Sequence-Based Identification of First-Person Camera Wearers in Third-Person Views
This work addresses a key gap for applications like immersive learning and collaborative robotics by enabling better analysis of interactions between multiple camera wearers in shared environments.
The paper tackles the problem of identifying first-person camera wearers in third-person views by introducing a sequence-based method that combines motion cues and person re-identification, and it presents TF2025, an expanded dataset with synchronized first- and third-person views to address the underexplored interactions in multi-camera environments.
The increasing popularity of egocentric cameras has generated growing interest in studying multi-camera interactions in shared environments. Although large-scale datasets such as Ego4D and Ego-Exo4D have propelled egocentric vision research, interactions between multiple camera wearers remain underexplored-a key gap for applications like immersive learning and collaborative robotics. To bridge this, we present TF2025, an expanded dataset with synchronized first- and third-person views. In addition, we introduce a sequence-based method to identify first-person wearers in third-person footage, combining motion cues and person re-identification.