mlsanityData to 7 Oct 2026

Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition

arXiv 2109.07270 ↗First posted 15 Sep 2021cs.CVcited by 55

Not on the map. Why?

Abstract (arXiv)

We present a novel facial expression recognition network, called Distract your Attention Network (DAN). Our method is based on two key observations. Firstly, multiple classes share inherently similar underlying facial appearance, and their differences could be subtle. Secondly, facial expressions exhibit themselves through multiple facial regions simultaneously, and the recognition requires a holistic approach by encoding high-order interactions among local features. To address these issues, we propose our DAN with three key components: Feature Clustering Network (FCN), Multi-head cross Attention Network (MAN), and Attention Fusion Network (AFN). The FCN extracts robust features by adopting a large-margin learning objective to maximize class separability. In addition, the MAN instantiates a number of attention heads to simultaneously attend to multiple facial areas and build attention maps on these regions. Further, the AFN distracts these attentions to multiple locations before fusing the attention maps to a comprehensive one. Extensive experiments on three public datasets (including AffectNet, RAF-DB, and SFEW 2.0) verified that the proposed method consistently achieves state-of-the-art facial expression recognition performance. Code will be made available at https://github.com/yaoing/DAN.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). Builds on 27 of its 66 references that are in the map. First posted on arXiv 15 Sep 2021.

Builds on

27 of 66 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  7. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  8. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  9. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  10. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  11. 2020FcaNet: Frequency Channel Attention Networkscited by 177
  12. 2019RetinaFace: Single-stage Dense Face Localisation in the Wildcited by 164
15 more
  1. 2020Suppressing Uncertainties for Large-Scale Facial Expression Recognitioncited by 157
  2. 2019Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognitioncited by 127
  3. 2020Rotate to Attend: Convolutional Triplet Attention Modulecited by 75
  4. 2021Facial expression and attributes recognition based on multi-task learning of lightweight neural networkscited by 40
  5. 2017Island Loss for Learning Discriminative Features in Facial Expression Recognitioncited by 35
  6. 2019Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networkscited by 33
  7. 2021MVT: Mask Vision Transformer for Facial Expression Recognition in the wildcited by 27
  8. 2020Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural Networkscited by 24
  9. 2019Facial Motion Prior Networks for Facial Expression Recognitioncited by 20
  10. 2021Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognitioncited by 18
  11. 2020Occlusion-Adaptive Deep Network for Robust Facial Expression Recognitioncited by 17
  12. 2019Identity-Free Facial Expression Recognition using conditional Generative Adversarial Networkcited by 14
  13. 2019FERAtt: Facial Expression Recognition with Attention Netcited by 9
  14. 2017Learning Deep Features via Congenerous Cosine Loss for Person Recognitioncited by 7
  15. 2019Pose-adaptive Hierarchical Attention Network for Facial Expression Recognitioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 21; 2024: 18; 2025: 2; 2026: 6.

55 papers.

Sort:

By area:

