Remarks:
Regular papers: 20 minutes presentation, 5 minutes Q&A
Short papers:15 minutes presentation, 5 minutes Q&A
Time: June 27, 2022, Local time, NJ, USA
ICDAR2022 Proceedings
9:15 - 9:30: Welcome from workshop organizers
9:30 - 10:30: Invited Talk
Title: Inferential machine learning
Speaker: Professor Hugo Hammer, OsloMet University and SimulaMet, Norway
Abstract:
The talk will discuss how concepts from statistical inference can extent
and improve machine learning methodology, and likewise how machine learning
can be used to improve traditional statistical inference. The suggested
directions allow for better cross data understanding and in general can
result in more trustworthy and reproducible methods.
10:30 - 10:50: Coffee break & Networking
10:50 - 12:40: Multimodal Data Analysis
Session Chair: Michael Riegler (Simula Metropolitan Center for Digital Engineering, Norway)
(R) Explainable Artificial Intelligence for Human Embryo Cell Cleavage Stages Analysis Video
Authors: Akriti Sharma, Mette Stensen, Erwan Delbarre, Trine Haugen and Hugo Hammer
(R) Multimodal Cheapfakes Detection by Utilizing Image Captioning for Global Context Video
Authors: Tuan-Vinh La, Quang-Tien Tran, Thanh-Phuc Tran, Anh-Duy Tran, Duc-Tien Dang-Nguyen
(S) Tone Classification for Political Advertising Video using Multimodal Cues Video
Authors: Anh-Khoa Vo and Yuta Nakashima
(S) A Hybrid Transformer Network for Detection of Risk Situations on Multimodal Life-Log Health Data Video
Authors: Rupayan Mallick, Jenny Benois-Pineau, Akka Zemmari, Marion Pech, Thinhinane Yebda, Hélène Amieva and Laura Middleton
(S) Predicting High-risk Congestion Areas During Heavy Rain Using Multi Prediction Model and Maximum Periodic Frequent Pattern Algorithms Video
Authors: Minh-Dang Tran and Nazmudeen Mohamed Saleem
12:45 - 14:00: Lunch & Networking
14:00 - 15:40: IoT, Education, and Privacy Preserving
Session Chair: Duc-Tien Dang-Nguyen (University of Bergen, Norway)
(R) IoT-based Multimodal Analysis for Smart Education: Current Status, Challenges and Opportunities Video
Authors: Wenbin Gan, Koji Zettsu and Yuan Sun
(R) Is More Realistic Better? A Comparison of Game Engine and GAN-based Avatars for Investigative Interviews of Children
Authors: Pegah Salehi, Syed Zohaib Hassan, Saeed Shafiee Sabet, Gunn Astrid Baugerud, Miriam Sinkerud Johnson, Pål Halvorsen and Michael Alexander Riegler
(R) Towards Intellectual Property Rights Protection in Big Data Video
Authors: Rafik Hamza, Sadanori Ito and Zettsu Koji
(S) DeDigi: A Privacy-by-Design Platform for Image Forensics Efficient Resource Allocation using Federated Learning in Cellular Networks Video
Authors: Chi-Hao Tran, Quoc-Thang Tran, Quynh-Chau Long-Vu, Hai-Son Nguyen, Anh-Duy Tran and Duc-Tien Dang-Nguyen
15:40 - 16:00: Coffee break & Networking
16:00 - 16:45: Federated Learning
Session Chair: Minh-Son Dao (NICT, Japan)
(R) FedMCRNN: Federated Learning using Multiple Convolutional Recurrent Neural Networks for Sleep Quality Prediction Video
Authors: Khoa Tran, Do-Van Nguyen, Phuoc Van Nguyen Thi and Zettsu Koji
(S)Efficient Resource Allocation using Federated Learning in Cellular Networks Video
Authors: Son Cao Nguyen, Minh Hoang, Tinh Phuc Vo and Duc Ngoc Minh Dang
16:45 - 17:30: Panel
Session Chair: Michael Riegler (Simula Metropolitan Center for Digital Engineering, Norway)
17:30 - 17:45: Closing Remarks