ジャーナル論文 / Journal
  1. Yoshida, S. M., Shibata, T., Terao, M., Okatani, T., and Sugiyama, M., "Action-Agnostic Point-Level Supervision for Temporal Action Detection", Proceedings of the AAAI Conference on Artificial Intelligence 39(9), 9571–9579, (2025).
  2. Kasai, R., and Okatani, T., "Visual Measurement and Uncertainty Prediction of Insulator Thickness in Insulated Rail Joints", IEEE Trans. Intell. Transport. Syst. 27(1), 375–386, (2025).
  3. Hosoya, Y., Suganuma, M., and Okatani, T., "Rethinking Open-Set Object Detection: Issues, A New Formulation, and Taxonomy", Int. J. Comput. Vis. 133(9), 6145–6169, (2025).
  4. Areerob, K., Nguyen, V., Li, X., Inadomi, S., Shimada, T., Kanasaki, H., Wang, Z., Suganuma, M., Nagatani, K., Chun, P., and Okatani, T., "Multimodal artificial intelligence approaches using large language models for expert‐level landslide image analysis", Comput.-Aided Civ. Infrastruct. Eng. 40(19), 2900–2921, (2025).
  5. Areerob, K., Nguyen, V., Li, X., Inadomi, S., Shimada, T., Kanasaki, H., Wang, Z., Suganuma, M., Nagatani, K., Chun, P., and Okatani, T., "Multimodal artificial intelligence approaches using large language models for expert‐level landslide image analysis", Comput.-Aided Civ. Infrastruct. Eng. 40(19), 2900–2921, (2025).
  6. Zhang, J., Suganuma, M., and Okatani, T., "That’s BAD: blind anomaly detection by implicit local feature clustering", Machine Vision and Applications 35(2), 31, (2024).
  7. Ye, Q., Suganuma, M., and Okatani, T., "Improved high dynamic range imaging using multi-scale feature flows balanced between task-orientedness and accuracy", Comput. Vision Image Understanding 248, 104126, (2024).
  8. Yamane, T., Chun, P., Dang, J., and Okatani, T., "Deep learning-based bridge damage cause estimation from multiple images using visual question answering", Struct. Infrastruct. Eng. ahead-of-print(ahead-of-print), 1–14, (2024).
  9. Wang, Z., Suganuma, M., and Okatani, T., "Rethinking unsupervised domain adaptation for semantic segmentation", Pattern Recognit. Lett. 186, 119–125, (2024).
  10. Charoenpitaks, K., Nguyen, V., Suganuma, M., Takahashi, M., Niihara, R., and Okatani, T., "Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction", IEEE Trans. Intell. Veh. PP(99), 1–11, (2024).
  11. Zhang, J., Suganuma, M., and Okatani, T., "Network Pruning and Fine-tuning for Few-shot Industrial Image Anomaly Detection", 2023 IEEE 21st International Conference on Industrial Informatics (INDIN) 00, 1–6, (2023).
  12. Wang, Z., Liu, X., Suganuma, M., and Okatani, T., "Unsupervised domain adaptation for semantic segmentation via cross-region alignment", Comput. Vision Image Understanding 234, 103743, (2023).
  13. Liu, S., Suganuma, M., and Okatani, T., "Symmetry-aware Neural Architecture for Embodied Visual Navigation", Int. J. Comput. Vis. 132(4), 1091–1107, (2023).
  14. Kunlamai, T., Yamane, T., Suganuma, M., Chun, P., and Okatani, T., "Improving visual question answering for bridge inspection by pre‐training with external data of image–text pairs", Computer‐Aided Civil and Infrastructure Engineering 39(3), 345–361, (2023).
  15. Zhu, Y., Sekiya, H., Okatani, T., Yoshida, I., and Hirano, S., "Real-time vehicle identification using two-step LSTM method for acceleration-based bridge weigh-in-motion system", Journal of Civil Structural Health Monitoring 12(3), 689–703, (2022).
  16. Nagatani, K., Abe, M., Osuka, K., Chun, P., Okatani, T., Nishio, M., Chikushi, S., Matsubara, T., Ikemoto, Y., and Asama, H., "Innovative technologies for infrastructure construction and maintenance through collaborative robots based on an open design approach", Adv. Rob., (2021).
国際会議 / Proceedings
  1. Zou, H., Suganuma, M., and Okatani, T., "RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution.", Wacv, 2756–2765, (2025).
  2. Zeng, Y., Suganuma, M., and Okatani, T., "Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method.", Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision, 4516–4524, (2025).
  3. Liu, K., Suganuma, M., and Okatani, T., "Self-Supervised Learning of Intertwined Content and Positional Features for Object Detection.", Icml, (2025).
  4. Ji, C., Kawasaki, K., Hasegawa, I., and Okatani, T., "Time-Frequency-Spatial Neural Architecture for Decoding Visual Signals from Macaque ECoG", 2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC) 00, 3254–3259, (2025).
  5. Charoenpitaks, K., Nguyen, V., Suganuma, M., Arai, K., Totsuka, S., Ino, H., and Okatani, T., "TB-Bench: Training and Testing Multi-Modal AI for Understanding Spatio-Temporal Traffic Behaviors from Dashcam Images/Videos", 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 00, 2436–2446, (2025).
  6. ge Imaging", Proceedings of ACM Multimedia, 5290–5297, (2021).
  7. Tanaka, T., Sasagawa, Y., and Okatani, T., "Learning To Bundle-Adjust: A Graph Network Approach to Faster Optimization of Bundle Adjustment for Vehicular SLAM", Proceedings of the IEEE/CVF International Conference on Computer Vision, 6250–6259, (2021).
  8. Song, W., Suganuma, M., Liu, X., Simobayashi, N., Maruta, D., and Okatani, T., "Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes", Proceedings of the IEEE/CVF International Conference on Computer Vision, 6029–6038, (2021).
  9. Nguyen, V., Suganuma, M., and Okatani , T., "Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks", Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 923–930, (2021).