Computer Vision

This repository consists of various computer vision and Multimodal AI projects. The projects focus on various fields of CV such as:

• Vision Language Models and Multimodal AI
• Stable Diffusion (Text-To-Image Generation)
• Video Summarization
• Object Tracking (Face Tracking & Lip Tracking)
• Object Detection
• Semantic Segmentation and Segment Anything
• Realtime Pose Estimation

The tools in which I gained proficiency while working on these projects are:

• PyTorch
• TensorFlow
• OpenCV
• OpenVino
• Transformers
• OpenAI
• Diffusers

Multimodal AI Assistant

VidSummAPI: Video Summarization API Using DSNet

Gym Workout Tracker

Background Removal Using Segment Any

Semantic Segmentation

YoloV8 Object Detection

Lip Reading: Deep Learning Based Spoken Text Generation from Lip Movement