Dezhi Peng
14 papers · 2021–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (6) π Conference Polyglot (7) π Academic Marathon (5) πΊοΈ Taxonomy Completionist (33)
π
Conference Polyglot
(7)
π
Academic Marathon
(5)
π
Renaissance Researcher
(6)
π€
Dynamic Duo
(13)
β‘
Prolific Year
(6)
π
Century Club
(13)
ποΈ
Keyword Collector
(80)
Conferences
AAAI (4)
CVPR (4)
ICCV (2)
ACL (1)
EMNLP (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
text recognition
(3)
attention mechanism
(2)
multimodal large language model
(2)
diffusion model
(2)
image restoration
(2)
semantic segmentation
(2)
benchmark evaluation
(1)
image segmentation
(1)
unsupervised learning
(1)
deep learning
(1)
anomaly detection
(1)
style transfer
(1)
curriculum learning
(1)
self-supervised learning
(1)
image generation
(1)
image-to-image translation
(1)
multimodal learning
(1)
multi-task learning
(1)
data augmentation
(1)
vision transformer
(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Predicting the Original Appearance of Damaged Historical Documents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
Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods
CVPR 2024
ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining
AAAI 2024
FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning
AAAI 2024
DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks
CVPR 2024
TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models
EMNLP 2024
UPOCR: Towards Unified Pixel-Level OCR Interface
ICML 2024
Revisiting Scene Text Recognition: A Data Perspective
ICCV 2023
Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution
CVPR 2023
M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark
NIPS 2023
ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer
ICCV 2023
Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter
CVPR 2021