multi-source observations and mixed-pixel effects in small parcels. When historical archive records are used as training labels, inter-annual cropping pattern changes further introduce label noise that undermines model reliability. To address these challenges and the label noise issue, we propose PAST (Parcel-level Asynchronous SpatioTemporal), a parcel-level cropping pattern classification framework comprising three stages: K-Shape-based label quality control, parallel dual-branch classification, and decision-level fusion. PAST employs a dual-branch architecture: the temporal branch achieves interpolation-free cross-modal phenological fusion of Sentinel-1 and Sentinel-2 data, while the image branch extracts canopy texture features from 0.8 m high-resolution imagery to partially address mixed-pixel interference. Experiments in a typical fragmented agricultural region of the Yangtze River Delta demonstrate that PAST achieves an overall F1 score of 0.926 and a small-parcel F1 score of 0.906, outperforming mainstream time-series baselines. These results confirm that combining K-Shape label quality control at the data level with a dual-branch interference-robust architecture at the model level provides a complete integrated three-stage pipeline for fine-grained crop mapping under weakly supervised historical archive label conditions.
- 8 July 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (14) , 2268
Open AccessA Parcel-Level Asynchronous SpatioTemporal Framework for Cropping Pattern Classification in Fragmented Agricultural Landscapes
High-accuracy parcel-level agricultural mapping is fundamental to precision agriculture. However, in fragmented agricultural regions of the Yangtze River Delta, identifying cropping patterns at the parcel level faces two compounding challenges: asynchronous multi-source observations and mixed-pixel effects in small parcels. When historical archive records are used as training labels, inter-annual cropping pattern changes further introduce label noise that undermines model reliability. To address these challenges and the label noise issue, we propose PAST (Parcel-level Asynchronous SpatioTemporal), a parcel-level cropping pattern classification framework comprising three stages: K-Shape-based label quality control, parallel dual-branch classification, and decision-level fusion. PAST employs a dual-branch architecture: the temporal branch achieves interpolation-free cross-modal phenological fusion of Sentinel-1 and Sentinel-2 data, while the image branch extracts canopy texture features from 0.8 m high-resolution imagery to partially address mixed-pixel interference. Experiments in a typical fragmented agricultural region of the Yangtze River Delta demonstrate that PAST achieves an overall F1 score of 0.926 and a small-parcel F1 score of 0.906, outperforming mainstream time-series baselines. These results confirm that combining K-Shape label quality control at the data level with a dual-branch interference-robust architecture at the model level provides a complete integrated three-stage pipeline for fine-grained crop mapping under weakly supervised historical archive label conditions.
- 27 March 2026
- Published by Wiley in Computer Graphics Forum
- p. e70335
Vector sketch animation generation with differentialable motion trajectories
Sketching is a direct and inexpensive means of visual expression. Though image‐based sketching has been well studied, video‐based sketch animation generation is still very challenging due to the temporal coherence requirement. In this paper, we propose a novel end‐to‐end automatic generation approach for vector sketch animation. To solve the flickering issue, we introduce a Differentiable Motion Trajectory (DMT) representation that describes the frame‐wise movement of stroke control points using differentiable polynomial‐based trajectories. DMT enables global semantic gradient propagation across multiple frames, significantly improving the semantic consistency and temporal coherence, and producing high‐framerate output. DMT employs a Bernstein basis to balance the sensitivity of polynomial parameters, thus achieving more stable optimization. Instead of implicit fields, we introduce sparse track points for explicit spatial modeling, which improves efficiency and supports long‐duration video processing. Evaluations on DAVIS and LVOS datasets demonstrate the superiority of our approach over SOTA methods. Cross‐domain validation on 3D models and text‐to‐video data confirms the robustness and compatibility of our approach.
