Publications

TubeQuery - Ask anything from a YouTube video

• Audio Processing
• FFMPEG
• GitHub
• +11

Summarize and Explain Contents with AI Agents

• agent
• ai
• ai-agent
• +6

w3b3_agent

• AI
• blockchain
• digital art
• +2

Building image-to-text AI agents using NLP and Llama 3.2 11B Vision Model

• Image-to-text
• Llama3.2
• NLP

Backseat Driver Kid - a curious toddler, designed to explore data analysis with privacy in mind

Legal AI Assistant

The Mistral model fine-tune for smart-home consulting

• CSS selector
• web crawler

Visionary Platform: Real-Time Image, Video, and Webcam Interaction with AI Integration

• AIIntegration
• ComputerVision
• EyeDectection
• +5

Enhanced Face and Eye Detection in Real-Time Using Haar Cascades in OpenCV

• computer vision
• eyes detection
• face detection
• +3

CancerCare Bot: An AI-Powered Chatbot for Cancer Awareness and Patient Assistance

• #ArtificialIntelligence
• #ChatbotDevelopment
• #HealthcareAI

Screen Sage

AI for Flow Pattern Identification: One-dimensional Model

• Artificial Intelligence
• Deep Learning
• Machine Learning
• +2

Multi-Modal Vision-Language Monitoring System

• Computer Vision
• Llama 3.2 Vision
• Object Tracking
• +2

OCR and Keyword Search Application

• Gradio
• Gradle
• Machine Learning
• +4

Manga_Colorization_and_Translation

• ARTIFICIAL INTELLIGENCE
• Colorization
• GAN
• +5

Autonomous Driving using CV

Leukocyte Detection with Raspberry Pi

• Hematology
• Leukocytes
• Pathology
• +1

Svaisthi

• gemini
• Health
• medication adherance
• +2

Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking

• 3D tracking
• 3D vision
• autonomous driving
• +3

Bayesian Causal Inference for Sentiment Polarity

• Bayesian
• Causal Inference
• causal-inference