The Kinetics-600 is a large-scale action recognition dataset which consists of around 480K videos from 600 action categories. The 480K videos are divided into 390K, 30K, 60K for training, validation and test sets, respectively. Each video in the dataset is a 10-second clip of action moment annotated from raw YouTube video. It is an extensions of the Kinetics-400 dataset.
Source: Learning to Localize Actions from MomentsBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Kinetics-600
|
InternVideo2-6B
|
|||
|
Kinetics-600 12 frames, 64x64
|
MAGVIT-v2
|
|||
|
Kinetics-600
|
CVRL
|
|||
|
Kinetics-600 12 frames, 64x64
|
W.A.L.T-L
|
|||
|
Kinetics-600 48 frames, 64x64
|
DVD-GAN
|
|||
|
Kinetics-600 12 frames, 128x128
|
DVD-GAN
|
|||
|
Kinetics-600
|
Florence
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