- 27 March 2026
- Published by Wiley in Computer Graphics Forum
- p. e70335
Vector sketch animation generation with differentialable motion trajectories
Sketching is a direct and inexpensive means of visual expression. Though image‐based sketching has been well studied, video‐based sketch animation generation is still very challenging due to the temporal coherence requirement. In this paper, we propose a novel end‐to‐end automatic generation approach for vector sketch animation. To solve the flickering issue, we introduce a Differentiable Motion Trajectory (DMT) representation that describes the frame‐wise movement of stroke control points using differentiable polynomial‐based trajectories. DMT enables global semantic gradient propagation across multiple frames, significantly improving the semantic consistency and temporal coherence, and producing high‐framerate output. DMT employs a Bernstein basis to balance the sensitivity of polynomial parameters, thus achieving more stable optimization. Instead of implicit fields, we introduce sparse track points for explicit spatial modeling, which improves efficiency and supports long‐duration video processing. Evaluations on DAVIS and LVOS datasets demonstrate the superiority of our approach over SOTA methods. Cross‐domain validation on 3D models and text‐to‐video data confirms the robustness and compatibility of our approach.
- 16 March 2026
- Published by Aerospace Information Research Institute, Chinese Academy of Sciences in Journal of Image and Graphics
- Vol. 31 (3) , 840-849
跨模态风格评分模型引导的矢量图风格迁移
目的矢量图风格迁移旨在将特定艺术风格应用于目标内容,同时保持其结构。然而,现有方法仅提取特定图像特征作为风格,导致迁移结果与人类视觉感知存在差距。为解决这一问题,提出了一种跨模态风格评分模型引导的矢量图风格迁移方法(vector graphics style transfer guided by cross-modal style evaluation models,CLIPVGStyler),旨在利用CLIP(contrastive language-image pre-training)模型的跨模态理解能力实现更符合感知的矢量图风格迁移。方法首先,将风格描述文本或风格参考图像作为输入,通过预训练的CLIP模型将其编码至共享语义信息的潜在空间,无需额外训练;然后,计算风格文本/图像编码与当前画面编码之间的余弦距离,构建风格损失,而内容损失则由像素域的L2距离和CLIP编码后的余弦距离共同组成;最后,通过迭代优化画面参数(路径控制点、颜色等)最小化联合损失函数(风格损失+内容损失),最终生成符合目标风格的矢量图。结果与先进的3种方法进行了风格迁移效率和风格质量比较,CLIP评分和用户调研的评分均更高,CLIP评分相比排名第2的模型高了0.003,用户调研的得分相比排名第2的模型高了0.36分,迭代速度排第2。实验结果表明,相比现有矢量图风格迁移方法,该方法生成的图像细节更精细,风格迁移效果更显著且符合人类视觉感知。此外,该方法在迭代优化速度上也展现出优势。结论本文提出的基于CLIP跨模态风格评分的CLIPVGStyler方法,有效融合了文本和图像的语义信息,成功解决了现有方法风格迁移结果与人类视觉感知不符的问题,显著提升了矢量图风格迁移的效果和效率。
- 16 March 2026
- Published by Aerospace Information Research Institute, Chinese Academy of Sciences in Journal of Image and Graphics
- Vol. 31 (3) , 840-849
跨模态风格评分模型引导的矢量图风格迁移
目的矢量图风格迁移旨在将特定艺术风格应用于目标内容,同时保持其结构。然而,现有方法仅提取特定图像特征作为风格,导致迁移结果与人类视觉感知存在差距。为解决这一问题,提出了一种跨模态风格评分模型引导的矢量图风格迁移方法(vector graphics style transfer guided by cross-modal style evaluation models,CLIPVGStyler),旨在利用CLIP(contrastive language-image pre-training)模型的跨模态理解能力实现更符合感知的矢量图风格迁移。方法首先,将风格描述文本或风格参考图像作为输入,通过预训练的CLIP模型将其编码至共享语义信息的潜在空间,无需额外训练;然后,计算风格文本/图像编码与当前画面编码之间的余弦距离,构建风格损失,而内容损失则由像素域的L2距离和CLIP编码后的余弦距离共同组成;最后,通过迭代优化画面参数(路径控制点、颜色等)最小化联合损失函数(风格损失+内容损失),最终生成符合目标风格的矢量图。结果与先进的3种方法进行了风格迁移效率和风格质量比较,CLIP评分和用户调研的评分均更高,CLIP评分相比排名第2的模型高了0.003,用户调研的得分相比排名第2的模型高了0.36分,迭代速度排第2。实验结果表明,相比现有矢量图风格迁移方法,该方法生成的图像细节更精细,风格迁移效果更显著且符合人类视觉感知。此外,该方法在迭代优化速度上也展现出优势。结论本文提出的基于CLIP跨模态风格评分的CLIPVGStyler方法,有效融合了文本和图像的语义信息,成功解决了现有方法风格迁移结果与人类视觉感知不符的问题,显著提升了矢量图风格迁移的效果和效率。
- 17 February 2026
