Object Aware Egocentric Online Action Detection
This work addresses the gap in action detection for egocentric videos, which is important for applications like augmented reality and assisted living, but it is incremental as it builds on existing OAD frameworks.
The paper tackled the problem of adapting Online Action Detection (OAD) methods from exocentric to egocentric videos by introducing an Object-Aware Module that integrates egocentric-specific priors, resulting in consistent performance enhancements validated on the Epic-Kitchens 100 dataset.
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.