Dezhi Peng

64 papers A* 14A 2B 3Journal 37Unranked 8
YearRankTypeTitle / Venue / Authors
2026 A* conf
URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding.
AAAI
Yongxin Shi, Jiapeng Wang, Zeyu Shan, Dezhi Peng, Zening Lin, Lianwen Jin
2025 J jnl
Beyond Token Compression: A Training-Free Reduction Framework for Efficient Visual Processing in MLLMs.
CoRR
Hongliang Li, Jiaxin Zhang, Wenhui Liao, Dezhi Peng, Kai Ding, Lianwen Jin
2025 J jnl
CTRNet++: Dual-Path Learning with Local-Global Context Modeling for Scene Text Removal.
ACM Trans. Multim. Comput. Commun. Appl.
Chongyu Liu, Dezhi Peng, Yuliang Liu, Lianwen Jin
2025 J jnl
EGO-LM: An efficient, generic, and out-of-the-box language model for handwritten text recognition.
Pattern Recognit.
Hongliang Li, Dezhi Peng, Lianwen Jin
2025 J jnl
Enhancing document dewarping evaluation: A new metric with improved accuracy and efficiency.
Pattern Recognit. Lett.
Jiaxin Zhang, Peirong Zhang, Dezhi Peng, Haowei Xu, Lianwen Jin
2025 J jnl
HierCode: A lightweight hierarchical codebook for zero-shot Chinese text recognition.
Pattern Recognit.
Yuyi Zhang, Yuanzhi Zhu, Dezhi Peng, Peirong Zhang, Zhenhua Yang, Zhibo Yang, Cong Yao, Lianwen Jin
2025 J jnl
OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning.
CoRR
Mingxin Huang, Yongxin Shi, Dezhi Peng, Songxuan Lai, Zecheng Xie, Lianwen Jin
2025 A* conf
Predicting the Original Appearance of Damaged Historical Documents.
AAAI
Zhenhua Yang, Dezhi Peng, Yongxin Shi, Yuyi Zhang, Chongyu Liu, Lianwen Jin
2025 J jnl
QT-TextSR: Enhancing scene text image super-resolution via efficient interaction with text recognition using a Query-aware Transformer.
Neurocomputing
Chongyu Liu, Qing Jiang, Dezhi Peng, Yuxin Kong, Jiaixin Zhang, Longfei Xiong, Jiwei Duan, Cheng Sun, Lianwen Jin
2025 — conf
RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs.
ACL (Findings)
Hongliang Li, Jiaxin Zhang, Wenhui Liao, Dezhi Peng, Kai Ding, Lianwen Jin
2025 J jnl
SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting.
Int. J. Comput. Vis.
Mingxin Huang, Dezhi Peng, Hongliang Li, Zhenghao Peng, Chongyu Liu, Dahua Lin, Yuliang Liu, Xiang Bai, Lianwen Jin
2025 J jnl
Toward Accurate Readings of Water Meters by Eliminating Transition Error: New Dataset and Effective Solution.
IEEE Trans. Instrum. Meas.
Jiaxin Zhang, Daizhen Jia, Chongyu Liu, Dezhi Peng, Bangdong Chen, Xue Gao, Lianwen Jin
2025 J jnl
URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding.
CoRR
Yongxin Shi, Jiapeng Wang, Zeyu Shan, Dezhi Peng, Zening Lin, Lianwen Jin
2024 J jnl
C
CoRR
Jiahuan Cao, Yongxin Shi, Dezhi Peng, Yang Liu, Lianwen Jin
2024 — conf
DTSM: Toward Dense Table Structure Recognition with Text Query Encoder and Adjacent Feature Aggregator.
ICDAR (1)
Xinhong Chen, Bangdong Chen, Chenfan Qu, Dezhi Peng, Chongyu Liu, Lianwen Jin
2024 A* conf
DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks.
CVPR
Jiaxin Zhang, Dezhi Peng, Chongyu Liu, Peirong Zhang, Lianwen Jin
2024 J jnl
DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks.
CoRR
Jiaxin Zhang, Dezhi Peng, Chongyu Liu, Peirong Zhang, Lianwen Jin
2024 A* conf
FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning.
AAAI
Zhenhua Yang, Dezhi Peng, Yuxin Kong, Yuyi Zhang, Cong Yao, Lianwen Jin
2024 J jnl
HierCode: A Lightweight Hierarchical Codebook for Zero-shot Chinese Text Recognition.
CoRR
Yuyi Zhang, Yuanzhi Zhu, Dezhi Peng, Peirong Zhang, Zhenhua Yang, Zhibo Yang, Cong Yao, Lianwen Jin
2024 J jnl
Predicting the Original Appearance of Damaged Historical Documents.
CoRR
Zhenhua Yang, Dezhi Peng, Yongxin Shi, Yuyi Zhang, Chongyu Liu, Lianwen Jin
2024 J jnl
SideNet: Learning representations from interactive side information for zero-shot Chinese character recognition.
Pattern Recognit.
