Session Chair: Takahiro Komamizu (Mathematical and Data Science Center at Nagoya University, Japan)

13:30 - 13:40: Welcome

Session 1: Cross-Modal Models

13:40 - 14:00: [Short Paper] Improving Cross-Modal Recipe Embeddings with Cross Decoder

Authors: Jing Yang (The University of Electro-Communications, Japan), Junwen Chen (The University of Electro-Communications, Japan), Keiji Yanai (The University of Electro-Communications, Japan)

14:05 - 14:30: [Application Paper] Enhancing Smart Service Development: Embedding Image Recognition Capabilities within the xDataAPI

Authors: Sadanori Ito (National Institute of Information and Communications Technology, Japan) Koji Zettsu (National Institute of Information and Communications Technology, Japan)

Session 2: AI Applied to Human Data

14:35 - 15:00: [Video][Regular Paper] Exploring Interpretable AI Methods for ECG Data Classification

Authors: Jaya Ojha (Computer Science, Oslo Metropolitan University, Norway), Hårek Haugerud (Computer Science, Oslo Metropolitan University, Norway), Anis Yazidi (Computer Science, Oslo Metropolitan University, Norway), Pedro G. Lind (Computer Science, Oslo Metropolitan University, Norway)

15:05 - 15:30: [Video][Regular Paper] Exploring Human Cognition From Eye-Movements: Is There Unconscious Visual Information?

Authors: Rujeena Mathema (Computer Science, OsloMet - Oslo Metropolitan University, Norway), Pedro G. Lind (Computer Science, OsloMet - Oslo Metropolitan University, Norway), Pedro Lencastre (Computer Science, OsloMet - Oslo Metropolitan University, Norway)

Session 3: Secure Image Processing and Video Violence Detection

15:35 - 16:00: [Video][Regular Paper] FHE-Based Secure Image Processing Framework with Integrated Key Management System

Authors: Rafik Hamza (Institute for International Strategy, Tokyo International University, Japan)

16:05 - 16:25: [Short Paper] Violence Detection in Videos based on CNN feature for ConvLSTM2D

Authors: Tan-Dat Trinh (Saigon University, Vietnam), Thanh-Sang Vu-Ngoc (Saigon University, Vietnam), Lam-Thuy Le-Nhi (Saigon University, Vietnam), Duy-Dong Le (University Of Economics Ho Chi Minh City, Vietnam), Thai-Binh Nguyen (University Of Economics Ho Chi Minh City, Vietnam) , The-Bao Pham (Saigon University, Vietnam)

Session 4: Model Compression for Federated Learning

16:30 - 16:55: [Survey Paper] A Survey of Model Compression and Its Feedback Mechanism in Federated Learning

Authors: Duy-Dong Le (Industrial University of Ho Chi Minh City, Vietnam), Anh-Khoa Tran (National Institute of Information and Communications Technology, Japan), The-Bao Pham (Saigon University, Vietnam), Tuong-Nguyen Huynh (Industrial University of Ho Chi Minh City, Vietnam)

17:00 - 17:10: Best paper award and close

Best paper candidates

1. FHE-Based Secure Image Processing Framework with Integrated Key Management System

2. Exploring Interpretable AI Methods for ECG Data Classification

3. Exploring Human Cognition From Eye-Movements: Is There Unconscious Visual Information?

The Best paper Award is given to

Exploring Interpretable AI Methods for ECG Data Classification