https://github.com/Ego4DSounds/Ego4DSounds

Ego4DSounds: A diverse egocentric dataset with high action-audio correspondence
https://github.com/Ego4DSounds/Ego4DSounds

Last synced: 3 months ago
JSON representation

Ego4DSounds: A diverse egocentric dataset with high action-audio correspondence

• Host: GitHub
• URL: https://github.com/Ego4DSounds/Ego4DSounds
• Owner: Ego4DSounds
• Created: 2024-06-14T08:26:42.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-06-14T18:49:02.000Z (5 months ago)
• Last Synced: 2024-07-12T01:27:01.007Z (4 months ago)
• Language: Python
• Size: 3.95 MB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Video-Robotic-Papers - Code

README

        
# Ego4DSounds

Ego4DSounds is a subset of Ego4D, an existing large-scale egocentric video dataset. Videos have a high action-audio correspondence, making it a high-quality dataset for action-to-sound generation.

[Explore the dataset](https://ego4dsounds.github.io/)

## Action2Sound

Dataset introduced in _"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos"_.

Action2Sound is an ambient-aware approach that disentangles the action sound from the ambient sound, allowing successful generation after training with diverse in-the-wild data, as well as controllable conditioning on ambient sound levels.

![action2sound](https://github.com/Ego4DSounds/Ego4DSounds/assets/59634524/40a9d037-9134-4edc-82a5-1d81c6bbb40c)

[Explore the project](https://vision.cs.utexas.edu/projects/action2sound/)

## Contents

This repository contains scripts for processing the Ego4DSounds dataset. It includes functionality for loading video and audio data and extracting clips using metadata.

- `extract_ego4d_clips.py`: Extracts clips from the Ego4D dataset

- `dataset.py`: Defines the Ego4DSounds dataset class for loading and processing video and audio clips

- Metadata files: `train_clips_1.2m.csv`, `test_clips_11k.csv`, `ego4d.json`

Each row in the csv files has the following columns

```

video_uid, video_dur, narration_source, narration_ind, narration_time, clip_start, clip_end, clip_text, tag_verb, tag_noun, positive, clip_file, speech, background_music, traffic_noise, wind_noise

```

## BibTeX

```

@article{chen2024action2sound,

  title = {Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos},

  author = {Changan Chen and Puyuan Peng and Ami Baid and Sherry Xue and Wei-Ning Hsu and David Harwath and Kristen Grauman},

  year = {2024},

  journal = {arXiv},

}

```