Prof. Miki Haseyama Profile

Prof. Miki Haseyama

SPIE Involvement:

Author

Publications (7)

Proceedings Article | 5 February 2025 Paper

Improving robustness of CLIP by adversarial training enhanced by brain activity

Tasuku Nakajima, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama

Proceedings Volume 13510, 135101K (2025) https://doi.org/10.1117/12.3058026

KEYWORDS: Brain, Functional magnetic resonance imaging, Adversarial training, Education and training, Data modeling, Neuroimaging, Feature extraction, Defense and security, Semantics, Image processing

Read Abstract +

Proceedings Article | 5 February 2025 Paper

Balancing generalization and personalization by sharing layers in clustered federated learning

Kenta Kubota, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama

Proceedings Volume 13510, 135100L (2025) https://doi.org/10.1117/12.3057727

Read Abstract +

Proceedings Article | 5 February 2025 Paper

Enhanced framework for generating counterfactual images with sophisticated caption and inversion-free image editing

Xiang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama

Proceedings Volume 13510, 135100H (2025) https://doi.org/10.1117/12.3057596

KEYWORDS: Image processing, Image classification, Data modeling, Image enhancement, Semantics, Classification systems, Atmospheric modeling, Systems modeling, Education and training

Read Abstract +

Proceedings Article | 5 February 2025 Paper

Expert comment generation from sports videos using multimodal LLM

Tatsuki Seino, Naoki Saito, Takahiro Ogawa, Huang-Chia Shih, Satoshi Asamizu, Miki Haseyama

Proceedings Volume 13510, 135100S (2025) https://doi.org/10.1117/12.3057887

Read Abstract +

Proceedings Article | 5 February 2025 Paper

Learning hierarchical video-text relationship via large language model for cross-modal video retrieval

Huaying Zhang, Ren Togo, Takahiro Ogawa, Miki Haseyama

Proceedings Volume 13510, 135100I (2025) https://doi.org/10.1117/12.3057615

KEYWORDS: Video, Education and training, Video coding, Video acceleration, Curium, Feature extraction, Information technology, Information science, Design, Video processing

Read Abstract +