Scholar
Keisuke Maeda
Google Scholar ID: 5sZKrK0AAAAJ
Hokkaido University
Citations & Impact
Citations
700
H-index
10
i10-index
13
Publications
20
Co-authors
10
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- Publications:
- - Keisuke MAEDA, Masaya SATO, Takahiro OGAWA, Miki HASEYAMA, "Construction of a bridge inspection specialized multimodal LLM with controllable attention areas - Introduction of an area-guided control mechanism based on Visual Prompt Learning without training", AI & Data Science Papers, 2025. (Accepted for publication)
- - Masaki YOSHIDA, Keisuke MAEDA, Ren TOGO, Takahiro OGAWA, Miki HASEYAMA, "Prediction of incident occurrence location from emergency call audio considering real-time and place name speech recognition", AI & Data Science Papers, 2025. (Accepted for publication)
- - Mitsuo TOISHI, Keisuke MAEDA, Ren TOGO, Takahiro OGAWA, Miki HASEYAMA, "Bridge health assessment through fine-tuning of base models - Analysis of the impact on classification accuracy of imbalanced data", AI & Data Science Papers, 2025. (Accepted for publication)
- - Yuhu FENG, Keisuke MAEDA, Takahiro OGAWA, Miki HASEYAMA, "Damage classification based on dynamically adaptive federated learning considering non-iid data for each region", AI & Data Science Papers, 2025. (Accepted for publication)
- - Koushi WATANABE, Keisuke MAEDA, Ren TOGO, Takahiro OGAWA, Miki HASEYAMA, "Estimation of damage types and degrees of road accessories using Vision Transformer and large-scale visual-language models", AI & Data Science Papers, 2025. (Accepted for publication)
- - Masaya SATO, Keisuke MAEDA, Ren TOGO, Takahiro OGAWA, Miki HASEYAMA, "Automatic generation of findings using generative AI in the 2024 bridge regular inspection guidelines - Introduction of inspection record extraction and similar image group search", AI & Data Science Papers, 2025. (Accepted for publication)
- - Masaya SATO, Keisuke MAEDA, Takahiro OGAWA, Miki HASEYAMA, "InfLLaVA: Construction of a bridge inspection specialized multimodal large-scale language model through instruction tuning - Acquisition of specialized knowledge and multitasking capabilities for bridge inspection", AI & Data Science Papers, 2025. (Accepted for publication)
- - Ren TOGO, Xiang LI, Ryo Ta GO, Naoki SAITO, Keisuke MAEDA, Fumiyuki KAMADA, Ryuji KUBO, Yuji KAWASAKI, Takahiro OGAWA, Miki HASEYAMA, "Anomaly detection of highway accessories and vegetation using in-context learning of multimodal large language models with onboard camera videos", AI & Data Science Papers, 2025. (Accepted for publication)
- - Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “GeoJapan Fusion Framework: A large multimodal model for regional remote sensing recognition,” Remote Sensing, vol. 17, no. 17: 3044, 2025.
- - Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Cross-domain multi-step thinking: Zero-shot fine-grained traffic sign recognition in the wild,” Knowledge-Based Systems, vol. 327, no. 9: 114172, 2025.
- - Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Few-shot Personalized Saliency Prediction Based on Interpersonal Gaze Patterns,” ITE Transactions on Media Technology and Applications, 2025. (Accepted for publication)
- - Yuki Era, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Generalizing stylized motion generation method by introducing metadata-independent learning and unified multiple motion dataset,” IEEE Transactions on Multimedia, 2025. (Accepted for publication)
- - Chinami FUKUI, Chang WANG, Zibin LAN, Guang LI, Akira TAMURA, Tsuyoshi HANAOKA, Keisuke MAEDA, Sho TAKAHASHI, Takahiro OGAWA, Miki HASEYAMA, “Text region detection and numerical recognition of scanned drawings using LMM,” AI & Data Science Papers, vol. 6, no. 2, pp. 173-178, 2025.
- - Hiroki OKAMURA, Keisuke MAEDA, Ren TOGO, Takahiro OGAWA, Miki HASEYAMA, “Linear structure analysis of embeddings for bias disparity reduction in collaborative filtering” IEEE Transactions on Services Computing, vol. 18, no. 4, pp. 2201-2211, 2025.
- - Tasuku NAKAJIMA, Keisuke MAEDA, Ren TOGO, Takahiro OGAWA, Miki HASEYAMA, “Enhancing adversarial defense via brain activity integration without adversarial examples,” Sensors, vol. 25, no. 9: 2736, 2025.
- - Kenta KUBOTA, Ren TOGO, Keisuke MAEDA, Takahiro OGAWA, Miki HASEYAMA, “Analysis of model merging methods for continual updating of foundation models in distributed data settings,” Applied Sciences, vol. 15, no. 9: 5196, 2025.
Research Experience
- April 2019 - February 2020: JSPS Research Fellow (PD)
- March 2020 - March 2022: Assistant Professor, General IR Office, Hokkaido University
- April 2022 - January 2024: Assistant Professor, Laboratory of Media Dynamics, Graduate School of Information Science and Technology, Hokkaido University
- February 2024 - March 2025: Associate Professor, Data-Driven Fusion Research Center, Hokkaido University
- April 2025 - Present: Associate Professor, Graduate School of Information Science and Technology, Hokkaido University
Education
- March 2015: Graduated from the Faculty of Engineering, Hokkaido University
- March 2017: Completed Master's Program in Graduate School of Information Science and Technology, Hokkaido University
- April 2017: Entered the Doctoral Program in Graduate School of Information Science and Technology, Hokkaido University
- March 2019: Graduated from the Doctoral Program in Graduate School of Information Science and Technology, Hokkaido University (shortened period of study)
Background
- Engaged in interdisciplinary research centered on information science. Promoting research on multimodal signal processing and machine learning using heterogeneous data such as images, text, and biological information, and their applications. Member of IEEE and the Institute of Electronics, Information and Communication Engineers. Ph.D. (Information Science).
Miscellany
- Keywords: Generative AI, Adversarial Attacks/Defense, Continual Learning, Federated Learning, Computer Vision, Machine Unlearning, Gaze and Brain Activity Analysis, Infrastructure AI, Correlation Analysis, Emotion Recognition, Multimedia Retrieval, Sports AI
