Program

Oral Session-1: Character and Text Recognition

Location: Zoom ID：965 7567 4004
Chair: Professor Seiichi Uchida
Volunteer: Yuzhe Gao, [email protected]; Cong Fang [email protected]

1. Maximum Entropy Regularization and Chinese Text Recognition 
   Changxu Cheng, Wuheng Xu, Xiang Bai, Bin Feng, and Wenyu Liu
2. An Improved Convolutional Block Attention Module for Chinese Character Recognition
   Kai Zhou, Yongsheng Zhou, Rui Zhang and Xiaolin Wei 
3. Adapting OCR with limited supervision 
   Deepayan Das and Cv Jawahar 
4. High performance offline handwritten Chinese text recognition with a new data preprocessing and augmentation pipeline
   Canyu Xie, Songxuan Lai, Qianying Liao and Lianwen Jin

Oral Session-2: Document Image Processing

Location: Zoom ID：965 7567 4004
Chair: Professor Robert Sablatnig
Volunteer: Yuzhe Gao, [email protected]; Cong Fang [email protected]

1. Self-Supervised Representation Learning on Document Images 
   Adrian Cosma, Mihai Ghidoveanu, Michael Panaitescu-Liess and Marius Popescu
2. ACMU-Net: Advanced Cascading Modular U-Nets incorporating Squeeze and Excitation blocks 
   Seokjun Kang, Brian Kenji Iwana and Seiichi Uchida
3. Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network
   Guo-Wang Xie, Fei Yin, Xu-Yao Zhang and Cheng-Lin Liu 
4. Building Super-Resolution Image Generator for OCR Accuracy Improvement 
   Xujun Peng and Chao Wang 

Oral Session-3: Segmentation and Layout Analysis

Location: Zoom ID：928 8718 9528
Chair: Professor Jean-Christophe Burie
Volunteer: Yu Zhou, [email protected]; Shi Gong [email protected]

1. The Benefits of Close-Domain Fine-Tuning for Table Detection in Document Images 
   Ángela Casado García, César Domínguez, Jónathan Heras, Eloy Mata and Vico Pascual
2. IIIT-AR-13K: A New Dataset for Graphical Object Detection in Documents 
   Ajoy Mondal, Peter Lipps and C V Jawahar 
3. Page Segmentation Using Convolutional Neural Network and Graphical Model 
   Xiao-Hui Li, Fei Yin and Cheng-Lin Liu 
4. The Notary in the Haystack–Countering Class Imbalance in Document Processing with CNNs 
   Martin Leipert, Georg Vogeler, Mathias Seuret, Andreas Maier and Vincent Christlein 

Oral Session-4: Word Embedding and Spotting

Location: Zoom ID： 928 8718 9528
Chair: Professor Rui Zhang
Volunteer: Yu Zhou, [email protected]; Shi Gong [email protected]

1. Annotation-free Learning of Deep Representations for Word Spotting using Synthetic Data and Self Labeling 
   Fabian Wolf and Gernot A. Fink
2. Fused Text Recogniser and Deep Embeddings Improve Word Recognition and Retrieval 
   Siddhant Bansal, Praveen Krishnan and C. V. Jawahar 
3. A Named Entity Extraction System for Historical Financial Data 
   Wassim Swaileh, Thierry Paquet, Sébastien Adam and Andres Rojas Camacho 
4. Effect of Text Color on Word Embeddings 
   Masaya Ikoma, Brian Kenji Iwana and Seiichi Uchida 

Oral Session-5: Text Detection

Location: Zoom ID：981 4690 6186
Chair: Professor Xucheng Yin
Volunteer: Xinwei He [email protected]; Peng Liu [email protected]

1. SickZil-Machine: A Deep Learning Based Script Text Isolation System for Comics Translation 
   U-Ram Ko and Hwan-Gue Cho
2. Lyric Video Analysis Using Text Detection and Tracking 
   Shota Sakaguchi, Jun Kato, Masataka Goto and Seiichi Uchida 
3. Fast and Lightweight Text Line Detection on Historical Documents 
   Aleksei Melnikov and Ivan Zagaynov
4. From Automatic Keyword Detection to Ontology-based Topic Modeling 
   Marc Beck, Syed Tahseen Raza Rizvi, Andreas Dengel and Sheraz Ahmed 

Oral Session-6: Font Design and Classification

Location: Zoom ID: 981 4690 6186
Chair: Professor Marçal Rusiñol
Volunteer: Xinwei He [email protected]; Peng Liu [email protected]

1. Character-independent font identification 
   Daichi Haraguchi, Shota Harada, Brian Kenji Iwana, Yuto Shinahara and Seiichi Uchida
2. A New Common Points Detection based Method for Classification of 2D and 3D Text in Video/Scene Images 
   Lokesh Nandanwar,  Palaiahnakote Shivakumara, Ahlad Kumar, Tong Lu, Umapada Pal and Daniel Lopresti
3. Analysis of Typefaces Designed for Readers with Developmental Dyslexia: Insights from Neural Networks
   Xinru Zhu, Kyo Kageura and Shin’Ichi Satoh
4. Neural Style Difference Transfer and Its Application to Font Generation 
   Gantugs Atarsaikhan, Brian Kenji Iwana and Seiichi Uchida

