FreqFLD: Towards All-in-One Facial Landmark Detection via Frequency Modulation
本文提出FreqFLD，通过频率调制方法解决面部标志点检测中的跨数据集泛化问题，实现全合一的面部标志点检测。
0 citationsRead paper
Selected work
Representative Papers
Discrete asset pricing under transaction costs and model uncertainty with and without short-sale constraints
本文研究了在存在买卖差价和模型不确定性的情况下，资产定价问题，并探讨了有无卖空限制下的单期及多期市场中无套利条件与一致价格体系的关系。
0 citationsRead paper
Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
To address the high computational complexity—O(an³), where a=1 for linear and a=27 for nonlinear ODEs—of kernel-based methods (e.g., LS-SVM) in solving ordinary differential equations (ODEs), this paper proposes a Nyström-accelerated primal-space LS-SVM framework. The core method constructs, for the first time, a one-dimensional temporal domain-to-m-dimensional explicit feature-space Nyström mapping and its analytical derivatives, enabling direct embedding of differential constraints into the primal space. This reduces computational complexity from O(n³) to O(m³), with m ≪ n. The approach achieves both high accuracy and scalability: on 16 benchmark ODEs, it accelerates computation by 10–6,000× over classical LS-SVM and physics-informed neural networks (PINNs), attains errors <0.13%, improves RMSE by up to 72%, and supports solutions with tens of thousands of time steps.
0 citationsRead paper
TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition
To address the challenges of recognizing diverse Chinese and English license plates under open-world conditions—characterized by complex imaging environments and scarce annotated bilingual plate data—this paper proposes a lightweight vision-language collaborative framework. Methodologically, it integrates a lightweight Vision Transformer (ViT) visual encoder with a sequence transcription decoder, and introduces a novel perspective correction module jointly supervised by corner-point regression and viewpoint classification to enhance robustness and interpretability. Additionally, synthetic data augmentation, texture-mapping-based realism enhancement, and a coordinate-regression auxiliary network are incorporated to reduce annotation dependency. Evaluated on the CCPD dataset, the framework achieves 99.34% recognition accuracy under coarse localization interference, 99.58% under precise localization, and 98.70% for bilingual plates, operating at 167 FPS—demonstrating both high accuracy and practical efficiency.
0 citationsRead paper
LPTR-AFLNet: Lightweight Integrated Chinese License Plate Rectification and Recognition Network
To address perspective distortion induced by arbitrary camera angles, difficulties in rectifying single- and double-line Chinese license plates, and computational constraints on edge devices, this paper proposes a lightweight end-to-end network jointly optimizing geometric rectification and recognition. The method integrates a differentiable Perspective Transformation Rectification (PTR) module directly into the recognition backbone, enabling weakly supervised geometric correction guided solely by recognition outputs. It further incorporates an enhanced AFLNet architecture, a strengthened channel-spatial attention mechanism, and a weighted Focal Loss to improve discrimination among visually similar Chinese characters (e.g., “川”/“川”, “京”/“津”). Evaluated on standard benchmarks, the model achieves state-of-the-art accuracy while processing each frame in under 10 ms on GPU hardware—demonstrating both high precision and efficiency for real-time deployment on resource-constrained platforms.
0 citationsRead paper
Recent publications
Latest Papers
FreqFLD: Towards All-in-One Facial Landmark Detection via Frequency Modulation
本文提出FreqFLD，通过频率调制方法解决面部标志点检测中的跨数据集泛化问题，实现全合一的面部标志点检测。
0 citationsRead paper
Discrete asset pricing under transaction costs and model uncertainty with and without short-sale constraints
本文研究了在存在买卖差价和模型不确定性的情况下，资产定价问题，并探讨了有无卖空限制下的单期及多期市场中无套利条件与一致价格体系的关系。
0 citationsRead paper
Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
To address the high computational complexity—O(an³), where a=1 for linear and a=27 for nonlinear ODEs—of kernel-based methods (e.g., LS-SVM) in solving ordinary differential equations (ODEs), this paper proposes a Nyström-accelerated primal-space LS-SVM framework. The core method constructs, for the first time, a one-dimensional temporal domain-to-m-dimensional explicit feature-space Nyström mapping and its analytical derivatives, enabling direct embedding of differential constraints into the primal space. This reduces computational complexity from O(n³) to O(m³), with m ≪ n. The approach achieves both high accuracy and scalability: on 16 benchmark ODEs, it accelerates computation by 10–6,000× over classical LS-SVM and physics-informed neural networks (PINNs), attains errors <0.13%, improves RMSE by up to 72%, and supports solutions with tens of thousands of time steps.
0 citationsRead paper
TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition
To address the challenges of recognizing diverse Chinese and English license plates under open-world conditions—characterized by complex imaging environments and scarce annotated bilingual plate data—this paper proposes a lightweight vision-language collaborative framework. Methodologically, it integrates a lightweight Vision Transformer (ViT) visual encoder with a sequence transcription decoder, and introduces a novel perspective correction module jointly supervised by corner-point regression and viewpoint classification to enhance robustness and interpretability. Additionally, synthetic data augmentation, texture-mapping-based realism enhancement, and a coordinate-regression auxiliary network are incorporated to reduce annotation dependency. Evaluated on the CCPD dataset, the framework achieves 99.34% recognition accuracy under coarse localization interference, 99.58% under precise localization, and 98.70% for bilingual plates, operating at 167 FPS—demonstrating both high accuracy and practical efficiency.
0 citationsRead paper
LPTR-AFLNet: Lightweight Integrated Chinese License Plate Rectification and Recognition Network
To address perspective distortion induced by arbitrary camera angles, difficulties in rectifying single- and double-line Chinese license plates, and computational constraints on edge devices, this paper proposes a lightweight end-to-end network jointly optimizing geometric rectification and recognition. The method integrates a differentiable Perspective Transformation Rectification (PTR) module directly into the recognition backbone, enabling weakly supervised geometric correction guided solely by recognition outputs. It further incorporates an enhanced AFLNet architecture, a strengthened channel-spatial attention mechanism, and a weighted Focal Loss to improve discrimination among visually similar Chinese characters (e.g., “川”/“川”, “京”/“津”). Evaluated on standard benchmarks, the model achieves state-of-the-art accuracy while processing each frame in under 10 ms on GPU hardware—demonstrating both high precision and efficiency for real-time deployment on resource-constrained platforms.
0 citationsRead paper