UNDERSTANDING HUMAN INTERACTION USING GRAPH NEURAL NETWORKS: AN OVERVIEW
Ключевые слова:
GNNs, human interaction understanding, graph-based interaction modeling, action recognition.Аннотация
Understanding human interaction is a fundamental challenge in various fields such as social sciences, psychology, and artificial intelligence. In recent years, Graph Neural Networks (GNNs) have emerged as powerful tools for modeling complex relationships in graph-structured data. This paper explores the application of GNNs in understanding human interaction, aiming to overcome the limitations of traditional shallow graphical models. The unique capabilities of GNNs in capturing intricate patterns and dynamics inherent in human interactions have been discussed.
Библиографические ссылки
W. Sultani, C. Chen, and M. Shah. Real-world anomaly detection in surveillance videos. In CVPR, 2018.
Z. Gao, G. Hua, D. Zhang, N. Jojic, L. Wang, J. Xue, and N. Zheng. Er3: A unified framework for event retrieval, recognition and recounting. In CVPR, 2017.
T. Bagautdinov, A. Alahi, F. Fleuret, P. Fua, and S. Savarese. Social scene understanding: End-to-end multi-person action localization and collective activity recognition. In CVPR, 2017.
M. Qi, J. Qin, A. Li, Y. Wang, J. Luo, and L. Gool. stagnet: An attentive semantic rnn for group activity recognition. In ECCV, 2018.
W. Choi, K. Shahid, and S. Savarese. Learning context for collective activity recognition. In CVPR, 2011.
A. Patron-Perez, M. Marszalek, I. Reid, and A. Zisserman. Structured learning of human interactions in tv shows. IEEE Trans. Pattern Anal. Mach. Intell., 34(12):2441–2453, 2012.
S. Ji, W. Xu, M. Yang, and K. Yu. 3d convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell., 35(1):221–231, 2013.
K. Simonyan and A. Zisserman. Two-stream convolutional networks for action recognition in videos. In NeurIPS, 2014.
Z. Wang, S. Liu, J. Zhang, S. Chen, and Q. Guan. A spatiotemporal crf for human interaction understanding. IEEE Trans. Circuits Syst. Video Technol., 2016.
Z. Wang, T. Liu, Q. Shi, M. Kumar, and J. Zhang. New convex relaxations for MRF inference with unknown graphs. In ICCV, 2019.
Wang, Z., Meng, J., Guo, D., Zhang, J., Shi, J. Q., & Chen, S. (2021). Consistency-aware graph network for human interaction understanding. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 13369-13378).
R. Pramono, Y. Chen, and W. Fang. Empowering relational network by self-attention augmented conditional random fields for group activity recognition. In ECCV, 2020.
Liang, Z., Liu, J., Guan, Y., & Rojas, J. (2021, December). Visual-semantic graph attention networks for human-object interaction detection. In 2021 IEEE international conference on robotics and biomimetics (ROBIO) (pp. 1441-1447). IEEE.
Ulutan, O., Iftekhar, A. S. M., & Manjunath, B. S. (2020). Vsgnet: Spatial attention network for detecting human object interactions using graph convolutions. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 13617-13626).






