Repetitive Action Counting Dataset
Counting repetitive actions are widely seen in human activities such as physical exercise. Existing methods focus on performing repetitive action counting in short videos, which is tough for dealing with longer videos in more realistic scenarios. In the data-driven era, the degradation of such generalization capability is mainly attributed to the lack of long video datasets. To complement this margin, we introduce a new large-scale repetitive action counting dataset called RepCount covering a wide variety of video lengths, along with more realistic situations where action interruption or action inconsistencies occur in the video. Besides, we also provide a fine-grained annotation of the action cycles instead of just counting annotation along with a numerical value. Such a dataset contains 1451 videos with about 20000
annotations, which is more challenging. Furthermore, the dataset consists of two subsets namely Part-A and Part-B. The videos in Part-A are fetched from YouTube, while the others in Part-B record simulated physical examinations by junior school students and teachers.
Variants: RepCount
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Repetitive Action Counting | HTRM-Net | Repetitive Action Counting with Hybrid … | 2024-12-10 |
| Repetitive Action Counting | RepNet | A Short Note on Evaluating … | 2024-11-13 |
| Repetitive Action Counting | ESCounts | Every Shot Counts: Using Exemplars … | 2024-03-26 |
| Repetitive Action Counting | PoseRAC | PoseRAC: Pose Saliency Transformer for … | 2023-03-15 |
| Repetitive Action Counting | TransRAC | TransRAC: Encoding Multi-scale Temporal Correlation … | 2022-04-03 |
| Repetitive Action Counting | RepNet | Counting Out Time: Class Agnostic … | 2020-06-27 |
Recent papers with results on this dataset: