Visible to the public Facial Expression Recognition Using Spatial-Temporal Semantic Graph Network

TitleFacial Expression Recognition Using Spatial-Temporal Semantic Graph Network
Publication TypeConference Paper
Year of Publication2020
AuthorsZhou, J., Zhang, X., Liu, Y., Lan, X.
Conference Name2020 IEEE International Conference on Image Processing (ICIP)
Date PublishedOct. 2020
PublisherIEEE
ISBN Number978-1-7281-6395-6
KeywordsAction Units, convolution, dynamic patterns, end-to-end feature learning, face recognition, facial expression recognition, facial expression recognition algorithm, Facial Graph Representation, facial recognition, facial topology structure, feature extraction, Geometry, graph theory, Heuristic algorithms, Human Behavior, image motion analysis, learning (artificial intelligence), Metrics, Neural networks, pubcrawl, resilience, Resiliency, Semantics, spatial patterns, Spatial Temporal Graph Convolutional Network, spatial-temporal semantic graph network, temporal patterns
Abstract

Motions of facial components convey significant information of facial expressions. Although remarkable advancement has been made, the dynamic of facial topology has not been fully exploited. In this paper, a novel facial expression recognition (FER) algorithm called Spatial Temporal Semantic Graph Network (STSGN) is proposed to automatically learn spatial and temporal patterns through end-to-end feature learning from facial topology structure. The proposed algorithm not only has greater discriminative power to capture the dynamic patterns of facial expression and stronger generalization capability to handle different variations but also higher interpretability. Experimental evaluation on two popular datasets, CK+ and Oulu-CASIA, shows that our algorithm achieves more competitive results than other state-of-the-art methods.

URLhttps://ieeexplore.ieee.org/document/9191181
DOI10.1109/ICIP40778.2020.9191181
Citation Keyzhou_facial_2020