jun-pu / pav-sod Goto Github PK

View Code? Open in Web Editor NEW

29.0 2.0 7.0 10.46 MB

Panoramic audiovisual salient object segmentation

Python 100.00%

pav-sod's Issues

Is paper publicly available? If yes, can you provide a link? Many thanks.

The audios of provided videos are not ambisonic technically.

The channels of provided audios extracted by ffmpeg are 2 (should be 4, at least).

The audios are stereo technically since the paired videos are downloaded from youtube.

Question about the difference between PAVS10K and ASOD60k

Hi, thanks for your wanderful repo to share the paronamic video dataset. I am a little bit confused about the difference between PAVS10K and ASOD60k dataset. Also, could you please tell me where to download the ASOD60k dataset? Thanks! : )

WAV file

Hi, thanks for your great work!

Could you provide the 'ambisonics_trimmed' (.wav) audio files, please? It seems to include 4 channels.

Thanks!

WAV files

Hi, thanks for your share the PAVSOD dataset.
Could you share the 'ambisonics_trimmed' (.wav) audio files, please?
It seems to have 4 channels in data.py. I tried to convert the .mp4 file to .wav file, but I only got 2 channels
Thanks!

Recommend Projects