Poster Session-1

P1-1. A New Context based Method for Restoring Occluded Text in Natural Scene Images  
Ayush Mittal, Shivakumara Palaiahnakote, Umapada Pal, Tong Lu, Michael Blumenstein and Daniel Lopresti
Location: Zoom ID: 955 3142 7547
Volunteer: Mengde Xu, [email protected]
P1-2. Document Data Extraction System Based on Visual Words Codebook 
Vasily Loginov, Aleksander Valjukov, Stanislav Semenov and Ivan Zagaynov
Location: Zoom ID: 974 4728 7404
Volunteer: Xudong Xie, [email protected]
P1-3. ALEC: An Accurate, Light and Efficient Network for CAPTCHA Recognition    
Nan Li, Qianyi Jiang, Qi Song, Rui Zhang and Xiaolin Wei
Location: Zoom ID: 920 5057 3733
Volunteer: Mingtao Fu, [email protected]
P1-4. Automated Transcription for Pre-Modern Japanese Kuzushiji Documents by Random Lines Erasure and Curriculum Training
Anh Le Duc
Location: Zoom ID: 925 2965 7483
Volunteer: Tianyi Shi, [email protected];
P1-5. A Benchmark System for Indian Language Text Recognition 
Krishna Tulsyan, Nimisha Srivastava, Ajoy Mondal and C V Jawahar
Location: Zoom ID: 956 7484 8148
Volunteer: Changxu Cheng, [email protected];
P1-6. Representative Image Selection for Data Efficient Word Spotting
Florian Westphal, Håkan Grahn and Niklas Lavesson
Location: Zoom ID: 943 8967 6102
Volunteer: Zhisheng Zou, [email protected];
P1-7. Classification of phonetic characters by space-filling curves 
Valentin Owczarek, Jordan Drapeau, Jean-Christophe Burie, Patrick Franco, Mickaël Coustaty, Rémy Mullot and Véronique Egli
Location: Zoom ID: 934 7830 0621
Volunteer: Yuzhe Gao, [email protected];
P1-8. Faster Glare Detection in Document Images  
Dmitry Rodin, Ivan Zagaynov and Andrey Zharkov
Location: Zoom ID: 957 0688 0101
Volunteer: Peng Liu, [email protected];

SP1-1. Self-condence prediction based on analysis of handwriting behavior using log-normal distributions of features
Takanori Maruichi and Koichi Kise
Location: Zoom ID: 950 6367 8549
Volunteer: Xing Li, [email protected];
SP1-2. Optical Character Recognition for Navigation Signs in Japanese Stations
Shoya Hirukawa and Kazutaka Maruyama
Location: Zoom ID: 927 5556 4386
Volunteer: Shi Gong, [email protected];
SP1-3. Audio Book Creation System for Indian Languages
Krishna Tulsyan, Vandna Chaturvedi, Aradhana Vinod, Nimisha Srivastava, Ajoy Mondal, and C V Jawahar
Location: Zoom ID: 984 6688 0902
Volunteer: Jiajia Chu, [email protected]

Poster Session-2

P2-1. Camera Captured DIQA with Linearity and Monotonicity Constraints     
Xujun Peng and Chao Wang
Location: Zoom ID: 988 0084 1383
Volunteer: Mengde Xu, [email protected]
P2-2. New Benchmarks for Barcode Detection using both Synthetic and Real Data     
Andrey Zharkov, Andrey Vavilin and Ivan Zagaynov.
Location: Zoom ID: 999 2637 1052
Volunteer: Xudong Xie, [email protected]
P2-3. A Method for Scene Text Style Transfer  
Gaojing Zhou, Xi Liu, Lei Wang, Rui Zhang, Yongsheng Zhou and Xiaolin We
Location: Zoom ID: 971 6725 6349
Volunteer: Mingtao Fu, [email protected]
P2-4. Evaluation of Neural Network Classification System on Documents Stream
Joris Voerman, Aurélie Joseph, Mickaël Coustaty, Vincent Poulain d’Andecy and Jean-Marc Ogier
Location: Zoom ID: 990 3262 5619
Volunteer: Tianyi Shi, [email protected]
P2-5. Re-ranking for Writer Identification and Writer Retrieval       
Simon Jordan, Mathias Seuret, Pavel Král, Ladislav Lenc, Jiřı́ Martı́nek, Barbara Wiermann, Tobias Schwinger, Andreas Maier and Vincent Christlei
Location: Zoom ID: 975 4656 4567
Volunteer: Changxu Cheng, [email protected]
P2-6. Background Removal of French University Diplomas      
Tanmoy Mondal, Mickaël Coustaty and Petra Gomez-Krämer
Location: Zoom ID: 933 1689 2298
Volunteer: Zhisheng Zou, [email protected]
P2-7. Counting Population of Ottoman Villages by Using CNN-based Page Segmentation and Object Recognition in Historical Records    
Yekta Said Can and Mustafa Erdem Kabadayi
Location: Zoom ID: 938 6518 7589
Volunteer: Yuzhe Gao, [email protected]
P2-8. Named Entity Recognition in Semi Structured Documents using Neural Tensor Networks   
Khurram Shehzad, Adnan Ul-Hasan, Muhammad Imran Malik and Faisal Shafait
Location: Zoom ID: 964 9181 8408
Volunteer: Peng Liu, [email protected]

SP2-1. Automated Cause-of-Death Tagging from 1918 Ohio Death Records
Joseph Price, Mark Clement, Stanley Fujimoto, M. Johnson Merrell, Sophia Rawlings and Alex Bay
Location: Zoom ID: 973 6328 6214
Volunteer: Xing Li, [email protected]
SP2-2. Reverse Indexing
Mark Clement, Joseph Price, Kyler Rosquist, Joseph Steed, and Zhihao Tsai
Location: Zoom ID: 937 9817 1435
Volunteer: Shi Gong, [email protected]
SP2-3. Document Visual Question Answering Challenge 2020
Minesh Mathew, Rubn Tito, Dimosthenis Karatzas, R. Manmatha3 and C.V. Jawahar
Location: Zoom ID: 928 9506 5521
Volunteer: Jiajia Chu, [email protected]