Workshop date: June 15, 2020
All times below are in PDT. Links are included in “Title/Description” as well as on landing page: http://cvpr20.com/text-and-documents/ (Last Updated: 13 June)
| Time (PDT) | Type | Title / Description (Click to join each session) | Presenter / Author / Responsible |
|---|---|---|---|
| 8:30 – 8:40 | (LIVE) | Opening Remarks | R. Manmatha, Yuting Zhang, Vijay Mahadevan, Dimosthenis Karatzas |
| 8:40 – 9:35 | Invited Talk | Images with Text: Visually Grounded Reading Comprehension | Marcus Rohrbach |
| 9:35 – 10:30 | Invited Talk | Semantic Reading of Population Records: A Digital Twin of the Past Societies | Josep Lladós |
| 10:30 – 10:50 | Break | ||
| 10:50 – 11:50 | ORAL SESSION (Q & A with authors during the whole session) | ||
| Best Paper | 10:50 – 11:00 | READ: Recursive Autoencoders for Document Layout Generation | Akshay Gadi Patil, Omri Ben-Eliezer, Or Perel, Hadar Averbuch-Elor |
| 11:00 – 11:10 | On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention | Junyeop Lee, Sungrae Park, Jeonghun Baek, Seong Joon Oh, Seonghyeon Kim, Hwalsuk Lee | |
| 11:10 – 11:20 | CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks | Youngmin Baek, Daehyun Nam, Sungrae Park, Junyeop Lee, Seung Shin, Jeonghun Baek, Chae Young Lee, Hwalsuk Lee | |
| 11:20 – 11:30 | Recognizing handwritten mathematical expressions via paired dual loss attention network and printed mathematical expressions | Anh Duc Le | |
| 11:30 – 11:40 | Visual Parsing with Query-Driven Global Graph Attention (QD-GGA): Preliminary Results for Handwritten Math Formula Recognition | Mahshad Mahdavi, Richard Zanibbi | |
| 11:40 – 11:50 | CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents | Devashish Krishna Prasad, Ayan Gadpal, Kshitij Kapadni, Manish Visave, Kavita A Sultanpure | |
| 11:50 – 13:20 | POSTER SESSION (Q & A with authors during the whole session) | ||
| Poster paper #1 | A method for detecting text of arbitrary shapes in natural scenes that improves text spotting | Qitong Wang, YI ZHENG, Margrit Betke | |
| Poster paper #2 | Textual Visual Semantic Dataset for Text Spotting | Ahmed A Sabir, Francesc Moreno, Lluís Padró | |
| Poster paper #3 | A Large Dataset of Historical Japanese Documents with Complex Layouts | Zejiang Shen, Kaixuan Zhang, Melissa Dell | |
| Poster paper #4 | An Accurate Segmentation-Based Scene Text Detector with Context Attention and Repulsive Text Border | Xi Liu, Gaojing Zhou, Rui Zhang, Xiaolin Wei | |
| Poster paper #5 | Illegible Text to Readable Text: An Image-to-Image Transformation using Conditional Sliced Wasserstein Adversarial Networks | Mostafa Karimi, Gopalkrishna Veni, Yen-Yun Yu | |
| Poster paper #6 | Optical Braille Recognition Based on Semantic Segmentation Network with Auxiliary Learning Strategy | Renqiang Li, Hong Liu, Xiangdong Wang, Jianxing Xu, Yueliang Qian | |
| Poster paper #7 | Font-ProtoNet: Prototypical Network based Font Identification of Document Images in Low Data Regime | Nikita Goel, Monika Sharma, Lovekesh Vig | |
| Poster paper #8 | Information Extraction from Document Images via FCA based Template Detection and Knowledge Graph Rule Induction | Mouli Rastogi, Afshan Syed, Mrinal Rawat, Lovekesh Vig, Puneet Agarwal, Gautam Shroff, Ashwin Srinivasan | |
| Poster paper #9 | An OCR for Classical Indic Documents Containing Arbitrarily Long Words | Agam Dwivedi, Rohit Saluja, Ravi Kiran Sarvadevabhatla | |
| Poster paper #10 | Visual and Textual Deep Feature Fusion for Document Image Classification | Souhail Bakkali, Zuheng MING, Mickael Coustaty, Marçal Rusiñol | |
| Poster paper #11 | Symbol Spotting on Digital Architectural Floor Plans Using a Deep Learning-based Framework | Alireza Rezvanifar, Melissa Cote, Alexandra Branzan Albu | |
| 13:20 – 13:50 | Long Break | ||
| 13:50 – 14:45 | Invited Talk | Gaining a Deeper Visual Understanding of Documents | Brian Price |
| 14:45 – 15:30 | (LIVE, recorded) | Panel session | Marcus Rohrbach, Josep Lladós, Brian Price |
| 15:30 – 15:50 | Break | ||
| 15:50 – 17:30 | DocVQA CHALLENGE SESSION (Q & A with authors during the live discussion) | ||
| 15:50 – 16:05 | Intro and Overview of Task 1 (Dataset, Results, Analysis of the results) | Minesh Mathew | |
| Task 1 Winner | 16:05 – 16:15 | Task 1: PingAn-OneConnect-Gammalab-DQA | Han Qiu, Guoqiang Xu, Chenjie Cao, Chao Gao, Dexun Wang, Fengxin Yang, Xiao Xie, Yu Qiu, Ziqi Zheng |
| Task 1 Runner-up 1st | 16:15 – 16:25 | Task 1: Structural LM-v2 | Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang |
| Task 1 Runner-up 2nd | 16:25 – 16:35 | Task 1: QA_Base_MRC_1 | Yudi Chen, Youhui Guo, Gangyan Zeng, Jianjian Cao, Qiming Peng, Sijin Wu |
| 16:35 – 16:45 | Overview of Task 2 (Dataset, Results, Analysis of the results) | Ruben Tito Perez | |
| Task 2 Winner | 16:45 – 16:50 | Task 2: PingAn-OneConnect-Gammalab-DQA | Han Qiu, Guoqiang Xu, Chenjie Cao, Chao Gao, Dexun Wang, Fengxin Yang, Xiao Xie, Yu Qiu, Ziqi Zheng |
| Task 2 Runner-up 1st | 16:50 – 17:00 | Task 2: iFLYTEK-DOCR | Chenyu Liu, Fengren Wang, Jiajia Wu, Jinshui Hu, Bing Yin, Cong Liu |
| 17:00 – 17:30 (LIVE, recorded) | Discussion and Awards ceremony | Minesh Mathew, Ruben Tito Perez, R. Manmatha, C.V. Jawahar, D. Karatzas | |
| 17:30 – 17:40 | Opening/Closing (LIVE, recorded) | Closing and best paper award | R. Manmatha, Yuting Zhang, Vijay Mahadevan, Dimosthenis Karatzas |
