Dezhi Peng
14 papers · 2021–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (31) π Academic Marathon Β· Sprint π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver
π€
Dynamic Duo
(14)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(84)
Top co-authors
Research topics
Computer Vision
(9)
Machine Learning
(8)
Deep Learning
(6)
Processing
(6)
Application Areas
(4)
Artificial Intelligence
(3)
Analysis
(3)
Architectures
(3)
Core AI
(3)
Computer Science
(2)
Applications
(2)
Core Methods
(2)
Domain-Specific
(2)
Learning Types Β· Deep Learning
(2)
Learning Types Β· Machine Learning
(2)
Keywords
text recognition
(3)
vision transformer
(2)
multimodal large language model
(2)
retrieval-augmented generation
(2)
attention mechanism
(2)
diffusion model
(2)
semantic segmentation
(2)
image restoration
(2)
self-supervised learning
(1)
style transfer
(1)
benchmark evaluation
(1)
curriculum learning
(1)
catastrophic forgetting
(1)
anomaly detection
(1)
efficient computing
(1)
image segmentation
(1)
deep learning
(1)
image-to-image translation
(1)
image generation
(1)
multimodal learning
(1)
Papers
URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding
AAAI 2026
Predicting the Original Appearance of Damaged Historical Documents
AAAI 2025
RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs
ACL 2025
DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks
CVPR 2024
FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning
AAAI 2024
TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models
EMNLP 2024
Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods
CVPR 2024
UPOCR: Towards Unified Pixel-Level OCR Interface
ICML 2024
ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining
AAAI 2024
ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer
ICCV 2023
M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark
NeurIPS 2023
Revisiting Scene Text Recognition: A Data Perspective
ICCV 2023
Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution
CVPR 2023
Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter
CVPR 2021