Improving Social Awareness Through DANTE: Deep Affinity Network for Clustering Conversational Interactants
Autor: | Sydney Thompson, Mason Swofford, Nathan Tsoi, Roberto Martín-Martín, Marynel Vázquez, John Charles Peruzzi, Silvio Savarese |
---|---|
Rok vydání: | 2020 |
Předmět: |
FOS: Computer and information sciences
Computer Networks and Communications Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Group detection 02 engineering and technology Machine learning computer.software_genre 0202 electrical engineering electronic engineering information engineering 0501 psychology and cognitive sciences Social consciousness Cluster analysis 050107 human factors Clustering coefficient Group (mathematics) business.industry Deep learning 05 social sciences Social environment Human-Computer Interaction 020201 artificial intelligence & image processing Artificial intelligence business computer Social Sciences (miscellaneous) |
Zdroj: | Proceedings of the ACM on Human-Computer Interaction. 4:1-23 |
ISSN: | 2573-0142 |
Popis: | We propose a data-driven approach to detect conversational groups by identifying spatial arrangements typical of these focused social encounters. Our approach uses a novel Deep Affinity Network (DANTE) to predict the likelihood that two individuals in a scene are part of the same conversational group, considering their social context. The predicted pair-wise affinities are then used in a graph clustering framework to identify both small (e.g., dyads) and large groups. The results from our evaluation on multiple, established benchmarks suggest that combining powerful deep learning methods with classical clustering techniques can improve the detection of conversational groups in comparison to prior approaches. Finally, we demonstrate the practicality of our approach in a human-robot interaction scenario. Our efforts show that our work advances group detection not only in theory, but also in practice. |
Databáze: | OpenAIRE |
Externí odkaz: |