Human Social Interaction Modeling Using Temporal Deep Networks

TL;DR

This paper introduces a new dataset and a deep learning model for analyzing social interactions, successfully detecting and generating social predicates like engagement with high accuracy, advancing computational social behavior understanding.

Contribution

It presents a novel dataset and a joint DCRBM model that detects and generates social interaction predicates, providing new insights into social behavior modeling.

Findings

Achieved 76%-49% accuracy in ESIP detection

Generated data with mean square error 0.01-0.1

Uncovered actionable behaviors underlying social predicates

Abstract

We present a novel approach to computational modeling of social interactions based on modeling of essential social interaction predicates (ESIPs) such as joint attention and entrainment. Based on sound social psychological theory and methodology, we collect a new "Tower Game" dataset consisting of audio-visual capture of dyadic interactions labeled with the ESIPs. We expect this dataset to provide a new avenue for research in computational social interaction modeling. We propose a novel joint Discriminative Conditional Restricted Boltzmann Machine (DCRBM) model that combines a discriminative component with the generative power of CRBMs. Such a combination enables us to uncover actionable constituents of the ESIPs in two steps. First, we train the DCRBM model on the labeled data and get accurate (76\%-49\% across various ESIPs) detection of the predicates. Second, we exploit the generative capability of DCRBMs to activate the trained model so as to generate the lower-level data corresponding to the specific ESIP that closely matches the actual training data (with mean square error 0.01-0.1 for generating 100 frames). We are thus able to decompose the ESIPs into their constituent actionable behaviors. Such a purely computational determination of how to establish an ESIP such as engagement is unprecedented.