Biased Action Recognition
Biased Action Recognition (BAR) dataset is a real-world image dataset categorized as six action classes which are biased to distinct places. The authors settle these six action classes by inspecting imSitu, which provides still action images from Google Image Search with action and place labels. In detail, the authors choose action classes where images for each of these candidate actions share common place characteristics. At the same time, the place characteristics of action class candidates should be distinct in order to classify the action only from place attributes. The select pairs are six typical action-place pairs: (Climbing, RockWall), (Diving, Underwater), (Fishing, WaterSurface), (Racing, APavedTrack), (Throwing, PlayingField),and (Vaulting, Sky).
Source: https://github.com/alinlab/BAR
Image Source: https://github.com/alinlab/BAR
Variants: BAR
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Action Recognition | DebiAN | Discover and Mitigate Unknown Biases … | 2022-07-20 |
| Action Recognition | OccamResNet | OccamNets: Mitigating Dataset Bias by … | 2022-04-05 |
| Action Recognition | BiaSwap | BiaSwap: Removing dataset bias with … | 2021-08-23 |
| Action Recognition | LfF | Learning from Failure: Training Debiased … | 2020-07-06 |
Recent papers with results on this dataset: