Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2307.02730 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911831645224960 |
|---|---|
| author | Liu, Sheng-Lan Ding, Yu-Ning Yan, Gang Zhang, Si-Fan Zhang, Jin-Rong Chen, Wen-Yue Xu, Xue-Hai |
| author_facet | Liu, Sheng-Lan Ding, Yu-Ning Yan, Gang Zhang, Si-Fan Zhang, Jin-Rong Chen, Wen-Yue Xu, Xue-Hai |
| contents | The fine-grained action analysis of the existing action datasets is challenged by insufficient action categories, low fine granularities, limited modalities, and tasks. In this paper, we propose a Multi-modality and Multi-task dataset of Figure Skating (MMFS) which was collected from the World Figure Skating Championships. MMFS, which possesses action recognition and action quality assessment, captures RGB, skeleton, and is collected the score of actions from 11671 clips with 256 categories including spatial and temporal labels. The key contributions of our dataset fall into three aspects as follows. (1) Independently spatial and temporal categories are first proposed to further explore fine-grained action recognition and quality assessment. (2) MMFS first introduces the skeleton modality for complex fine-grained action quality assessment. (3) Our multi-modality and multi-task dataset encourage more action analysis models. To benchmark our dataset, we adopt RGB-based and skeleton-based baseline methods for action recognition and action quality assessment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_02730 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Fine-grained Action Analysis: A Multi-modality and Multi-task Dataset of Figure Skating Liu, Sheng-Lan Ding, Yu-Ning Yan, Gang Zhang, Si-Fan Zhang, Jin-Rong Chen, Wen-Yue Xu, Xue-Hai Computer Vision and Pattern Recognition Artificial Intelligence The fine-grained action analysis of the existing action datasets is challenged by insufficient action categories, low fine granularities, limited modalities, and tasks. In this paper, we propose a Multi-modality and Multi-task dataset of Figure Skating (MMFS) which was collected from the World Figure Skating Championships. MMFS, which possesses action recognition and action quality assessment, captures RGB, skeleton, and is collected the score of actions from 11671 clips with 256 categories including spatial and temporal labels. The key contributions of our dataset fall into three aspects as follows. (1) Independently spatial and temporal categories are first proposed to further explore fine-grained action recognition and quality assessment. (2) MMFS first introduces the skeleton modality for complex fine-grained action quality assessment. (3) Our multi-modality and multi-task dataset encourage more action analysis models. To benchmark our dataset, we adopt RGB-based and skeleton-based baseline methods for action recognition and action quality assessment. |
| title | Fine-grained Action Analysis: A Multi-modality and Multi-task Dataset of Figure Skating |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2307.02730 |