Code and results for ICASSP2020 "VGGSound: A Large-scale Audio-Visual Dataset".
The repo contains the dataset file and our best audio classification model.
To download VGGSound, we provide a csv file. For each YouTube video, we provide YouTube URLs, time stamps, audio labels and train/test split. Each line in the csv file has columns defined by here.
# YouTube ID, start seconds, label,train/test split.
A helpful link for data download!
We detail the audio classfication results here.
- Pretrain refers whether the model was pretrained on YouTube-8M dataset.
- Dataset (common) means it is a subset of the dataset. This subset only contains data of common classes (listed here) between AudioSet and VGGSound.
- ASTest is the intersection of AudioSet and VGGSound testsets.
Model | Aggregation | Pretrain | Finetune/Train | Test | mAP | AUC | d-prime | |
---|---|---|---|---|---|---|---|---|
A | VGGish | \ | ✔️ | AudioSet (common) | ASTest | 0.286 | 0.899 | 1.803 |
B | VGGish | \ | ✔️ | VGGSound (common) | ASTest | 0.326 | 0.916 | 1.950 |
C | VGGish | \ | ❌ | VGGSound (common) | ASTest | 0.301 | 0.910 | 1.900 |
D | ResNet18 | AveragePool | ❌ | VGGSound (common) | ASTest | 0.328 | 0.923 | 2.024 |
E | ResNet18 | NetVLAD | ❌ | VGGSound (common) | ASTest | 0.369 | 0.927 | 2.058 |
F | ResNet18 | AveragePool | ❌ | VGGSound | ASTest | 0.404 | 0.944 | 2.253 |
G | ResNet18 | NetVLAD | ❌ | VGGSound | ASTest | 0.434 | 0.950 | 2.327 |
H | ResNet18 | AveragePool | ❌ | VGGSound | VGGSound | 0.516 | 0.968 | 2.627 |
I | ResNet18 | NetVLAD | ❌ | VGGSound | VGGSound | 0.512 | 0.970 | 2.660 |
- Python 3.6.8
- Pytorch 1.3.0
We provide the pretrained model H and model I here.
To test the model and generate prediction files,
python test.py --data_path "directory to audios/" --result_path "directory to predictions/" --summaries "path to pretrained models" --pool "avgpool"
To evaluate the model performance using the generated prediction files,
python eval.py --result_path "directory to predictions/"
@InProceedings{Chen20,
author = "Honglie Chen and Weidi Xie and Andrea Vedaldi and Andrew Zisserman",
title = "VGGSound: A Large-scale Audio-Visual Dataset",
booktitle = "International Conference on Acoustics, Speech, and Signal Processing (ICASSP)",
year = "2020",
}
The VGG-Sound dataset is available to download for commercial/research purposes under a Creative Commons Attribution 4.0 International License. The copyright remains with the original owners of the video. A complete version of the license can be found here.