Tongkun Guan

Tongkun Guan

Auto-generated profile, based on publicly available information

Tongkun Guan

Shanghai Jiao Tong University

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
2 March 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
TGTongkun Guan
Tongkun Guan
CGChaochen Gu
Chaochen Gu
CLChangsheng Lu
Changsheng Lu
JTJingzheng Tu
Jingzheng Tu
QFQi Feng
Qi Feng
XGXinping Guan
Xinping Guan
Detecting the marking characters of industrial metal parts remains challenging due to low visual contrast, uneven illumination, corroded surfaces, and cluttered background of metal part images. Affected by these factors, bounding boxes generated by most existing methods could not locate low-contrast text areas very well. In this paper, we propose a refined feature-attentive network (RFN) to solve the inaccurate localization problem. Specifically, we first design a parallel feature integration mechanism to construct an adaptive feature representation from multi-resolution features, which enhances the perception of multi-scale texts at each scale-specific level to generate a high-quality attention map. Then, an attentive proposal refinement module is developed by the attention map to rectify the location deviation of candidate boxes. Besides, a re-scoring mechanism is designed to select text boxes with the best rectified location. To promote the research towards industrial scene text detection, we contribute two industrial scene text datasets, including a total of 102156 images and 1948809 text instances with various character structures and metal parts. Extensive experiments on our dataset and four public datasets demonstrate that our proposed method achieves the state-of-the-art performance. Both code and dataset are available at: https://github.com/TongkunGuan/RFN .

30 September 2024
Verified
Book Chapter
Closed access
PDF file
TGTongkun Guan
Tongkun Guan
CLChengyu Lin
Chengyu Lin
WSWei Shen
Wei Shen
XYXiaokang Yang
Xiaokang Yang

30 September 2024
Verified
Book Chapter
Closed access
PDF file
TGTongkun Guan
Tongkun Guan
WSWei Shen
Wei Shen
XYXue Yang
Xue Yang
XWXuehui Wang
Xuehui Wang
XYXiaokang Yang
Xiaokang Yang

13 February 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
TGTongkun Guan
Tongkun Guan
WSWei Shen
Wei Shen
XYXiaokang Yang
Xiaokang Yang
Existing scene text recognition methods leverage large-scale labeled synthetic data (LSD) to reduce reliance on labor-intensive annotation tasks and improve recognition capability in real-world scenarios. However, the emergence of a synth-to-real domain gap still limits their efficiency and robustness. Consequently, harvesting the meaningful intrinsic qualities of unlabeled real data (URD) is of great importance, given the prevalence of text-laden images. Toward the target, recent efforts have focused on pre-training on URD through sequence-to-sequence self-supervised learning, followed by fine-tuning on LSD via supervised learning. Nevertheless, they encounter three important issues: coarse representation learning units, inflexible data augmentation, and an emerging real-to-synth domain drift. To overcome these challenges, we propose CCDPlus, an accurate character-to-character distillation method for scene text recognition with a joint supervised and self-supervised learning framework. Specifically, tailored for text images, CCDPlus delineates the fine-grained character structures on URD as representation units by transferring knowledge learned from LSD online. Without requiring extra bounding box or pixel-level annotations, this process allows CCDPlus to enable character-to-character distillation flexibly with versatile data augmentation, which effectively extracts general real-world character-level feature representations. Meanwhile, the unified framework combines self-supervised learning on URD with supervised learning on LSD, effectively solving the domain inconsistency and enhancing the recognition performance. Extensive experiments demonstrate that CCDPlus outperforms previous state-of-the-art (SOTA) supervised, semi-supervised, and self-supervised methods by an average of 1.8%, 0.6%, and 1.1% on standard datasets, respectively. Additionally, it achieves a 6.1% improvement on the more challenging Union14M-L dataset.

1 January 2025
Verified
Conference Paper
Open access
PDF file
PFPei Fu
Pei Fu
TGTongkun Guan
Tongkun Guan
ZWZining Wang
Zining Wang
ZGZhentao Guo
Zhentao Guo
CDChen Duan
Chen Duan
JLJunfeng Luo
Junfeng Luo
Pei Fu, Tongkun Guan, Zining Wang, Zhentao Guo, Chen Duan, Hao Sun, Boming Chen, Qianyi Jiang, Jiayao Ma, Kai Zhou, Junfeng Luo. Findings of the Association for Computational Linguistics: ACL 2025. 2025.

9 April 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
CGChanghao Guo
Changhao Guo
MLMin Liu
Min Liu
TGTongkun Guan
Tongkun Guan
WCWeixun Chen
Weixun Chen
HWHe Wen
He Wen
YWYaonan Wang
Yaonan Wang
Morphology reconstruction of neurons from 3-D microscopic images is essential to neuroscience research. However, many reconstructions may contain errors and ambiguities because of the crossover neuronal fibers. In this article, an automatic algorithm is proposed for the detection and separation of crossover structures and is applied to neuron tracing for improving the neuron reconstruction results. First, a spherical-patches extraction (SPE)-Net is employed to detect the 3-D neuron crossover points and locate the crossover structures in neuron volumetric images. Second, a multiscale upgraded ray-shooting model (MSURS) is proposed to obtain robust results at different scales with high confidence and is employed to extract the crossover neuronal structure features. Then, a crossover structure separation (CSS) method is developed to eliminate the false connections of crossover structures and generate deformed separated neuronal fibers based on the extracted features to replace the original neurites signals. Experiments demonstrate that the SPE-Net for crossover point detection achieves average precision and recall rates of 73.89% and 79.66%, respectively, and demonstrate the proposed CSS method can improve 20.46% the performance of the reconstructions on average. The results confirm that the proposed method can effectively improve the neuron tracing results in volumetric images.