paper-with-me

Papers

Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos

2025-02-25 · Luigi Seminara, Giovanni Maria Farinella, Antonino Furnari

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.

📄 PDF Abstract BibTeX arXiv:2502.17753

Code (1)

fpv-iplab/differentiable-task-graph-learning 공식 구현 pytorch

Tasks

Graph LearningMistake DetectionOnline Mistake DetectionTask Graph LearningVideo Understanding

Similar Papers 제목 키워드 기반

Composite Likelihood Estimation for Restricted Boltzmann machines

2014-06-24 · Muneki Yasuda, Shun Kataoka, Yuji Waizumi, Kazuyuki Tanaka

Learning the parameters of graphical models using the maximum likelihood estimation is generally hard which requires an approximation. Maximum composite likelihood estimations are statistical approximations of the maximu…

Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos

2024-06-03 · Luigi Seminara, Giovanni Maria Farinella, Antonino Furnari

Procedural activities are sequences of key-steps aimed at achieving specific goals. They are crucial to build intelligent agents able to assist users effectively. In this context, task graphs have emerged as a human-unde…

Mistake DetectionOnline Mistake DetectionTask Graph LearningVideo Understanding

Maximum likelihood thresholds of Gaussian graphical models and graphical lasso

2023-12-05 · Daniel Irving Bernstein, Hayden Outlaw

Associated to each graph G is a Gaussian graphical model. Such models are often used in high-dimensional settings, i.e. where there are relatively few data points compared to the number of variables. The maximum likeliho…

A local approach to estimation in discrete loglinear models

2015-04-21 · Helene Massam, Nanwei Wang

We consider two connected aspects of maximum likelihood estimation of the parameter for high-dimensional discrete graphical models: the existence of the maximum likelihood estimate (mle) and its computation. When the d…

Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood Estimation

2020-04-07 · Ke Li, Shichong Peng, Tianhao Zhang, Jitendra Malik

Many tasks in computer vision and graphics fall within the framework of conditional image synthesis. In recent years, generative adversarial nets (GANs) have delivered impressive advances in quality of synthesized images…

Image GenerationImage Super-ResolutionSuper-Resolution