Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

Thumbnail of www-x-com-tom-doerr-status-1893213032542527854-d050b4223f5b44b9

OCR & document extraction using vision models https://t.co/Gcx6LKiNxw

Github 👨‍🔧: PDF to Markdown with vision models 🔹 Document to Markdown Conversion: Converts various document formats such as PDF, DOCX, and images into markdown format. 🔹 Vision Model Powered OCR: Employs vision models like GPT-4o for Optical Character Recognition to accurately extract text... See more

Rohan Paul

x.com

multi-language OCR tool for fast offline text recognition https://t.co/LLc51bnTWG

Tom Dörr

x.com

new tutorial: how to use SAM2 for video segmentation - load SAM2 for video processing - data preprocessing - segment and track one object - refine predictions - propagate prompts across video - segment and track multiple objects -... See more

SkalskiP x.com

Our computer vision textbook is now available for free online here: https://t.co/ERy2Spc7c2 We are working on adding some interactive components like search and (beta) integration with LLMs. Hope this is useful and feel free to submit Github issues to help us improve the text!

Phillip Isola x.com

Thumbnail of www-x-com-saboo-shubham-status-1930813656419438702-075be38ad8e7413e

Vector databases for AI memory just got replaced by MP4 files. Store millions of text chunks in MP4 files instead of expensive vector databases with lightning-fast semantic search. No database needed. 100% Opensource. https://t.co/iuIS5ElHsM

Shubham Saboo

x.com

OCR and document analysis toolkit https://t.co/7yChPCjagz

Tom Dörr

x.com

VideoDoodles: a great combination of modern CV techniques and clever HCI by @emxtyu & al @adobe (+ is now open source) project: https://t.co/Udm4Doo7bT paper: https://t.co/3Dv2APvcXP code: https://t.co/H3apwvrthK https://t.co/lKPYtDn7bk

Cyril Diagne x.com

Thumbnail of www-x-com-tom-doerr-status-1854999995507761594-febe95054a9646d1

"A Comprehensive Toolkit for High-Quality PDF Content Extraction" https://t.co/pzipx2Tawf

Tom Dörr

x.com