Learning to Visually Connect Actions and their Effects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Parmar, Paritosh, Peh, Eric, Fernando, Basura
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911967977930752
author Parmar, Paritosh
Peh, Eric
Fernando, Basura
author_facet Parmar, Paritosh
Peh, Eric
Fernando, Basura
contents We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in areas like task planning and learning from demonstration. We identify and explore two different aspects of the concept of CATE: Action Selection (AS) and Effect-Affinity Assessment (EAA), where video understanding models connect actions and effects at semantic and fine-grained levels, respectively. We design various baseline models for AS and EAA. Despite the intuitive nature of the task, we observe that models struggle, and humans outperform them by a large margin. Our experiments show that in solving AS and EAA, models learn intuitive properties like object tracking and pose encoding without explicit supervision. We demonstrate that CATE can be an effective self-supervised task for learning video representations from unlabeled videos. The study aims to showcase the fundamental nature and versatility of CATE, with the hope of inspiring advanced formulations and models.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10805
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to Visually Connect Actions and their Effects
Parmar, Paritosh
Peh, Eric
Fernando, Basura
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Robotics
We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in areas like task planning and learning from demonstration. We identify and explore two different aspects of the concept of CATE: Action Selection (AS) and Effect-Affinity Assessment (EAA), where video understanding models connect actions and effects at semantic and fine-grained levels, respectively. We design various baseline models for AS and EAA. Despite the intuitive nature of the task, we observe that models struggle, and humans outperform them by a large margin. Our experiments show that in solving AS and EAA, models learn intuitive properties like object tracking and pose encoding without explicit supervision. We demonstrate that CATE can be an effective self-supervised task for learning video representations from unlabeled videos. The study aims to showcase the fundamental nature and versatility of CATE, with the hope of inspiring advanced formulations and models.
title Learning to Visually Connect Actions and their Effects
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Robotics
url https://arxiv.org/abs/2401.10805