RareAct is a video dataset of unusual actions, including actions like “blend phone”, “cut keyboard” and “microwave shoes”. It aims at evaluating the zero-shot and few-shot compositionality of action recognition models for unlikely compositions of common action verbs and object nouns. It contains 122 different actions which were obtained by combining verbs and nouns rarely co-occurring together in the large-scale textual corpus from HowTo100M, but that frequently appear separately.
Source: https://github.com/antoine77340/RareAct
Image Source: https://github.com/antoine77340/RareAct
Variants: RareAct
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Action Recognition | 🦩 Flamingo | Flamingo: a Visual Language Model … | 2022-04-29 |
| Action Recognition | CLIP | Learning Transferable Visual Models From … | 2021-02-26 |
| Action Recognition | HT100M S3D | End-to-End Learning of Visual Representations … | 2019-12-13 |
Recent papers with results on this dataset: