computer vision and sports

Train Models Contrastively in Pytorch

OpenL3: Open-source deep audio and image embeddings

Locally run web app and Chrome extension to remove duplicates from Google Photos

A Python toolkit for image clustering using deep learning, PCA, and K-means, with support for GPU and CPU processing. Simplify your image analysis projects with advanced embeddings, dimensionality reduction, and automated visual categorization.

Kernel Fisher Discriminant Analysis implementation following https://arxiv.org/abs/1906.09436

Content for workshops on computer vision @ HPI's AI Service Center

This repository contains the implementation of a facings identifier using YOLOv8 and image embeddings. The goal of this project is to count the number of facings (product instances) of each product present on shelves in a retail store using computer vision techniques.

Code implementation for our ICPR, 2020 paper titled "Improving Word Recognition using Multiple Hypotheses and Deep Embeddings"

Hybrid recommendation engine using deep learning that incorporates user and item features, including images and text.

Code implementation for our DAS, 2020 paper titled "Fused Text Recogniser and Deep Embeddings Improve Word Recognition and Retrieval"

A lightweight Text-to-Image Retrieval model [Web App]

Mind-X is my intelligent alter ego that understands me the best. It assists with and resolves my bothersome tasks, growing in real-time as a next-generation PersonAI system.

project group 129

Text2ImageDescription retrieves relevant images from Pascal VOC 2012 dataset using OpenAI CLIP, based on text queries, and generates descriptions using quantized Mistral-7b model.

This notebook demonstates end-to-end process of generating image embeddings from Flickr8k dataset using InceptionV3 and generate captions using LSTM.

Uncover visual connections in a flash with AI-powered reverse image search.

end-to-end image search app

This app allows users to search for products by either entering text or uploading an image, and retrieves relevant products from a database

imgs.ai is a fast, dataset-agnostic, visual search engine for digital art history based on neural network embeddings.