Fan Tang

Mr. Fan Tang

School of Cyberspace Security and Computer, Hebei University, Baoding, Hebei, China
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
22 March 2023 in Electronics
Verified
Journal Article
Open access
PDF file
FTFan Tang
Fan Tang
Fang YangFang Yang
Fang Yang
XTXianqing Tian
Xianqing Tian
In the research field of small object detection, most object detectors have been successfully used for pedestrian detection, face recognition, lost and found, and automatic driving, among other applications, and have achieved good results. However, when general object detectors encounter challenging low-resolution images from the TinyPerson dataset, they will produce undesirable detection results because of the dense occlusion between people and different body poses. In order to solve these problems, this paper proposes a tiny object detection method TOD-YOLOv7 based on YOLOv7.First, this paper presents a reconstruction of the YOLOv7 network by adding a tiny object detection layer to enhance its detection ability. Then, we use the recursive gated convolution module to realize the interaction with the higher-order space to accelerate the model initialization process and reduce the reasoning time. Secondly, this paper proposes the integration of a coordinate attention mechanism into the YOLOv7 feature extraction network to strengthen the pedestrian object information and weaken the background information.Additionally, we leverage data augmentation techniques to improve the representation learning of the algorithm. The results show that compared with the baseline model YOLOv7, the detection accuracy of this model on the TinyPerson dataset is improved from 7.1% to 9.5%, and the detection speed reaches 208 frames per second (FPS). The algorithm of this paper is shown to achieve better detection results for tiny object detection.

25 September 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
XTXianqing Tian
Xianqing Tian
Fang YangFang Yang
Fang Yang
FTFan Tang
Fan Tang
Stylish fonts are widely utilized in social networks, driving research interest in stylish Chinese font generation. Most existing methods for generating Chinese characters rely on GAN-based deep learning approaches. However, persistent issues of mode collapse and missing structure in CycleGAN-generated results make font generation a formidable task. This paper introduces a unique semi-supervised model specifically designed for generating stylish Chinese fonts. By incorporating a small amount of paired data and stroke encoding as information into CycleGAN, our model effectively captures both the global structural features and local characteristics of Chinese characters. Additionally, an attention module has been added and refined to improve the connection between strokes and character structures. To enhance the model’s understanding of the global structure of Chinese characters and stroke encoding reconstruction, two loss functions are included. The integration of these components successfully alleviates mode collapse and structural errors. To assess the effectiveness of our approach, comprehensive visual and quantitative assessments are conducted, comparing our method with benchmark approaches on six diverse datasets. The results clearly demonstrate the superior performance of our method in generating stylish Chinese fonts.

25 May 2026 in Research Square
Verified
Preprint
Open access
PDF file
FTFan Tang
Fan Tang
SLSiyuan Li
Siyuan Li
Real-world video post-processing often involves multiple high-frequency tasks, including video super-resolution, occlusion removal and repair, and instruction-driven semantic editing. However, most existing methods are designed for a single scenario, or rely on frame-by-frame processing and multi-model cascades, which easily lead to task interference, cross-frame flickering, and high deployment cost. To address these issues, we propose LTX-Insight, a unified framework for video restoration and semantic editing, which jointly models multiple video post-processing tasks on a shared video diffusion backbone. Specifically, TADA (Task-Aware Decoupled Adapter) introduces a task-aware branch-separated adaptation mechanism with a weak decoupling constraint to regulate structure restoration and texture-semantic editing at different layers, thereby alleviating semantic interference under shared multi-task parameters. FGLC (Flow-Guided Latent Consistency) introduces explicit temporal consistency constraints in latent space by combining optical-flow alignment and cross-frame attention bias, reducing flickering while improving the stability of motion regions and occlusion completion. PMTR (Progressive Multi-Task Routing) enhances convergence stability and generalization under joint multi-task training through progressive curriculum learning and collaborative task routing. We conduct systematic experiments and ablation studies on three tasks, namely video super-resolution, occlusion removal, and semantic editing, validating the effectiveness and complementarity of all modules. Experimental results show that our method consistently improves editability, detail preservation, and visual fidelity over representative baselines.

9 April 2026 in Research Square
Verified
Preprint
Open access
PDF file
FTFan Tang
Fan Tang
SLSiyuan Li
Siyuan Li
Instruction-based image editing has advanced substantially with the emergence of Diffusion Transformers (DiTs). However, a central challenge remains unresolved: how to accurately execute complex editing instructions while preserving the structural consistency and visual quality of the source image. Existing methods are primarily limited by three factors: noisy and imbalanced training data, insufficient structural supervision, and inadequate alignment with human aesthetic preferences. To address these issues, we propose Qwen-Edit+, a unified framework for image editing. Specifically, we first introduce Semantic-Consistency Aware Filtering (SCAF) and Distribution-Adaptive Sampling (DAS) to construct high-quality and category-balanced training data. We then propose a VLM-aware Consistency Loss (VCL), which exploits the hierarchical hidden states of Qwen2.5-VL to provide deep semantic and structural supervision. Finally, we incorporate Aesthetic Preference Distillation (APD) to further improve visual harmony and perceptual quality. In comparative experiments, our method achieved a CLIP Score of 0.347, an LPIPS of 0.219, a PSNR of 25.63, and an Aesthetic Score of 6.31 on Qwen-Consistent-Edit-1.2K, outperforming representative baselines in editability, structural fidelity, and visual quality.