Learning Human Motion with Temporally Conditional Mamba
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917013176188928 |
|---|---|
| author | Nguyen, Quang Le, Tri Huang, Baoru Vu, Minh Nhat Le, Ngan Vo, Thieu Nguyen, Anh |
| author_facet | Nguyen, Quang Le, Tri Huang, Baoru Vu, Minh Nhat Le, Ngan Vo, Thieu Nguyen, Anh |
| contents | Learning human motion based on a time-dependent input signal presents a challenging yet impactful task with various applications. The goal of this task is to generate or estimate human movement that consistently reflects the temporal patterns of conditioning inputs. Existing methods typically rely on cross-attention mechanisms to fuse the condition with motion. However, this approach primarily captures global interactions and struggles to maintain step-by-step temporal alignment. To address this limitation, we introduce Temporally Conditional Mamba, a new mamba-based model for human motion generation. Our approach integrates conditional information into the recurrent dynamics of the Mamba block, enabling better temporally aligned motion. To validate the effectiveness of our method, we evaluate it on a variety of human motion tasks. Extensive experiments demonstrate that our model significantly improves temporal alignment, motion realism, and condition consistency over state-of-the-art approaches. Our project page is available at https://zquang2202.github.io/TCM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12573 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Human Motion with Temporally Conditional Mamba Nguyen, Quang Le, Tri Huang, Baoru Vu, Minh Nhat Le, Ngan Vo, Thieu Nguyen, Anh Computer Vision and Pattern Recognition Learning human motion based on a time-dependent input signal presents a challenging yet impactful task with various applications. The goal of this task is to generate or estimate human movement that consistently reflects the temporal patterns of conditioning inputs. Existing methods typically rely on cross-attention mechanisms to fuse the condition with motion. However, this approach primarily captures global interactions and struggles to maintain step-by-step temporal alignment. To address this limitation, we introduce Temporally Conditional Mamba, a new mamba-based model for human motion generation. Our approach integrates conditional information into the recurrent dynamics of the Mamba block, enabling better temporally aligned motion. To validate the effectiveness of our method, we evaluate it on a variety of human motion tasks. Extensive experiments demonstrate that our model significantly improves temporal alignment, motion realism, and condition consistency over state-of-the-art approaches. Our project page is available at https://zquang2202.github.io/TCM. |
| title | Learning Human Motion with Temporally Conditional Mamba |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.12573 |