3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in online-mistake-detection-5
No benchmarks available.
Use these libraries to find online-mistake-detection-5 models and implementations
No datasets available.
No subtasks available.
This work proposes PREGO, the first online one-class classification model for mistake detection in PRocedural EGOcentric videos, based on an online action recognition component to model the current action, and a symbolic reasoning module to predict the next actions.
This paper proposes an approach based on direct maximum likelihood optimization of edges' weights, which allows gradient-based learning of task graphs and can be naturally plugged into neural network architectures and introduces a feature-based approach, aiming to predict task graphs from key-step textual or video embeddings.
Adding a benchmark result helps the community track progress.