English

Sequence-Based Identification of First-Person Camera Wearers in Third-Person Views

Computer Vision and Pattern Recognition 2025-06-03 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2506.00394,
  title  = {Sequence-Based Identification of First-Person Camera Wearers in Third-Person Views},
  author = {Ziwei Zhao and Xizi Wang and Yuchen Wang and Feng Cheng and David Crandall},
  journal= {arXiv preprint arXiv:2506.00394},
  year   = {2025}
}
R2 v1 2026-07-01T02:52:01.923Z