ARPGNet: Appearance- and Relation-aware Parallel Graph Attention Fusion Network for Facial Expression Recognition

• URL: http://arxiv.org/abs/2511.22188v1
• Date: Thu, 27 Nov 2025 07:54:34 GMT
• Title: ARPGNet: Appearance- and Relation-aware Parallel Graph Attention Fusion Network for Facial Expression Recognition
• Abstract summary: This paper presents an Appearance- and Relation-aware Parallel Graph attention fusion Network (ARPGNet) to learn mutually enhanced spatial-temporal representations of appearance and relation information.<n> Specifically, we construct a facial region relation graph and leverage the graph attention mechanism to model the relationships between facial regions.<n>The resulting relational representation sequences, along with CNN-based appearance representation sequences, are then fed into a parallel graph attention fusion module for mutual interaction and enhancement.
• Score: 17.573536098485274
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The key to facial expression recognition is to learn discriminative spatial-temporal representations that embed facial expression dynamics. Previous studies predominantly rely on pre-trained Convolutional Neural Networks (CNNs) to learn facial appearance representations, overlooking the relationships between facial regions. To address this issue, this paper presents an Appearance- and Relation-aware Parallel Graph attention fusion Network (ARPGNet) to learn mutually enhanced spatial-temporal representations of appearance and relation information. Specifically, we construct a facial region relation graph and leverage the graph attention mechanism to model the relationships between facial regions. The resulting relational representation sequences, along with CNN-based appearance representation sequences, are then fed into a parallel graph attention fusion module for mutual interaction and enhancement. This module simultaneously explores the complementarity between different representation sequences and the temporal dynamics within each sequence. Experimental results on three facial expression recognition datasets demonstrate that the proposed ARPGNet outperforms or is comparable to state-of-the-art methods.

