Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.24690 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915313695588352 |
|---|---|
| author | Peirone, Simone Alberto Pistilli, Francesca Alliegro, Antonio Tommasi, Tatiana Averta, Giuseppe |
| author_facet | Peirone, Simone Alberto Pistilli, Francesca Alliegro, Antonio Tommasi, Tatiana Averta, Giuseppe |
| contents | Our comprehension of video streams depicting human activities is naturally multifaceted: in just a few moments, we can grasp what is happening, identify the relevance and interactions of objects in the scene, and forecast what will happen soon, everything all at once. To endow autonomous systems with such holistic perception, learning how to correlate concepts, abstract knowledge across diverse tasks, and leverage tasks synergies when learning novel skills is essential. In this paper, we introduce Hier-EgoPack, a unified framework able to create a collection of task perspectives that can be carried across downstream tasks and used as a potential source of additional insights, as a backpack of skills that a robot can carry around and use when needed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24690 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning reusable concepts across different egocentric video understanding tasks Peirone, Simone Alberto Pistilli, Francesca Alliegro, Antonio Tommasi, Tatiana Averta, Giuseppe Computer Vision and Pattern Recognition Our comprehension of video streams depicting human activities is naturally multifaceted: in just a few moments, we can grasp what is happening, identify the relevance and interactions of objects in the scene, and forecast what will happen soon, everything all at once. To endow autonomous systems with such holistic perception, learning how to correlate concepts, abstract knowledge across diverse tasks, and leverage tasks synergies when learning novel skills is essential. In this paper, we introduce Hier-EgoPack, a unified framework able to create a collection of task perspectives that can be carried across downstream tasks and used as a potential source of additional insights, as a backpack of skills that a robot can carry around and use when needed. |
| title | Learning reusable concepts across different egocentric video understanding tasks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.24690 |