Ziyan Li, Yuhao Huang, Dezhi Peng, Mengchao He, Lianwen Jin
2024 J jnl
SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting.
CoRR
Mingxin Huang, Dezhi Peng, Hongliang Li, Zhenghao Peng, Chongyu Liu, Dahua Lin, Yuliang Liu, Xiang Bai, Lianwen Jin
2024 — conf
TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models.
EMNLP (Findings)
Jiahuan Cao, Dezhi Peng, Peirong Zhang, Yongxin Shi, Yang Liu, Kai Ding, Lianwen Jin
2024 J jnl
TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models.
CoRR
Jiahuan Cao, Dezhi Peng, Peirong Zhang, Yongxin Shi, Yang Liu, Kai Ding, Lianwen Jin
2024 A* conf
Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods.
CVPR
Chenfan Qu, Yiwu Zhong, Chongyu Liu, Guitao Xu, Dezhi Peng, Fengjun Guo, Lianwen Jin
2024 A* conf
UPOCR: Towards Unified Pixel-Level OCR Interface.
ICML
Dezhi Peng, Zhenhua Yang, Jiaxin Zhang, Chongyu Liu, Yongxin Shi, Kai Ding, Fengjun Guo, Lianwen Jin
2024 A* conf
ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining.
AAAI
Dezhi Peng, Chongyu Liu, Yuliang Liu, Lianwen Jin
2023 A conf
Building A Mobile Text Recognizer via Truncated SVD-based Knowledge Distillation-Guided NAS.
BMVC
Weifeng Lin, Canyu Xie, Dezhi Peng, Jiapeng Wang, Lianwen Jin, Wei Ding, Cong Yao, Mengchao He
2023 A* conf
ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer.
ICCV
Mingxin Huang, Jiaxin Zhang, Dezhi Peng, Hao Lu, Can Huang, Yuliang Liu, Xiang Bai, Lianwen Jin
2023 J jnl
ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer.
CoRR
Mingxin Huang, Jiaxin Zhang, Dezhi Peng, Hao Lu, Can Huang, Yuliang Liu, Xiang Bai, Lianwen Jin
2023 — conf
EnsExam: A Dataset for Handwritten Text Erasure on Examination Papers.
ICDAR (3)
Liufeng Huang, Bangdong Chen, Chongyu Liu, Dezhi Peng, Weiying Zhou, Yaqiang Wu, Hui Li, Hao Ni, Lianwen Jin
2023 J jnl
Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation.
CoRR
Yongxin Shi, Dezhi Peng, Wenhui Liao, Zening Lin, Xinhong Chen, Chongyu Liu, Yuyi Zhang, Lianwen Jin
2023 J jnl
FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning.
CoRR
Zhenhua Yang, Dezhi Peng, Yuxin Kong, Yuyi Zhang, Cong Yao, Lianwen Jin
2023 A* conf
M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark.
NeurIPS
Yongxin Shi, Chongyu Liu, Dezhi Peng, Cheng Jian, Jiarong Huang, Lianwen Jin
2023 J jnl
On the Hidden Mystery of OCR in Large Multimodal Models.
CoRR
Yuliang Liu, Zhang Li, Hongliang Li, Wenwen Yu, Mingxin Huang, Dezhi Peng, Mingyu Liu, Mingrui Chen, Chunyuan Li, Lianwen Jin, Xiang Bai
2023 A* conf
Read Ten Lines at One Glance: Line-Aware Semi-Autoregressive Transformer for Multi-Line Handwritten Mathematical Expression Recognition.
ACM Multimedia
Wentao Yang, Zhe Li, Dezhi Peng, Lianwen Jin, Mengchao He, Cong Yao
2023 J jnl
Recognition of Handwritten Chinese Text by Segmentation: A Segment-Annotation-Free Approach.
IEEE Trans. Multim.
Dezhi Peng, Lianwen Jin, Weihong Ma, Canyu Xie, Hesuo Zhang, Shenggao Zhu, Jing Li
2023 A* conf
Revisiting Scene Text Recognition: A Data Perspective.
ICCV
Qing Jiang, Jiapeng Wang, Dezhi Peng, Chongyu Liu, Lianwen Jin
2023 J jnl
Revisiting Scene Text Recognition: A Data Perspective.
CoRR
Qing Jiang, Jiapeng Wang, Dezhi Peng, Chongyu Liu, Lianwen Jin
2023 J jnl
SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text.
IEEE Trans. Neural Networks Learn. Syst.
Canjie Luo, Yuanzhi Zhu, Lianwen Jin, Zhe Li, Dezhi Peng
2023 J jnl
SPTS v2: Single-Point Scene Text Spotting.
CoRR
Yuliang Liu, Jiaxin Zhang, Dezhi Peng, Mingxin Huang, Xinyu Wang, Jingqun Tang, Can Huang, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin
2023 J jnl
SPTS v2: Single-Point Scene Text Spotting.
IEEE Trans. Pattern Anal. Mach. Intell.
