The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 10s and is taken from a different YouTube video. The actions are human focussed and cover a broad range of classes including human-object interactions such as playing instruments, as well as human-human interactions such as shaking hands.
Source: https://arxiv.org/abs/1705.06950Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Kinetics-400
|
InternVideo2-6B
|
|||
|
Kinetics-400
|
CVRL
|
|||
|
Kinetics-400
|
CAST-B/16
|
|||
|
Kinetics-400
|
CASTANET+ Ensemble
|
|||
|
Kinetics-400
|
CASTANET+ Ensemble
|
|||
|
Kinetics-400
|
STGAT
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
Tasks
Similar Datasets
Similar Datasets
Source: https://arxiv.org/abs/1705.06950.
