Regular papers:
15 minutes presentation, followed by 5 minutes Q&A
Short papers:
10 minutes presentation, followed by 5 minutes Q&A
Remarks:
Remote presentation need to comply with ICMR presentation instructions: Prepare a pre-recorded video of the presentation (which will be played in case of any connection issues) and send it
to the workshop organizers
xgu-habault@kddi.com(using Google Drive, Dropbox, or WeTransfer) by Thursday June 8th.
Time:
June 12th, 2023, Local time (EET), Thessaloniki, Greece
9:00 - 9:15 (EET): Welcome message from workshop organizers
9:15 - 10:30 (EET): Invited Talk + Q&A
Title: Frontiers of Machine Learning for Spatiotemporal Data
Speaker: Professor Yan Liu, University of Southern California
Abstract:
Recent years we have seen many progresses and changes in the spatiotemporal data domain. In this talk, Prof. Yan Liu will introduce several latest developments of the AI and ML research on the spatiotemporal data, including foundation models, physics-informed deep learning, casual models and federated learning. She will also talk about the interpretations of AI, especially based on the feature interaction perspective. This talk aims to provide some potential and essential challenges and opportunities for effectively applying AI and ML in the spatiotemporal data domain.
10:30 - 11:00 (EET): Coffee Break & Networking
11:05 - 11:25 (EET): AI Applied to Medical Domain
(R) Mask-conditioned latent diffusion for generating gastrointestinal polyp images
Authors: Roman Machácek, Leila Mozaffari, Zahra Sepasdar, Sravanthi Parasa, Pĺl Halvorsen, Michael-Alexander Riegler, Vajira Thambawita
11:30 - 12:10 (EET): AI for Transportation
(R) Procedural Driving Skill Coaching from More Skilled Drivers to Safer Drivers: A Survey
Authors: Wenbin Gan, Minh-Son Dao, Koji Zettsu
(S) Towards Multimodal Spatio-Temporal Transformer-based Models for Traffic Congestion Prediction
Authors: Huy Quang Ung, Yutaro Mishima, Hao Niu, Shinya Wada
12:15 - 12:55 (EET): AI Applied to Texts and Images
(R) CG-GNN: A Novel Compiled Graphs-based Feature Extraction Method for Enterprise Social Networks
Authors: Tatsuya Konishi, Shuichiro Haruta, Mori Kurokawa, Kenta Tsukatsune, Yuto Mizutani, Tomoaki Saito, Hideki Asoh, Chihiro Ono
(S) A Joint Scene Text Recognition and Visual Appearance Model for Protest Issue Classification
Authors: Xuan Luo, Sota Kato, Asahi Obata, Budrul Ahsan, Ryotaro Okada, Takafumi Nakanishi
13:00 - 14:00 (EET): Lunch Break & Networking
14:00 - 14:40 (EET): AI for Recommendation Systems
(R) User-irrelevant Cross-domain Association Analysis for Cross-domain Recommendation with Transfer Learning
Authors: Hao Niu, Duc Nguyen, Kei Yonekawa, Mori Kurokawa, Chihiro Ono, Daichi Amagata, Takuya Maekawa, Takahiro Hara
(S) MTSS: Movie Trailers Surveillance System using Social Media Analytics and Public Mood
Authors: Ioannis Prokopiou, Pantelis Vikatos, Christos Chatzis, Christos Christodoulou
14:45 - 15:25 (EET): AI Applied to Cheapfakes Detection
(R) Leveraging Cross-Modals for Cheapfakes Detection
Authors: Thanh-Son Nguyen, Vinh Dang, Minh-Triet Tran, Duc-Tien Dang-Nguyen
(S) Detecting Cheapfakes using Self-Query Adaptive-Context Learning
Authors: Kha-Luan Pham, Manh-Thien Nguyen, Anh-Duy Tran, Minh-Son Dao, Duc-Tien Dang-Nguyen
15:30 - 15:40 (EET): Closing Remarks
15:40 - 16:00 (EET): Coffee Break