Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos
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_ | 1866912246902292480 |
|---|---|
| author | Seminara, Luigi Farinella, Giovanni Maria Furnari, Antonino |
| author_facet | Seminara, Luigi Farinella, Giovanni Maria Furnari, Antonino |
| contents | We introduce a gradient-based approach for learning task graphs from procedural activities, improving over hand-crafted methods. Our method directly optimizes edge weights via maximum likelihood, enabling integration into neural architectures. We validate our approach on CaptainCook4D, EgoPER, and EgoProceL, achieving +14.5%, +10.2%, and +13.6% F1-score improvements. Our feature-based approach for predicting task graphs from textual/video embeddings demonstrates emerging video understanding abilities. We also achieved top performance on the procedure understanding benchmark on Ego-Exo4D and significantly improved online mistake detection (+19.8% on Assembly101-O, +6.4% on EPIC-Tent-O). Code: https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17753 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos Seminara, Luigi Farinella, Giovanni Maria Furnari, Antonino Computer Vision and Pattern Recognition We introduce a gradient-based approach for learning task graphs from procedural activities, improving over hand-crafted methods. Our method directly optimizes edge weights via maximum likelihood, enabling integration into neural architectures. We validate our approach on CaptainCook4D, EgoPER, and EgoProceL, achieving +14.5%, +10.2%, and +13.6% F1-score improvements. Our feature-based approach for predicting task graphs from textual/video embeddings demonstrates emerging video understanding abilities. We also achieved top performance on the procedure understanding benchmark on Ego-Exo4D and significantly improved online mistake detection (+19.8% on Assembly101-O, +6.4% on EPIC-Tent-O). Code: https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning. |
| title | Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.17753 |