Unsupervised Temporal Adaptation in Skeleton-Based Human Action Recognition
With deep learning approaches, the fundamental assumption of data availability can be severely compromised when a model trained on a source domain is transposed to a target application domain where data are unlabeled, making supervised fine-tuning mostly impossible. To overcome this limitation, the...
| الحاوية / القاعدة: | Algorithms |
|---|---|
| المؤلفون الرئيسيون: | , |
| التنسيق: | مقال |
| اللغة: | الإنجليزية |
| منشور في: |
MDPI AG
2024-12-01
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://www.mdpi.com/1999-4893/17/12/581 |