In order to create the TED-talks dataset, 3,035 YouTube videos were downloaded using the "TED talks" query. From these initial candidates, videos in which the upper part of the person is visible for at least 64 frames, and the height of the person bounding box was at least 384 pixels were selected. Static videos were manually filtered out and videos in which a person is doing something other than presenting.
Image source: https://arxiv.org/pdf/2104.11280v1.pdf
Variants: TED-talks
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Video Reconstruction | Siarohin et al. | Motion Representations for Articulated Animation | 2021-04-22 |
| Video Reconstruction | FOMM | Motion Representations for Articulated Animation | 2021-04-22 |
Recent papers with results on this dataset: