Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909935095250944 |
|---|---|
| author | Tran, Quoc-Huy Ahmed, Muhammad Popattia, Murad Ahmed, M. Hassan Konin, Andrey Zia, M. Zeeshan |
| author_facet | Tran, Quoc-Huy Ahmed, Muhammad Popattia, Murad Ahmed, M. Hassan Konin, Andrey Zia, M. Zeeshan |
| contents | This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D skeleton coordinates are taken directly as input, our key idea is to use sequences of 2D skeleton heatmaps as input. Unlike CASA which performs self-attention in the temporal domain only, we feed 2D skeleton heatmaps to a video transformer which performs self-attention both in the spatial and temporal domains for extracting effective spatiotemporal and contextual features. In addition, we introduce simple heatmap augmentation techniques based on 2D skeletons for self-supervised learning. Despite the lack of 3D information, our approach achieves not only higher accuracy but also better robustness against missing and noisy keypoints than CASA. Furthermore, extensive evaluations on three public datasets, i.e., Penn Action, IKEA ASM, and H2O, demonstrate that our approach outperforms previous methods in different fine-grained human activity understanding tasks. Finally, fusing 2D skeleton heatmaps with RGB videos yields the state-of-the-art on all metrics and datasets. To our best knowledge, our work is the first to utilize 2D skeleton heatmap inputs and the first to explore multi-modality fusion for temporal video alignment. Our code and dataset are available on our research website: https://retrocausal.ai/research/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_19480 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion Tran, Quoc-Huy Ahmed, Muhammad Popattia, Murad Ahmed, M. Hassan Konin, Andrey Zia, M. Zeeshan Computer Vision and Pattern Recognition This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D skeleton coordinates are taken directly as input, our key idea is to use sequences of 2D skeleton heatmaps as input. Unlike CASA which performs self-attention in the temporal domain only, we feed 2D skeleton heatmaps to a video transformer which performs self-attention both in the spatial and temporal domains for extracting effective spatiotemporal and contextual features. In addition, we introduce simple heatmap augmentation techniques based on 2D skeletons for self-supervised learning. Despite the lack of 3D information, our approach achieves not only higher accuracy but also better robustness against missing and noisy keypoints than CASA. Furthermore, extensive evaluations on three public datasets, i.e., Penn Action, IKEA ASM, and H2O, demonstrate that our approach outperforms previous methods in different fine-grained human activity understanding tasks. Finally, fusing 2D skeleton heatmaps with RGB videos yields the state-of-the-art on all metrics and datasets. To our best knowledge, our work is the first to utilize 2D skeleton heatmap inputs and the first to explore multi-modality fusion for temporal video alignment. Our code and dataset are available on our research website: https://retrocausal.ai/research/. |
| title | Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2305.19480 |