# Social Relation Recognition in Egocentric Photostreams

## TL;DR

This paper introduces a deep learning approach for automatically recognizing social interactions in egocentric photo streams, leveraging social theories and hierarchical label structures to improve categorization accuracy.

## Contribution

It presents a novel deep learning architecture that exploits hierarchical social relation labels and frame-level social attributes for better social interaction recognition.

## Key findings

- Effective social relation classification on EgoSocialRelation dataset
- Hierarchical label structure improves recognition accuracy
- Social attributes enhance semantic understanding of interactions

## Abstract

This paper proposes an approach to automatically categorize the social interactions of a user wearing a photo-camera 2fpm, by relying solely on what the camera is seeing. The problem is challenging due to the overwhelming complexity of social life and the extreme intra-class variability of social interactions captured under unconstrained conditions. We adopt the formalization proposed in Bugental's social theory, that groups human relations into five social domains with related categories. Our method is a new deep learning architecture that exploits the hierarchical structure of the label space and relies on a set of social attributes estimated at frame level to provide a semantic representation of social interactions. Experimental results on the new EgoSocialRelation dataset demonstrate the effectiveness of our proposal.