Poster Session I & Doctoral Consortium
| Tuesday, September 3, 2024 |
| 3:10 PM - 4:40 PM |
Speaker
Dr. Xiao-Hui Li
Institute Of Automation, Chinese Academy Of Sciences
P1.1 GraphMLLM: A Graph-based Multi-level Layout Language-Independent Model for Document Understanding
Mr. Chening Yang
Cinnamonai
P1.2 One-shot Transformer-based Framework for Visually-Rich Document Understanding
Mr. Chening Yang
Cinnamonai
P1.3 Light-Weight Multi-Modality Feature Fusion Network for Visual Rich Document Understanding
Mr. Mohammad Minouei
Dfki
P1.4 Embedding Layout in Text for Document Understanding Using Large Language Models
Ms. Mayire Ibrahim
Xinjiang University
P1.5 Doc-DINO: A Transformer Model for Complex Logical Document Layout Analysis
Dr. Daichi Haraguchi
Kyushu university
P1.6 Font Style Interpolation with Diffusion Models
Prof. Seiichi Uchida
Kyushu University
P1.7 Learning to Kern — Set-wise Estimation of Optimal Letter Space
Mr. Ning Ding
Tsinghua University
P1.8 Geometric-aware control in diffusion model for handwritten Chinese font generation
Dr. Daichi Haraguchi
Kyushu university
P1.9 Typographic Text Generation with Off-the-Shelf Diffusion Model
Mr. Robert Sablatnig
CVL - TU Wien
P1.10 Drawing the Line: Deep Segmentation for Extracting Art from Ancient Etruscan Mirrors
Ms. Zeynep Sonat Baltaci
Ecole Des Ponts Paristech
P1.11 Historical Printed Ornaments: Dataset and Tasks
Dr. Christopher Kermorvant
Teklia
P1.12 The Socface Project: Large-Scale Collection, Processing, and Analysis of a Century of French Censuses
Dr. Hsiang-An Wang
Academia Sinica
P1.13 Recognition of Components in Taoist Charm Images
Mr. Stephan Unter
University Of Basel
P1.14 Text Line Segmentation on Ancient Egyptian Papyri: Layout Analysis with Object Detection Networks and Connected Components
Mr. Taylor Archibald
Brigham Young University
P1.15 DELINE8K: A Synthetic Pipeline for the Semantic Segmentation of Historical Documents
Dr. Christopher Kermorvant
Teklia
P1.16 Callico: a versatile open-source document image annotation platform
Dr. Birhanu Hailu Belay
University Of Paris-saclay
P1.17 A Historical Handwritten Dataset for Ethiopic OCR with Baseline Models and Human-level Performance
Mr. Andrei-Marius Avram
National University of Science and Technology POLITEHNICA Bucharest
P1.18 HistNERo: Historical Named Entity Recognition for the Romanian Language
Dr. Vladimir Arlazarov
Smart Engines
P1.19 Fully automatic virtual unwrapping method for documents imaged by X-ray tomography
Mr. Manuel Villarreal
Universitat Politècnica de València
P1.20 Enhancing Recognition of Historical Musical Pieces with Synthetic and Composed images
Dr. Matthias Beckmann
University Of Bremen
P1.21 On Image Processing and Pattern Recognition for Thermograms of Watermarks in Manuscripts - A First Proof-of-Concept
Prof. Liangcai Gao
Peking University
P1.22 SegHist: A General Segmentation-based Framework for Chinese Historical Document Text Line Detection
Prof. Hongxi Wei
Inner Mongolia University
P1.23 Recognition and Link Prediction of Onomatopoeia Texts with Arbitrary Shapes
Prof. Alimjan Aysa
Xinjiang University
P1.24 Oracle Bone Inscriptions Image Retrieval Based on Metric Learning
Mr. Thomas Constum
University of Rouen
P1.25 End-to-end information extraction in handwritten documents: understanding Paris marriage records from 1880 to 1940
Mr. Guodong Ding
Hithink Royalflush Information Network Co.,ltd.
P1.26 LMTextSpotter: Towards Better Scene Text Spotting with Language Modeling in Transformer
Prof. Yuliang Liu
Huazhong University Of Science And Technology
P1.27 Progressive Evolution from Single-Point to Polygon for Scene Text
Prof. Kurban Ubul
Xinjiang University
P1.28 A New Bottom-up Path Augmentation Attention Network for Script Identification in Scene Images
Prof. Elisa Barney Smith
Luleå Tekniska Universitet
P1.29 MOoSE: Multi-Orientation Sharing Experts for Open-set Scene Text Recognition
Ms. Mayire Ibrahim
Xinjiang University
P1.30 More and Less: Enhancing Abundance and Refining Redundancy for Text-prior-guided Scene Text Image Super-Resolution
Ms. Mayire Ibrahim
Xinjiang University
P1.31 A Real-Time Scene Uyghur Text Detection Network Based on Feature Complementation
Mr. Jiangyang He
WUT
P1.32 Controllable text layout generation for synthesizing scene text image
Mr. Ling Fu
Huazhong University of Science and Technology
P1.33 The First Swahili Language Scene Text Detection and Recognition Dataset
Prof. C.V. Jawahar
IIIT- H
P1.34 Indic Scene Text on the Roadside
Mr. Ling Fu
Huazhong University of Science and Technology
P1.35 Dataset and Benchmark for Urdu Natural Scenes Text Detection and Recognition and Visual Question Answering
Mr. Sho Shimotsumagari
Kyushu University
P1.36 Cross-Domain Image Conversion by CycleDM
Mr. Michal Hradis
Faculty Of Information Technology, Brno University
P1.37 Self-supervised Pre-training of Text Recognizers
Dr. Dimosthenis Karatzas
Computer Vision Center
P1.38 Counting the Corner Cases: Revisiting Robust Reading Challenge Data Sets, Evaluation Protocols, and Metrics
Dr. Qiufeng Wang
Xi’an Jiaotong-Liverpool University
P1.39 Coarse-to-Fine Document Image Registration for Dewarping
Dr. Ujjwal Bhattacharya
Indian Statistical Institute
P1.40 YOLO Assisted A* Algorithm for Robust Line Segmentation of Degraded Document Images
Dr. Josep Llados
Computer Vision Center
P1.41 DistilDoc: Knowledge Distillation for Visually-Rich Document Applications
Dr. Yahong Hu
Zhejiang University Of Technology
P1.42 Deep Learning Enabled Functional Knowledge Unit Innovation Generation Model
Dr. Mickael Coustaty
L3i Lab - La Rochelle University
P1.43 Global-SEG: Text semantic segmentation based on global semantic pair relations
Dr. Souhail Bakkali
La Rochelle University
P1.44 Multimodal Adaptive Inference with Anytime Early Exiting
Ms. Yiran Zhao
Beijing University Of Technology
P1.45 Integrating Dependency Type and Directionality into Adapted Graph Attention Networks to Enhance Relation Extraction
Dr. Vladimir Arlazarov
Smart Engines
P1.46 An Ultra-Lightweight Approach for Machine Readable Zone Detection via Semantic Segmentation and Fast Hough Transform
Ms. Konstantina Nikolaidou
Lulea University Of Technology
P1.47 Enhancing CRNN HTR Architectures with Transformer Blocks
Dr. Marie Beurton
LaBRI - Univ Bordeaux
P2.1 ViT-ED: Transformer network for image similarity measurement
Dr. Eyad Elyan
Robert Gordon University
P2.8 A Multiclass Imbalanced Dataset Classification of Symbols from Piping and Instrumentation Diagrams
