Interaction-GCN: A Graph Convolutional Network based framework for social interaction recognition in egocentric videos
This addresses the problem of automated social interaction categorization for applications like assistive technology or surveillance, but it appears incremental as it builds on existing GCN and GRU methods.
The paper tackles social interaction recognition in egocentric videos by proposing InteractionGCN, a framework that extracts relational cues to build graphs and uses GCNs with GRUs for temporal propagation, achieving state-of-the-art results on two public datasets.
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.