Learning State-Aware Visual Representations from Audible Interactions
This work addresses the problem of learning state-aware representations for robotics and AI systems that interact with dynamic environments, though it is incremental by building on existing multi-modal frameworks.
The paper tackles the challenge of learning effective visual representations from uncurated egocentric videos by leveraging audio signals to identify interaction moments and proposing a self-supervised objective for state changes, resulting in improvements on downstream tasks like action recognition and object state change classification across two large datasets.
We propose a self-supervised algorithm to learn representations from egocentric video data. Recently, significant efforts have been made to capture humans interacting with their own environments as they go about their daily activities. In result, several large egocentric datasets of interaction-rich multi-modal data have emerged. However, learning representations from videos can be challenging. First, given the uncurated nature of long-form continuous videos, learning effective representations require focusing on moments in time when interactions take place. Second, visual representations of daily activities should be sensitive to changes in the state of the environment. However, current successful multi-modal learning frameworks encourage representation invariance over time. To address these challenges, we leverage audio signals to identify moments of likely interactions which are conducive to better learning. We also propose a novel self-supervised objective that learns from audible state changes caused by interactions. We validate these contributions extensively on two large-scale egocentric datasets, EPIC-Kitchens-100 and the recently released Ego4D, and show improvements on several downstream tasks, including action recognition, long-term action anticipation, and object state change classification.