Kinetics-700 is a video dataset of 650,000 clips that covers 700 human action classes. The videos include human-object interactions such as playing instruments, as well as human-human interactions such as shaking hands and hugging. Each action class has at least 700 video clips. Each clip is annotated with an action class and lasts approximately 10 seconds.
Variants: Kinetics-700
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Video Generation | DiT-XL/2 + CVAE-FT-SE | Improving the Diffusability of Autoencoders | 2025-02-20 |
| Image Clustering | TURTLE (CLIP + DINOv2) | Let Go of Your Labels … | 2024-06-11 |
Recent papers with results on this dataset: