Flask-based AI app that summarizes surveillance videos using Whisper (audio), ViT-GPT2 (frame captions), and Groq LLM (narratives). Produces both general and law enforcement-style summaries.

AI-powered image captioning using InceptionV3+LSTM and ViT-GPT2 models. Trained on Flickr8k dataset with interactive Streamlit interface.

Developed an image captioning system using the BLIP model to generate detailed, context-aware captions. Achieved an average BLEU score of 0.72, providing rich descriptions that enhance accessibility and inclusivity.

The chrome extension that gets input images and generates the captions for them.

A powerful Streamlit application that analyzes images using multiple vision models and responds to queries about visual content through conversational AI.

An AI-powered image captioning app built with Streamlit, using ViT-GPT2 for caption generation and YOLOv8 for object detection. The app provides enhanced captions by integrating detected objects into the generated text.