  1. 2023GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognitioncited by 38
  2. 2022Vision Transformer with Attentive Pooling for Robust Facial Expression Recognitioncited by 35
  3. 2024EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuningcited by 27
  4. 2024Facial Affective Behavior Analysis with Instruction Tuningcited by 26
  5. 2023POSTER++: A simpler and stronger facial expression recognition networkcited by 25
  6. 2023Multi-modal Facial Affective Analysis based on Masked Autoencodercited by 23
  7. 2023Leveraging TCN and Transformer for effective visual-audio fusion in continuous emotion recognitioncited by 20
  8. 2023MMA-MRNNet: Harnessing Multiple Models of Affect and Dynamic Masked RNN for Precise Facial Expression Intensity Estimationcited by 16
  9. 2024ExpLLM: Towards Chain of Thought for Facial Expression Recognitioncited by 15
  10. 2023Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognitioncited by 13
  11. 2022Multi-Task Learning Framework for Emotion Recognition in-the-wildcited by 10
  12. 2022Affective Behaviour Analysis Using Pretrained Model with Facial Prioricited by 10
38 more
  1. 2023ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression Learningcited by 9
  2. 2024ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognitioncited by 9
  3. 2023Disguise without Disruption: Utility-Preserving Face De-Identificationcited by 8
  4. 2024Exploring Facial Expression Recognition through Semi-Supervised Pretraining and Temporal Modelingcited by 8
  5. 2024Rethinking Affect Analysis: A Protocol for Ensuring Fairness and Consistencycited by 7
  6. 2024FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed Modelcited by 7
  7. 2022HSE-NN Team at the 4th ABAW Competition: Multi-task Emotion Recognition and Learning from Synthetic Imagescited by 6
  8. 2024LRDif: Diffusion Models for Under-Display Camera Emotion Recognitioncited by 6
  9. 2022Learning from Synthetic Data: Facial Expression Classification based on Ensemble of Multi-task Networkscited by 5
  10. 2022Cluster-level pseudo-labelling for source-free cross-domain facial expression recognitioncited by 5
  11. 2024Neuromorphic Valence and Arousal Estimationcited by 5
  12. 2023Expressive Speech-driven Facial Animation with controllable emotionscited by 4
  13. 2023Exploring Large-scale Unlabeled Faces to Enhance Facial Expression Recognitioncited by 4
  14. 2024Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attentioncited by 4
  15. 2023ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillationcited by 3
  16. 2024Emotic Masked Autoencoder with Attention Fusion for Facial Expression Recognitioncited by 3
  17. 2023A Dual Branch Network for Emotional Reaction Intensity Estimationcited by 2
  18. 2023Efficient Neural Architecture Search for Emotion Recognitioncited by 2
  19. 2024Batch Transformer: Look for Attention in Batchcited by 2
  20. 2024Facing Asymmetry -- Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventionscited by 2
  21. 2025Lightweight Sequential Transformers for Blood Glucose Level Prediction in Type-1 Diabetescited by 2
  22. 2024Bridging the Gaps: Utilizing Unlabeled Face Recognition Datasets to Boost Semi-Supervised Facial Expression Recognitioncited by 1
  23. 2024Semantic Data Augmentation for Long-tailed Facial Expression Recognitioncited by 1
  24. 2025Interpretable Concept-based Deep Learning Framework for Multimodal Human Behavior Modelingcited by 1
  25. 2022A Peek at Peak Emotion Recognitioncited by 0
  26. 2022Selective manipulation of disentangled representations for privacy-aware facial image processingcited by 0
  27. 2023Facial Expression Recognition using Squeeze and Excitation-powered Swin Transformerscited by 0
  28. 2023SimFLE: Simple Facial Landmark Encoding for Self-Supervised Facial Expression Recognition in the Wildcited by 0
  29. 2023Emotional Reaction Intensity Estimation Based on Multimodal Datacited by 0
  30. 2023Human Reaction Intensity Estimation with Ensemble of Multi-task Networkscited by 0
  31. 2023Multi-Domain Norm-referenced Encoding Enables Data Efficient Transfer Learning of Facial Expression Recognitioncited by 0
  32. 2023Multi Loss-based Feature Fusion and Top Two Voting Ensemble Decision Strategy for Facial Expression Recognition in the Wildcited by 0
  33. 2023Semantic Face Compression for Metaverse: A Compact 3D Descriptor Based Approachcited by 0
  34. 2023Multi-Branch Network for Imagery Emotion Predictioncited by 0
  35. 2024eMotion-GAN: A Motion-based GAN for Photorealistic and Facial Expression Preserving Frontal View Synthesiscited by 0
  36. 2024LLDif: Diffusion Models for Low-light Emotion Recognitioncited by 0
  37. 2024GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distributioncited by 0
  38. 2026Semi-Supervised Facial Expression Recognition based on Dynamic Threshold and Negative Learningcited by 0

50 most cited of 55 All 55 (JSON)