FineAction
Introduced by Liu et al. in FineAction: A Fine-Grained Video Dataset for Temporal Action Localization
FineAction contains 103K temporal instances of 106 action categories, annotated in 17K untrimmed videos. FineAction introduces new opportunities and challenges for temporal action localization, thanks to its distinct characteristics of fine action classes with rich diversity, dense annotations of multiple instances, and co-occurring actions of different classes.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
FineAction
|
ActionMamba
|
|||
|
FineAction
|
HAAN
|
|||
|
FineAction
|
MiniROAD
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
