Posts by Collection

projects

publications

Minimally Invasive Intraperitoneal Photodynamic Therapy using a New Soft Robot System Y. Liu, K. Yamazaki, D. Zhang, Y. Li, M. Su, Q. Xie, Y. Chen, and M. Bai., SPIE 11220, Optical Methods for Tumor Treatment and Detection: Mechanisms and Techniques in Photodynamic Therapy XXIX, 2020.

Gearbox Development for an Emergency Brake System of the Wind Turbine E. Sirotkin, K. Yamazaki, and A. Miroshnichenko., IOP Conference Series: Earth and Environmental Science, Volume 459, Chapter 1., 2020.

A Multi-task Contextual Atrous Residual Networkfor Brain Tumor Detection & Segmentation N. Le, K. Yamazaki, K. Quach, D. Truong, and M. Savvides, International Conference on Pattern Recognition (ICPR), 2020.

Offset Curves Loss for Imbalanced Problem in Medical Segmentation N. Le, T. Le, K. Yamazaki, B. Toan, K. Luu , International Conference on Pattern Recognition (ICPR), 2020.

Towards Sensorimotor Coupling of a Spiking Neural Network and Deep Reinforcement Learning for Robotics Application. K. Yamazaki, Undergraduate Honors Thesis, 2020.

Genesis: A Generative and Universal Physics Engine for Robotics and Beyond Genesis Authors, , 2024.

Development of a Soft Robot-Based Photodynamic Therapy for Pancreatic Cancer Y. Li, Y. Liu, K. Yamazaki, M. Bai, and Y.Chen, IEEE/ASME Transactions on Mechatronics (TMECH), 2021.

Invertible Residual Network with Regularization for Effective Volumetric Segmentation K. Yamazaki, N. Le, V. Rathour, SPIE Medical Imaging, 2021.

Agent-Environment Network for Temporal Action Proposal Generation V. Vo-Ho, N. Le, K. Yamazaki, A. Sugimoto, and M. Tran, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.

Narrow Band Active Contour Attention Model for Medical Segmentation N. Le, T. Bui, K. Vo-Ho, K. Yamazaki, K. Luu, Diagnostics, 2021.

Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey N. Le, V. Rathour, K. Yamazaki, K. Luu, and M. Savvides, Artificial Intelligence Review, 2021.

ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation K. Vo, K. Yamazaki, S. Truong, M.-T. Tran, A. Sugimoto, and N. Le, IEEE Access, 2021.

AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation K. Vo, H. Joo, K. Yamazaki, S. Truong, K. Kitani,, M.-T. Tran, N. Le, The British Machine Vision Conference (BMVC) - (Oral Presentation-3.33%), 2021.

VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning K. Yamazaki, S. Truong, K. Vo, M. Kidd, C. Rainwater, K. Luu, N. Le, International Conference on Image Processing (ICIP), 2022.

Spiking neural networks and their applications: A Review K. Yamazaki, K. Vo-Ho, D. Bulsara, N. Le, Brain Sciences, 2022.

AISFormer: Amodal Instance Segmentation with Transformer M. Tran, K. Vo, K. Yamazaki, A. Fernandes, M. Kidd, N. Le, The British Machine Vision Conference (BMVC), 2022.

AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation K. Vo, S. Truong*, K. Yamazaki*, B. Raj, MT. Tran, N. Le, International Journal of Computer Vision (IJCV), 2022.

VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning K. Yamazaki, K. Vo, S. Truong, B. Raj, N. Le, Association for the Advancement of Artificial Intelligence (AAAI) - (Oral Presentation), 2023.

Neural architecture search for medical image applications K. Vo, K. Yamazaki, H. Hoang, M. Tran, N. Le, Meta-Learning with Medical Imaging and Health Informatics Applications, 2023.

CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection K. Joo, K. Vo, K. Yamazaki, N. Le, International Conference on Image Processing (ICIP), 2023.

DNA: Deformable Neural Articulations Network for Template-Free Dynamic 3D Human Reconstruction From Monocular RGB-D Video K. Vo, T. Pham, K. Yamazaki, M. Tran, N. Le, IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023.

Towards Multi-modal Explainable Video Understanding K. Yamazaki, Master's Thesis, 2023.

Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation K. Yamazaki, T. Hanyu, K. Vo, T. Pham, M. Tran, G. Doretto, A. Nguyen, N. Le, ICRA 2024, 2024.

R2-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations X. Li, K. Qiu, J. Wang, X. Xu, R. Singh, K. Yamazaki, H. Chen, X. Huang, B. Raj, European Conference on Computer Vision (ECCV), 2024.

AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation T. Hanyu*, K. Yamazaki*, M. Tran, R. McCann, H. Liao, C. Rainwater, M. Adkins, J. Cothren, N. Le, Remote Sensing, 2024.

HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model K. Vo, T. Phan, K. Yamazaki, M. Tran, N. Le, Conference on Neural Information Processing Systems (NeurIPS) - (Poster Presentation), 2024.

research

talks

teaching