Social Relation Recognition From Videos via Multi-Scale Spatial-Temporal Reasoning

Xinchen Liu, Wu Liu, Meng Zhang, Jingwen Chen, Lianli Gao, Chenggang Yan, Tao Mei; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 3566-3574

Abstract


Discovering social relations, e.g., kinship, friendship, etc., from visual contents can make machines better interpret the behaviors and emotions of human beings. Existing studies mainly focus on recognizing social relations from still images while neglecting another important media--video. On one hand, the actions and storylines in videos provide more important cues for social relation recognition. On the other hand, the key persons may appear at arbitrary spatial-temporal locations, even not in one same image from beginning to the end. To overcome these challenges, we propose a Multi-scale Spatial-Temporal Reasoning (MSTR) framework to recognize social relations from videos. For the spatial representation, we not only adopt a temporal segment network to learn global action and scene information, but also design a Triple Graphs model to capture visual relations between persons and objects. For the temporal domain, we propose a Pyramid Graph Convolutional Network to perform temporal reasoning with multi-scale receptive fields, which can obtain both long-term and short-term storylines in videos. By this means, MSTR can comprehensively explore the multi-scale actions and storylines in spatial-temporal dimensions for social relation reasoning in videos. Extensive experiments on a new large-scale Video Social Relation dataset demonstrate the effectiveness of the proposed framework.

Related Material


[pdf]
[bibtex]
@InProceedings{Liu_2019_CVPR,
author = {Liu, Xinchen and Liu, Wu and Zhang, Meng and Chen, Jingwen and Gao, Lianli and Yan, Chenggang and Mei, Tao},
title = {Social Relation Recognition From Videos via Multi-Scale Spatial-Temporal Reasoning},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}