Object Aware Egocentric Online Action Detection

TL;DR

This paper introduces an Object-Aware Module for egocentric online action detection, leveraging object-specific priors and temporal dynamics to improve scene understanding and action detection in first-person videos.

Contribution

It presents a novel Object-Aware Module tailored for egocentric videos, enhancing existing online action detection frameworks with minimal overhead.

Findings

Improved action detection accuracy on Epic-Kitchens 100 dataset.

Seamless integration with existing models with minimal computational overhead.

Consistent performance improvements across various scenarios.

Abstract

Advancements in egocentric video datasets like Ego4D, EPIC-Kitchens, and Ego-Exo4D have enriched the study of first-person human interactions, which is crucial for applications in augmented reality and assisted living. Despite these advancements, current Online Action Detection methods, which efficiently detect actions in streaming videos, are predominantly designed for exocentric views and thus fail to capitalize on the unique perspectives inherent to egocentric videos. To address this gap, we introduce an Object-Aware Module that integrates egocentric-specific priors into existing OAD frameworks, enhancing first-person footage interpretation. Utilizing object-specific details and temporal dynamics, our module improves scene understanding in detecting actions. Validated extensively on the Epic-Kitchens 100 dataset, our work can be seamlessly integrated into existing models with minimal overhead and bring consistent performance enhancements, marking an important step forward in adapting action detection systems to egocentric video analysis.