Data release for the ImageInWords (IIW) paper.

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

Content-Based Image Retrieval System

This repo represents our machine learning project Image Description which is used to generate a description of an image based on activities and objects detected in the image.

Integrates AWS Bedrock's multimodal capabilities (Claude 3) into the Docling framework for generating image descriptions within document processing pipelines.

we generate captions to the images which are given by user(user input) using prompt engineering and Generative AI

Experimenting with mastodon.social client alt-text usage dataset.

In this project, we use a Deep Recurrent Architecture, which uses CNN (VGG-16 Net) pretrained on ImageNet to extract 4096-Dimensional image feature Vector and an LSTM which generates a caption from these feature vectors.

Integrate AI capabilities into a DevExpress-powered Office File API Web API application.

NL Generation from structured inputs. Focuses on generating natural language descriptions for images by exploring the relationship between textual descriptions and image attributes. Leveraging an encoder-decoder architecture with LSTM cells, the system transforms normalized vector representations of attributes into fixed-length vector.

NotyVisualScan uses AI to generate descriptions and tags for images in Notion, with automated image uploads.

Python script that turns PDF into text files; It extracts text and change image into text by vision models.

This Python script processes images in a specified folder, sends them to the OpenAI API and saves the responses as text files.

Key Pointers/ Exhaustive Notes for various Machine Learning Research Papers

Trabalho de Conclusão de Curso de Engenharia de Computação (UTFPR): Descritor de imagem baseado em curvas de Hilbert

Testing the Moondream tiny vision model

An AI-powered accessibility Discord bot written in Node.js, using Discord.js, MongoDB and Google Gemini API. The image-reader bot is designed to describe and transcribe images for the visually impaired, features a manual image-reading command and an auto-reading system.

Smart Screen Reader- A Screen reader chrome extension for visually-impaired people. This is a Chrome extension that enhances web accessibility by: Generating image descriptions using AI, Summarizing entire pages, Allowing users to ask questions and automatically scroll to the relevant sections.

Lucene Image Retrieval (LIRe) code to extract Open Access Series of Imaging Studies (OASIS) features.

Tech spec specialized #markitdown-plugin, for example enhanced markdowns with image descriptions and more