Yuliang Liu, Jiaxin Zhang, Dezhi Peng, Mingxin Huang, Xinyu Wang, Jingqun Tang, Can Huang, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin
2023 — conf
SegCTC: Offline Handwritten Chinese Text Recognition via Better Fusion Between Explicit and Implicit Segmentation.
ICDAR (4)
Jiarong Huang, Dezhi Peng, Hongliang Li, Hao Ni, Lianwen Jin
2023 A* conf
Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution.
CVPR
Chenfan Qu, Chongyu Liu, Yuliang Liu, Xinhong Chen, Dezhi Peng, Fengjun Guo, Lianwen Jin
2023 J jnl
UPOCR: Towards Unified Pixel-Level OCR Interface.
CoRR
Dezhi Peng, Zhenhua Yang, Jiaxin Zhang, Chongyu Liu, Yongxin Shi, Kai Ding, Fengjun Guo, Lianwen Jin
2023 J jnl
ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining.
CoRR
Dezhi Peng, Chongyu Liu, Yuliang Liu, Lianwen Jin
2022 B conf
Complex Table Structure Recognition in the Wild Using Transformer and Identity Matrix-Based Augmentation.
ICFHR
Bangdong Chen, Dezhi Peng, Jiaxin Zhang, Yujin Ren, Lianwen Jin
2022 J jnl
PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition.
CoRR
Dezhi Peng, Lianwen Jin, Yuliang Liu, Canjie Luo, Songxuan Lai
2022 J jnl
PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition.
Int. J. Comput. Vis.
Dezhi Peng, Lianwen Jin, Yuliang Liu, Canjie Luo, Songxuan Lai
2022 J jnl
Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach.
CoRR
Dezhi Peng, Lianwen Jin, Weihong Ma, Canyu Xie, Hesuo Zhang, Shenggao Zhu, Jing Li
2022 J jnl
SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text.
CoRR
Canjie Luo, Yuanzhi Zhu, Lianwen Jin, Zhe Li, Dezhi Peng
2022 A* conf
SPTS: Single-Point Text Spotting.
ACM Multimedia
Dezhi Peng, Xinyu Wang, Yuliang Liu, Jiaxin Zhang, Mingxin Huang, Songxuan Lai, Jing Li, Shenggao Zhu, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin
2021 — conf
A Multi-level Progressive Rectification Mechanism for Irregular Scene Text Recognition.
ICDAR (4)
Qianying Liao, Qingxiang Lin, Lianwen Jin, Canjie Luo, Jiaxin Zhang, Dezhi Peng, Tianwei Wang
2021 J jnl
Development and implementation of an LIS-based validation system for autoverification toward zero defects in the automated reporting of laboratory test results.
BMC Medical Informatics Decis. Mak.
Di Jin, Qing Wang, Dezhi Peng, Jiajia Wang, Bijuan Li, Yating Cheng, Nanxun Mo, Xiaoyan Deng, Ran Tao
2021 J jnl
Efficient HLS Implementation of Fast Linear Discriminant Analysis Classifier.
IEEE Embed. Syst. Lett.
Dezhi Peng, Jin Sha
2021 A* conf
Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter.
CVPR
Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Dezhi Peng, Zhe Li, Mengchao He, Yongpan Wang, Canjie Luo
2021 J jnl
Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter.
CoRR
Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Dezhi Peng, Zhe Li, Mengchao He, Yongpan Wang, Canjie Luo
2021 J jnl
SPTS: Single-Point Text Spotting.
CoRR
Dezhi Peng, Xinyu Wang, Yuliang Liu, Jiaxin Zhang, Mingxin Huang, Songxuan Lai, Shenggao Zhu, Jing Li, Dahua Lin, Chunhua Shen, Lianwen Jin
2021 — conf
Towards Fast, Accurate and Compact Online Handwritten Chinese Text Recognition.
ICDAR (3)
Dezhi Peng, Canyu Xie, Hongliang Li, Lianwen Jin, Zecheng Xie, Kai Ding, Yichao Huang, Yaqiang Wu
2021 — conf
Zero-Shot Chinese Text Recognition via Matching Class Embedding.
ICDAR (3)
Yuhao Huang, Lianwen Jin, Dezhi Peng
2019 A conf
A Fast and Accurate Fully Convolutional Network for End-to-End Handwritten Chinese Text Segmentation and Recognition.
ICDAR
Dezhi Peng, Lianwen Jin, Yaqiang Wu, Zhepeng Wang, Mingxiang Cai
2018 B conf
Detecting Heads using Feature Refine Net and Cascaded Multi-scale Architecture.
ICPR
Dezhi Peng, Zikai Sun, Zirong Chen, Zirui Cai, Lele Xie, Lianwen Jin
2018 J jnl
Detecting Heads using Feature Refine Net and Cascaded Multi-scale Architecture.
CoRR
Dezhi Peng, Zikai Sun, Zirong Chen, Zirui Cai, Lele Xie, Lianwen Jin
2018 B conf
Scale Mapping and Dynamic Re-Detecting in Dense Head Detection.
ICIP
Zikai Sun, Dezhi Peng, Zirui Cai, Zirong Chen, Lianwen Jin