- Published by Springer Nature in Journal of Visualization
- Vol. 29 (2) , 287-307
LSN-VA: a visual analysis system for ancient chinese literati social network
- 17 February 2026
- Published by Springer Nature in Journal of Visualization
- Vol. 29 (2) , 287-307
LSN-VA: a visual analysis system for ancient chinese literati social network
- Open Access
TIBR4D: Tracing-Guided Iterative Boundary Refinement for Efficient 4D Gaussian Segmentation
Object-level segmentation in dynamic 4D Gaussian scenes remains challenging due to complex motion, occlusions, and ambiguous boundaries. In this paper, we present an efficient learning-free 4D Gaussian segmentation framework that lifts video segmentation masks to 4D spaces, whose core is a two-stage iterative boundary refinement, TIBR4D. The first stage is an Iterative Gaussian Instance Tracing (IGIT) at the temporal segment level. It progressively refines Gaussian-to-instance probabilities through iterative tracing, and extracts corresponding Gaussian point clouds that better handle occlusions and preserve completeness of object structures compared to existing one-shot threshold-based methods. The second stage is a frame-wise Gaussian Rendering Range Control (RCC) via suppressing highly uncertain Gaussians near object boundaries while retaining their core contributions for more accurate boundaries. Furthermore, a temporal segmentation merging strategy is proposed for IGIT to balance identity consistency and dynamic awareness. Longer segments enforce stronger multi-frame constraints for stable identities, while shorter segments allow identity changes to be captured promptly. Experiments on HyperNeRF and Neu3D demonstrate that our method produces accurate object Gaussian point clouds with clearer boundaries and higher efficiency compared to SOTA methods.
Open AccessTIBR4D: Tracing-Guided Iterative Boundary Refinement for Efficient 4D Gaussian Segmentation
Object-level segmentation in dynamic 4D Gaussian scenes remains challenging due to complex motion, occlusions, and ambiguous boundaries. In this paper, we present an efficient learning-free 4D Gaussian segmentation framework that lifts video segmentation masks to 4D spaces, whose core is a two-stage iterative boundary refinement, TIBR4D. The first stage is an Iterative Gaussian Instance Tracing (IGIT) at the temporal segment level. It progressively refines Gaussian-to-instance probabilities through iterative tracing, and extracts corresponding Gaussian point clouds that better handle occlusions and preserve completeness of object structures compared to existing one-shot threshold-based methods. The second stage is a frame-wise Gaussian Rendering Range Control (RCC) via suppressing highly uncertain Gaussians near object boundaries while retaining their core contributions for more accurate boundaries. Furthermore, a temporal segmentation merging strategy is proposed for IGIT to balance identity consistency and dynamic awareness. Longer segments enforce stronger multi-frame constraints for stable identities, while shorter segments allow identity changes to be captured promptly. Experiments on HyperNeRF and Neu3D demonstrate that our method produces accurate object Gaussian point clouds with clearer boundaries and higher efficiency compared to SOTA methods.
