Detection of Free-Standing Conversational Groups with Graph Convolutional Networks
26th International Conference on Pattern Recognition, ICPR 2022, Montreal, Kanada, 21 - 25 Ağustos 2022, cilt.2022-August, ss.1041-1047, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 2022-August
- Doi Numarası: 10.1109/icpr56361.2022.9956536
- Basıldığı Şehir: Montreal
- Basıldığı Ülke: Kanada
- Sayfa Sayıları: ss.1041-1047
- Boğaziçi Üniversitesi Adresli: Evet
Özet
Automatically detecting conversational groups from video footage is an important research area with applications in social robotics, human-computer interaction, and video analysis. In this paper, we use a novel approach based on Graph Convolutional Networks (GCN) for the social group detection problem. We base our approach on a method from the community detection domain called Deep Modularity Networks (DMoN). As an input to the DMoN method, we construct a graph representation using body view frustums, which indicates affinities among the individuals. In addition to the frame-level group detector, the proposed system utilizes temporal information to improve the group detection accuracy. Experiments conducted on the standard benchmark dataset SALSA confirm that our GCN-based approach improves the group detection quality over state-of-the-art group detection methods.