Actor and Observer: Joint Modeling of First and Third-Person Videos
This addresses a bottleneck in egocentric vision research by linking first-person data to abundant third-person sources, though it is incremental as it builds on existing cognitive theories and dataset creation methods.
The paper tackles the lack of paired first-person and third-person video data for human action recognition by introducing Charades-Ego, a dataset with 4000 paired videos from 112 people, and uses it to learn a joint representation that enables knowledge transfer from third-person to first-person domains.
Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and seamlessly transfer knowledge between third-person (observer) and first-person (actor). Despite this, learning such models for human action recognition has not been achievable due to the lack of data. This paper takes a step in this direction, with the introduction of Charades-Ego, a large-scale dataset of paired first-person and third-person videos, involving 112 people, with 4000 paired videos. This enables learning the link between the two, actor and observer perspectives. Thereby, we address one of the biggest bottlenecks facing egocentric vision research, providing a link from first-person to the abundant third-person data on the web. We use this data to learn a joint representation of first and third-person videos, with only weak supervision, and show its effectiveness for transferring knowledge from the third-person to the first-person domain.