- Open Access
BATISNet: Instance Segmentation of Tooth Point Clouds with Boundary Awareness
Accurate segmentation of the tooth point cloud is of great significance for diagnosis clinical assisting and treatment planning. Existing methods mostly employ semantic segmentation, focusing on the semantic feature between different types of teeth. However, due to the tightly packed structure of teeth, unclear boundaries, and the diversity of complex cases such as missing teeth, malposed teeth, semantic segmentation often struggles to achieve satisfactory results when dealing with complex dental cases. To address these issues, this paper propose BATISNet, a boundary-aware instance network for tooth point cloud segmentation. This network model consists of a feature extraction backbone and an instance segmentation module. It not only focuses on extracting the semantic features of different types of teeth but also learns the instance features of individual teeth. It helps achieve more robust and accurate tooth instance segmentation in complex clinical scenarios such as missing teeth and malposed teeth. Additionally, to further enhance the completeness and accuracy of tooth boundary segmentation, a boundary-aware loss function is designed to specifically supervise the boundary segmentation between instances. It mitigates effectively tooth adhesion and boundary ambiguity issues. Extensive experimental results show that BATISNet outperforms existing methods in tooth integrity segmentation, providing more reliable and detailed data support for practical clinical applications.
Open AccessBATISNet: Instance Segmentation of Tooth Point Clouds with Boundary Awareness
Accurate segmentation of the tooth point cloud is of great significance for diagnosis clinical assisting and treatment planning. Existing methods mostly employ semantic segmentation, focusing on the semantic feature between different types of teeth. However, due to the tightly packed structure of teeth, unclear boundaries, and the diversity of complex cases such as missing teeth, malposed teeth, semantic segmentation often struggles to achieve satisfactory results when dealing with complex dental cases. To address these issues, this paper propose BATISNet, a boundary-aware instance network for tooth point cloud segmentation. This network model consists of a feature extraction backbone and an instance segmentation module. It not only focuses on extracting the semantic features of different types of teeth but also learns the instance features of individual teeth. It helps achieve more robust and accurate tooth instance segmentation in complex clinical scenarios such as missing teeth and malposed teeth. Additionally, to further enhance the completeness and accuracy of tooth boundary segmentation, a boundary-aware loss function is designed to specifically supervise the boundary segmentation between instances. It mitigates effectively tooth adhesion and boundary ambiguity issues. Extensive experimental results show that BATISNet outperforms existing methods in tooth integrity segmentation, providing more reliable and detailed data support for practical clinical applications.
- Open Access
PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation
Existing text-driven 3D human motion editing methods have demonstrated significant progress, but are still difficult to precisely control over detailed, part-specific motions due to their global modeling nature. In this paper, we propose PartMotionEdit, a novel fine-grained motion editing framework that operates via part-level semantic modulation. The core of PartMotionEdit is a Part-aware Motion Modulation (PMM) module, which builds upon a predefined five-part body decomposition. PMM dynamically predicts time-varying modulation weights for each body part, enabling precise and interpretable editing of local motions. To guide the training of PMM, we also introduce a part-level similarity curve supervision mechanism enhanced with dual-layer normalization. This mechanism assists PMM in learning semantically consistent and editable distributions across all body parts. Furthermore, we design a Bidirectional Motion Interaction (BMI) module. It leverages bidirectional cross-modal attention to achieve more accurate semantic alignment between textual instructions and motion semantics. Extensive quantitative and qualitative evaluations on a well-known benchmark demonstrate that PartMotionEdit outperforms the state-of-the-art methods.
Open AccessPartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation
Existing text-driven 3D human motion editing methods have demonstrated significant progress, but are still difficult to precisely control over detailed, part-specific motions due to their global modeling nature. In this paper, we propose PartMotionEdit, a novel fine-grained motion editing framework that operates via part-level semantic modulation. The core of PartMotionEdit is a Part-aware Motion Modulation (PMM) module, which builds upon a predefined five-part body decomposition. PMM dynamically predicts time-varying modulation weights for each body part, enabling precise and interpretable editing of local motions. To guide the training of PMM, we also introduce a part-level similarity curve supervision mechanism enhanced with dual-layer normalization. This mechanism assists PMM in learning semantically consistent and editable distributions across all body parts. Furthermore, we design a Bidirectional Motion Interaction (BMI) module. It leverages bidirectional cross-modal attention to achieve more accurate semantic alignment between textual instructions and motion semantics. Extensive quantitative and qualitative evaluations on a well-known benchmark demonstrate that PartMotionEdit outperforms the state-of-the-art methods.