Koki Maeda
Doctoral Student Β· Vision and Language Researcher
Exploring the intersection of computer vision and natural language processing, with a focus on multimodal evaluation metrics and context-aware image captioning.
Education π
Ph.D., Tokyo Institute of Technology
Vision and Language, Evaluation Β· Advisor: Naoaki Okazaki
Focusing on novel evaluation metrics for multimodal systems and cross-modal representation learning.
M.Eng., Tokyo Institute of Technology
Vision and Language: Image Captioning Β· Advisor: Naoaki Okazaki
Developed context-aware image captioning models that generate descriptions based on user preferences.
B.Eng., Tokyo Institute of Technology
NLP: Grammatical Error Correction Β· Advisor: Naoaki Okazaki, Mentor: Masahiro Kaneko
Created improved evaluation metrics for grammatical error correction systems.