Related papers

• Learning Spatial-Temporal Coherent Correlations for Speech-Preserving Facial Expression Manipulation [75.05465510260944]
  Speech-preserving facial expression manipulation (SPFEM) aims to modify facial emotions while meticulously maintaining the mouth animation associated with spoken content.<n>Current works depend on inaccessible paired training samples for the person, where two aligned frames exhibit the same speech content yet differ in emotional expression, limiting the SPFEM applications in real-world scenarios.<n>We propose a novel spatial-temporal coherent correlation learning (STCCL) algorithm, which models the aforementioned correlations as explicit metrics and integrates the metrics to supervise manipulating facial expression and meanwhile better preserving the facial animation of spoken content.
  arXiv  Detail & Related papers  (2026-04-22T06:20:10Z)
• Computer Vision based group activity detection and action spotting [0.0]
  Group activity detection in multi-person scenes is challenging due to complex human interactions and variations in appearance over time.<n>This work presents a computer vision based framework for group activity recognition and action spotting using a combination of deep learning models and graph based relational reasoning.
  arXiv  Detail & Related papers  (2025-11-17T12:52:22Z)
• Exp-Graph: How Connections Learn Facial Attributes in Graph-based Expression Recognition [0.6042269506496204]
  We propose Exp-Graph, a novel framework to represent the structural relationships among facial attributes.<n>For facial attributes graph representation, facial landmarks are used as the graph's vertices.<n>The edges are determined based on the proximity of the facial landmark and the similarity of the local appearance of the facial attributes encoded using the vision transformer.
  arXiv  Detail & Related papers  (2025-07-19T13:10:21Z)
• Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation [64.85974098314344]
  Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. Inherently, object pairs and their relationships enjoy spatial co-occurrence correlations within each image and temporal consistency/transition correlations across different images. We propose a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial-temporal knowledge into the multi-head cross-attention mechanism.
  arXiv  Detail & Related papers  (2023-09-23T02:40:28Z)
• Spatio-Temporal AU Relational Graph Representation Learning For Facial Action Units Detection [30.480103923317536]
  Our approach consists of three main modules. The graph representation describes AUs contained in all frames. Our model ranks at the 4th place in the AU recognition track at the 5th ABAW Competition.
  arXiv  Detail & Related papers  (2023-03-19T12:28:59Z)
• Self-Supervised Relation Alignment for Scene Graph Generation [44.3983804479146]
  We introduce a self-supervised relational alignment regularization to improve scene graph generation performance. The proposed alignment is general and can be combined with any existing scene graph generation framework. We illustrate the effectiveness of this self-supervised relational alignment in conjunction with two scene graph generation architectures.
  arXiv  Detail & Related papers  (2023-02-02T20:34:13Z)
• Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting [50.901984244738806]
  We show how to model the evolutionary and multi-scale interactions of time series. In particular, we first provide a hierarchical graph structure cooperated with the dilated convolution to capture the scale-specific correlations. A unified neural network is provided to integrate the components above to get the final prediction.
  arXiv  Detail & Related papers  (2022-06-28T08:11:12Z)
• Biphasic Face Photo-Sketch Synthesis via Semantic-Driven Generative Adversarial Network with Graph Representation Learning [40.544844623958426]
  We propose a novel Semantic-Driven Generative Adversarial Network to address the above issues. Considering that human faces have distinct spatial structures, we first inject class-wise semantic layouts into the generator. We construct two types of representational graphs via semantic parsing maps upon input faces, dubbed the IntrA-class Semantic Graph (IASG) and the InteR-class Structure Graph (IRSG)
  arXiv  Detail & Related papers  (2022-01-05T13:14:14Z)
• Exploiting Emotional Dependencies with Graph Convolutional Networks for Facial Expression Recognition [31.40575057347465]
  This paper proposes a novel multi-task learning framework to recognize facial expressions in-the-wild. A shared feature representation is learned for both discrete and continuous recognition in a MTL setting. The results of our experiments show that our method outperforms the current state-of-the-art methods on discrete FER.
  arXiv  Detail & Related papers  (2021-06-07T10:20:05Z)
• Heterogeneous Graph Representation Learning with Relation Awareness [45.14314180743549]
  We propose a Relation-aware Heterogeneous Graph Neural Network, namely R-HGNN, to learn node representations on heterogeneous graphs at a fine-grained level. A dedicated graph convolution component is first designed to learn unique node representations from each relation-specific graph. A cross-relation message passing module is developed to improve the interactions of node representations across different relations.
  arXiv  Detail & Related papers  (2021-05-24T07:01:41Z)
• Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos [78.45050529204701]
  We propose a novel framework to pursue discriminative and robust representation by modeling cross-scale spatial-temporal correlation. CTL utilizes a CNN backbone and a key-points estimator to extract semantic local features from human body. It explores a context-reinforced topology to construct multi-scale graphs by considering both global contextual information and physical connections of human body.
  arXiv  Detail & Related papers  (2021-04-15T14:32:12Z)
• Unified Graph Structured Models for Video Understanding [93.72081456202672]
  We propose a message passing graph neural network that explicitly models relational-temporal relations. We show how our method is able to more effectively model relationships between relevant entities in the scene.
  arXiv  Detail & Related papers  (2021-03-29T14:37:35Z)
• Variational Structured Attention Networks for Deep Visual Representation Learning [49.80498066480928]
  We propose a unified deep framework to jointly learn both spatial attention maps and channel attention in a principled manner. Specifically, we integrate the estimation and the interaction of the attentions within a probabilistic representation learning framework. We implement the inference rules within the neural network, thus allowing for end-to-end learning of the probabilistic and the CNN front-end parameters.
  arXiv  Detail & Related papers  (2021-03-05T07:37:24Z)
• InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs [73.27299786083424]
  We propose a framework called InterFaceGAN to interpret the disentangled face representation learned by state-of-the-art GAN models. We first find that GANs learn various semantics in some linear subspaces of the latent space. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection.
  arXiv  Detail & Related papers  (2020-05-18T18:01:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.