Projects

Leveraging Large Multimodal Models for Building Damage Assessment

Image Difference Captioning using multi-branch Vision Transformer and GPT2

Face to Bitmoji Conversion using Domain Transfer Network

Musical Audio Similarity: A Signal Processing-based Shazam-like project

Pen-based Handwritten Character Recognition for Kannada Numbers

Finding optimal path for an agent using Dyna-Q+

One handed Braille: An HCI study using a Flutter-based application

Word Memory Android App