@saic-violet @egorzakharov Hello! Thank you so much for sharing. I'm really impressed with the great work!
I noticed that you mentioned in the paper you make a "VoxCeleb2-HQ" dataset from original VoxCeleb2, can you provide the contents VoxCeleb2-HQ has, such as the videos id or youtube link in original VoxCeleb2. I want to reproduce the higher quality VoxCeleb2-HQ dataset.
Chapter 4 Experiments
We also use a high-quality version of the same dataset, additionally annotated with the segmentation masks (which were obtained using a model [15]), to measure how the performance of our model scales with a dataset of a significantly higher quality. We obtained this version by downloading the original videos via the links provided in the VoxCeleb2 dataset, and filtering out the ones with low resolution. This dataset is, therefore, significantly smaller and contains only 14859 videos of 4242 people, with each video having at most 250 frames (first 10 seconds). Lastly, we do ablation studies on both VoxCeleb2 and VoxCeleb2-HQ.
@saic-violet @egorzakharov Hello! Thank you so much for sharing. I'm really impressed with the great work!
I noticed that you mentioned in the paper you make a "VoxCeleb2-HQ" dataset from original VoxCeleb2, can you provide the contents VoxCeleb2-HQ has, such as the videos id or youtube link in original VoxCeleb2. I want to reproduce the higher quality VoxCeleb2-HQ dataset.
Wish for your reply. Thanks again.