English

Interaction-GCN: A Graph Convolutional Network based framework for social interaction recognition in egocentric videos

Computer Vision and Pattern Recognition 2021-06-09 v2

Abstract

In this paper we propose a new framework to categorize social interactions in egocentric videos, we named InteractionGCN. Our method extracts patterns of relational and non-relational cues at the frame level and uses them to build a relational graph from which the interactional context at the frame level is estimated via a Graph Convolutional Network based approach. Then it propagates this context over time, together with first-person motion information, through a Gated Recurrent Unit architecture. Ablation studies and experimental evaluation on two publicly available datasets validate the proposed approach and establish state of the art results.

Keywords

Cite

@article{arxiv.2104.14007,
  title  = {Interaction-GCN: A Graph Convolutional Network based framework for social interaction recognition in egocentric videos},
  author = {Simone Felicioni and Mariella Dimiccoli},
  journal= {arXiv preprint arXiv:2104.14007},
  year   = {2021}
}

Comments

Accepted to ICIP 2021

R2 v1 2026-06-24T01:36:50.118Z