Thoughts & Articles
Writing about AI, Machine Learning, Computer Vision, and my research journey
Getting Started with YOLO for Real-Time Object Detection
A comprehensive guide to understanding YOLO architecture and implementing it for real-time object and gesture detection in computer vision applications.
Stable Diffusion: From Theory to Practice
Understanding the mathematics behind diffusion models and how to use them for generating lifelike avatar animations and 2D-to-3D video transformations.
Building Sign Language Recognition with Deep Learning
How I built a real-time Indian Sign Language recognition system supporting multi-person gestures and sentence-level translation using YOLO-NAS and MediaPipe.
Real-Time Pose Estimation with MediaPipe
Leveraging MediaPipe's pose estimation capabilities for skeletal keypoint extraction, enhancing gesture recognition accuracy in sign language systems.
LSTM + Dynamic Time Warping for Gesture Sequence Recognition
Combining LSTM temporal modeling with DTW for robust dynamic gesture recognition — the approach behind my IEEE GITCON 2026 publication.
Deploying AI Models to the Edge with TensorRT & ONNX
A practical guide to optimizing PyTorch models using ONNX and TensorRT for low-latency inference on edge devices.