Dense-World/Sa2VA-Training download history
Dense-World/Sa2VA-Training is an image text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 480 times (81 in the last 7 days), and 25,462 times in total. It ranks #34,222 among datasets by monthly downloads.
This repository contains the code and data for the paper "Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos". 🏠 Project Page📜 arXiv 🧑💻 GitHub Sa2VA is the first unified model for the dense grounded understanding of both images and videos. Unlike existing multi-m