EVUD

KO | EN

gitlite — search

#javascript #python #hacktoberfest #golang #machine-learning #docker #nodejs #java #windows #vue #pytorch #ios #openai #open-source

(★ 34)

Egocentric Video Understanding Dataset (EVUD)

EVUD 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<div align=center>
<h2 align="center"> <a href="https://arxiv.org/abs/2406.13807">Egocentric Video Understanding Dataset (EVUD)</a></h2>

[![arXiv](https://img.shields.io/badge/arXiv-2046.13807-b31b1b.svg)](https://arxiv.org/abs/2046-13807)

<h5 align="center"> If you like our project, please give us a star :star: on GitHub for the latest update.</h5>

</div>

## TL;DR
We introduce the Egocentric Video Understanding Dataset (EVUD), an instruction-tuning dataset for training VLMs on video captioning and question answering tasks specific to egocentric videos.

## News
- The AlanaVLM paper is now on arXiv! [![arXiv](https://img.shields.io/badge/arXiv-2046.13807-b31b1b.svg)](https://arxiv.org/abs/2046-13807)
- All the checkpoints developed for this project are available on [Hugging Face](https://huggingface.co/AlanaAI/AlanaVLM)
- The EVUD dataset is available on [Hugging Face](https://huggingface.co/datasets/AlanaAI/EVUD/)

## Prerequisites

Create and activate virtual environment:
```
python -m venv env
source venv/bin/activate
pip install -r requirements.txt
```

## Data generation
Together with our generated data released on HuggingFace, we are also releasing all the scripts to reproduce our data generation pipeline:
- [Ego4D VQA](ego4d_vqa/README.md)
- [Ego4D VQA Gemini](gemini/README.md)
- [EgoClip](egoclip/README.md)
- [VSR](vsr/README.md)
- [HM3D](hm3d/README.md)

The generated data follows the [LLaVa JSON format](https://github.com/haotian-liu/LLaVA/blob/main/docs/Finetune_Custom_Data.md).

EVUD

EVUD 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

EVUD

EVUD 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README