9 citations · 24 across the 14 of their papers we have counts for
14 papers
OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities
Peirong Zhang, Haowei Xu, Jiaxin Zhang +7
Improving visual text synthesis has long been a challenging and evolving frontier for image generation models. While recent state-of-the-art (SOTA) models have made remarkable stri…
Smaller But Better: Unifying Layout Generation with Smaller Large Language Models
Peirong Zhang, Jiaxin Zhang, Jiahuan Cao +2
We propose LGGPT, an LLM-based model tailored for unified layout generation. First, we propose Arbitrary Layout Instruction (ALI) and Universal Layout Response (ULR) as the uniform…
RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs
Hongliang Li, Jiaxin Zhang, Wenhui Liao +3
Current Multimodal Large Language Model (MLLM) architectures face a critical tradeoff between performance and efficiency: decoder-only architectures achieve higher performance but…
LEGO: Self-Supervised Representation Learning for Scene Text Images
Yujin Ren, Jiaxin Zhang, Lianwen Jin
In recent years, significant progress has been made in scene text recognition by data-driven methods. However, due to the scarcity of annotated real-world data, the training of the…
DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming
Jiaxin Zhang, Wentao Yang, Songxuan Lai +2
Current multimodal large language models (MLLMs) face significant challenges in visual document understanding (VDU) tasks due to the high resolution, dense text, and complex layout…
DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks
Jiaxin Zhang, Dezhi Peng, Chongyu Liu +2
Document image restoration is a crucial aspect of Document AI systems, as the quality of document images significantly influences the overall performance. Prevailing methods addres…
UPOCR: Towards Unified Pixel-Level OCR Interface
Dezhi Peng, Zhenhua Yang, Jiaxin Zhang +5
Existing optical character recognition (OCR) methods rely on task-specific designs with divergent paradigms, architectures, and training strategies, which significantly increases t…
ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer
Mingxin Huang, Jiaxin Zhang, Dezhi Peng +5
In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-based framework. While previous studies have shown the crucial importance of the intrinsi…
DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures
Jiaxin Zhang, Bangdong Chen, Hiuyi Cheng +3
Recently, there has been a growing interest in research concerning document image analysis and recognition in photographic scenarios. However, the lack of labeled datasets for this…
MDoc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
Hiuyi Cheng, Peirong Zhang, Sihang Wu +6
Document layout analysis is a crucial prerequisite for document understanding, including document retrieval and conversion. Most public datasets currently contain only PDF document…
SPTS v2: Single-Point Scene Text Spotting
Yuliang Liu, Jiaxin Zhang, Dezhi Peng +8
End-to-end scene text spotting has made significant progress due to its intrinsic synergy between text detection and recognition. Previous methods commonly regard manual annotation…
Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild
Jiaxin Zhang, Canjie Luo, Lianwen Jin +2
Camera-captured document images usually suffer from perspective and geometric deformations. It is of great value to rectify them when considering poor visual aesthetics and the det…
SPTS: Single-Point Text Spotting
Dezhi Peng, Xinyu Wang, Yuliang Liu +9
Existing scene text spotting (i.e., end-to-end text detection and recognition) methods rely on costly bounding box annotations (e.g., text-line, word-level, or character-level boun…
Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution
Jiapeng Wang, Chongyu Liu, Lianwen Jin +6
Visual information extraction (VIE) has attracted considerable attention recently owing to its various advanced applications such as document understanding, automatic marking and i…