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:this https URL.
View on arXiv@article{seminara2025_2502.17753,
title={ Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos },
author={ Luigi Seminara and Giovanni Maria Farinella and Antonino Furnari },
journal={arXiv preprint arXiv:2502.17753},
year={ 2025 }
}