Enregistré dans:
Détails bibliographiques
Auteurs principaux: Samel, Karan, Sontakke, Nitish, Essa, Irfan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2502.17352
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909508641488896
author Samel, Karan
Sontakke, Nitish
Essa, Irfan
author_facet Samel, Karan
Sontakke, Nitish
Essa, Irfan
contents Instructional videos provide a convenient modality to learn new tasks (ex. cooking a recipe, or assembling furniture). A viewer will want to find a corresponding video that reflects both the overall task they are interested in as well as contains the relevant steps they need to carry out the task. To perform this, an instructional video model should be capable of inferring both the tasks and the steps that occur in an input video. Doing this efficiently and in a generalizable fashion is key when compute or relevant video topics used to train this model are limited. To address these requirements we explicitly mine task hierarchies and the procedural steps associated with instructional videos. We use this prior knowledge to pre-train our model, $\texttt{Pivot}$, for step and task prediction. During pre-training, we also provide video augmentation and early stopping strategies to optimally identify which model to use for downstream tasks. We test this pre-trained model on task recognition, step recognition, and step prediction tasks on two downstream datasets. When pre-training data and compute are limited, we outperform previous baselines along these tasks. Therefore, leveraging prior task and step structures enables efficient training of $\texttt{Pivot}$ for instructional video recommendation.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17352
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Procedural Knowledge and Task Hierarchies for Efficient Instructional Video Pre-training
Samel, Karan
Sontakke, Nitish
Essa, Irfan
Computer Vision and Pattern Recognition
Instructional videos provide a convenient modality to learn new tasks (ex. cooking a recipe, or assembling furniture). A viewer will want to find a corresponding video that reflects both the overall task they are interested in as well as contains the relevant steps they need to carry out the task. To perform this, an instructional video model should be capable of inferring both the tasks and the steps that occur in an input video. Doing this efficiently and in a generalizable fashion is key when compute or relevant video topics used to train this model are limited. To address these requirements we explicitly mine task hierarchies and the procedural steps associated with instructional videos. We use this prior knowledge to pre-train our model, $\texttt{Pivot}$, for step and task prediction. During pre-training, we also provide video augmentation and early stopping strategies to optimally identify which model to use for downstream tasks. We test this pre-trained model on task recognition, step recognition, and step prediction tasks on two downstream datasets. When pre-training data and compute are limited, we outperform previous baselines along these tasks. Therefore, leveraging prior task and step structures enables efficient training of $\texttt{Pivot}$ for instructional video recommendation.
title Leveraging Procedural Knowledge and Task Hierarchies for Efficient Instructional Video Pre-training
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.17352