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

9:00 - 9:10: Welcome

Session 1 (9:10 - 10:10) : Cross-Modal Models

[in-person] Towards Integrated Multimodal Interaction: Merging Immersive 3D Worlds with Language Based Retrieval for 3D Scene Understanding

Authors: Shawn Bowser,Cynthia Matuszek,Stephanie Lukin

[online] SafeDriveQA: Benchmarking Vision Language Model for Safe Driving Assessment

Authors: Satoshi Yamazaki,Michiaki Inoue,Mika Sakuma,Takahiro Kimoto

[online] TOU: A Truncated-factorized reduction for a lightweight fine-tuning method

Authors: Phuong Thi-Mai Nguyen,Koji Zettsu

Session 2 (10:20 - 11:00): Image Retrieval

[TBD] CSD: Cross-Modal Similarity Distillation for Zero-Shot Composed Image Retrieval

Authors: Shuping Hui,Min Wang,Hui Wu,Wengang Zhou,Houqiang Li

[TBD] AMF: Adaptive Modality Fusion for Zero-Shot Composed Image Retrieval

Authors: Shuping Hui,Min Wang,Hui Wu,Wengang Zhou,Houqiang Li

Session 3 (11:10 - 11:50): Federated Learning

[online] Latency-Aware Split Learning Optimization via Genetic Algorithms

Authors: Le Hoang Trung,Tan Y. Nguyen,Duy Dong Le,Thai Thinh Dang,Tran Anh Khoa

[online] Efficient Federated Split Learning on Android Smartphones via Adaptive Offloading Point Mechanism

Authors: Pham Duy Thanh,Koji Zettsu

11:50 - 12:00: Best paper award and close