Tongkun Guan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tongkun Guan has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Wei Shen
Shanghai Jiao Tong University
7 shared publications Xiaokang Yang
Shanghai Jiao Tong University
5 shared publicationsChen Duan
3 shared publicationsKai Zhou
3 shared publications- Xiaokang Yang
Shanghai Jiao Tong University
3 shared publications Boming Chen
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 631-639
Video * Bench: Benchmarking Fine-grained Video Perception with "Think with Videos"
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 631-639
Open AccessVideo * Bench: Benchmarking Fine-grained Video Perception with "Think with Videos"
- 3 October 2026
- Published by Springer Nature
- p. 712-730
ViTexQA: A Multi-frame Temporal Perception Dataset for Video Text Question Answering
- 3 October 2026
- Published by Springer Nature
- p. 712-730
ViTexQA: A Multi-frame Temporal Perception Dataset for Video Text Question Answering
- 18 September 2026
- Published by Springer Nature
- p. 515-534
AdaThinking- : One-Token Entropy Regulation for Adaptive Thinking
- 18 September 2026
- Published by Springer Nature
- p. 515-534
AdaThinking- : One-Token Entropy Regulation for Adaptive Thinking
- 11 September 2026
- Published by Springer Nature
- p. 669-687
LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement
- 11 September 2026
- Published by Springer Nature
- p. 669-687
LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 9661-9674
BPE-Level Visual-Textual Alignment for Multi-Scene Text Retrieval
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 9661-9674
BPE-Level Visual-Textual Alignment for Multi-Scene Text Retrieval
- Open Access
Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review
The recent emergence of Multi-modal Large Language Models (MLLMs) has introduced a new dimension to the Text-rich Image Understanding (TIU) field, with models demonstrating impressive and inspiring performance. However, their rapid evolution and widespread adoption have made it increasingly challenging to keep up with the latest advancements. To address this, we present a systematic and comprehensive survey to facilitate further research on TIU MLLMs. Initially, we outline the timeline, architecture, and pipeline of nearly all TIU MLLMs. Then, we review the performance of selected models on mainstream benchmarks. Finally, we explore promising directions, challenges, and limitations within the field.
Open AccessMultimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review
The recent emergence of Multi-modal Large Language Models (MLLMs) has introduced a new dimension to the Text-rich Image Understanding (TIU) field, with models demonstrating impressive and inspiring performance. However, their rapid evolution and widespread adoption have made it increasingly challenging to keep up with the latest advancements. To address this, we present a systematic and comprehensive survey to facilitate further research on TIU MLLMs. Initially, we outline the timeline, architecture, and pipeline of nearly all TIU MLLMs. Then, we review the performance of selected models on mainstream benchmarks. Finally, we explore promising directions, challenges, and limitations within the field.
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (5) , 3546-3562
CCDPlus: Towards Accurate Character to Character Distillation for Text Recognition
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.
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (5) , 3546-3562
CCDPlus: Towards Accurate Character to Character Distillation for Text Recognition
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.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 19941-19958
Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review
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.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 19941-19958
Open AccessMultimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review
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.
- 30 September 2024
- Published by Springer Nature
- p. 130-147
PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer
- 30 September 2024
- Published by Springer Nature
- p. 130-147
PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer