image-embeddings

computer vision and sports

Train Models Contrastively in Pytorch

OpenL3: Open-source deep audio and image embeddings

An unofficial Chrome extension that finds and removes duplicate photos from your Google Photos library

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.

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

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

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

LightweightEmbeddings is a fast, free, and unlimited API service for multilingual embeddings and reranking, with support for both text and images and guaranteed uptime.

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

Image compression, denoising, similarity search and latent-space morphing with linear, convolutional and denoising autoencoders in TensorFlow and Keras 3. One CLI for LFW or your own images, with tests and measured results.

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"

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.

Predicts product prices using TF-IDF text features + EfficientNet image embeddings, fused into a LightGBM regressor, optimized for SMAPE and scalable e-commerce datasets.

Jina CLIP v2 - Multimodal embedding model for text and images with Matryoshka representations (64-1024 dimensions). Deployed on Replicate with optimized GPU inference.

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

Self-hosted visual and cross-modal product search for e-commerce catalogs: embed images and text with OpenAI CLIP, search a local FAISS index, and store every product image, embedding, and index in Backblaze B2 over the S3-compatible API. No managed vector database, no second API key. Next.js + FastAPI.

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

project group 129