Graph-Based Social Relation Reasoning (2020-07-15T00:00:00.000000Z)

TL;DR

A simpler, faster, and more accurate method named graph relational reasoning network (GR2N) for social relation recognition, which considers the paradigm of jointly inferring the relations by constructing a social relation graph.

Abstract

Human beings are fundamentally sociable -- that we generally organize our social lives in terms of relations with other people. Understanding social relations from an image has great potential for intelligent systems such as social chatbots and personal assistants. In this paper, we propose a simpler, faster, and more accurate method named graph relational reasoning network (GR2N) for social relation recognition. Different from existing methods which process all social relations on an image independently, our method considers the paradigm of jointly inferring the relations by constructing a social relation graph. Furthermore, the proposed GR2N constructs several virtual relation graphs to explicitly grasp the strong logical constraints among different types of social relations. Experimental results illustrate that our method generates a reasonable and consistent social relation graph and improves the performance in both accuracy and efficiency.

Authors

Jiwen Lu

18 papers

Jie Zhou

10 papers

Wanhua Li

4 papers

TL;DR

Abstract

Authors

References52 items

Graph-Based Kinship Reasoning Network

Relational Action Forecasting

BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation

An End-To-End Network for Generating Social Relationship Graphs

Stochastic Prediction of Multi-Agent Interactions from Partial Observations

Multi-Granularity Reasoning for Social Relation Recognition From Images

Graph-Based Global Reasoning Networks

How Powerful are Graph Neural Networks?

Relational Forward Models for Multi-Agent Learning

Deep Reasoning with Knowledge Graph for Social Relationship Understanding

Videos as Space-Time Region Graphs

Neural Relational Inference for Interacting Systems

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning

Graph Attention Networks

Dual-Glance Model for Deciphering Social Relationships

Discriminative Deep Metric Learning for Face and Kinship Verification

Inductive Representation Learning on Large Graphs

A Domain Based Approach to Social Relation Recognition

Neural Message Passing for Quantum Chemistry

Modeling Relational Data with Graph Convolutional Networks

Scene Graph Generation by Iterative Message Passing

YOLO9000: Better, Faster, Stronger

From Facial Expression Recognition to Interpersonal Relation Prediction

Semi-Supervised Classification with Graph Convolutional Networks

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Gated Graph Sequence Neural Networks

Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition

You Only Look Once: Unified, Real-Time Object Detection

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Joint inference of groups, events and human roles in aerial videos

Fast R-CNN

Beyond frontal faces: Improving Person Recognition using multiple cues

Adam: A Method for Stochastic Optimization

Person Re-identification by Video Ranking

ImageNet Large Scale Visual Recognition Challenge

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Spectral Networks and Locally Connected Networks on Graphs

What Do You Do? Occupation Recognition in a Photo via Social Context

Social Role Discovery in Human Events

Cost-Sensitive Subspace Analysis and Extensions for Face Recognition

Neighborhood repulsed metric learning for kinship verification

Social roles in hierarchical models for human activity recognition

Predicting occupation via human clothing and contexts

Seeing People in Social Context: Recognizing People and Social Relationships

A new model for learning in graph domains

The relationship context of human behavior and development.

Acquisition of the algorithms of social life: a domain-based approach.

The four elementary forms of sociality: framework for a unified theory of social relations.

A circumplex model for interpersonal personality traits.

Reconstruction-Based Metric Learning for Unconstrained Face Verification

The Graph Neural Network Model

Field of Study

Venue Information

Name

Type

URL

Alternate Names