mlsanityData to 14 Oct 2026

Local Multi-Head Channel Self-Attention for Facial Expression Recognition

arXiv 2111.07224 ↗First posted 14 Nov 2021cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Since the Transformer architecture was introduced in 2017 there has been many attempts to bring the self-attention paradigm in the field of computer vision. In this paper we propose a novel self-attention module that can be easily integrated in virtually every convolutional neural network and that is specifically designed for computer vision, the LHC: Local (multi) Head Channel (self-attention). LHC is based on two main ideas: first, we think that in computer vision the best way to leverage the self-attention paradigm is the channel-wise application instead of the more explored spatial attention and that convolution will not be replaced by attention modules like recurrent networks were in NLP; second, a local approach has the potential to better overcome the limitations of convolution than global attention. With LHC-Net we managed to achieve a new state of the art in the famous FER2013 dataset with a significantly lower complexity and impact on the "host" architecture in terms of computational cost when compared with the previous SOTA.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 37 of its 47 references that are in the map. First posted on arXiv 14 Nov 2021.

Builds on

37 of 47 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2017Squeeze-and-Excitation Networkscited by 4,789
  8. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  9. 2014Going Deeper with Convolutionscited by 4,241
  10. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  11. 2017Deformable Convolutional Networkscited by 1,488
  12. 2015Spatial Transformer Networkscited by 1,429
25 more
  1. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  2. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  3. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 856
  4. 2018Self-Attention Generative Adversarial Networkscited by 809
  5. 2018Image Transformercited by 772
  6. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 575
  7. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  8. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  9. 2020Meta Pseudo Labelscited by 374
  10. 2019Attention Augmented Convolutional Networkscited by 363
  11. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  12. 2013Challenges in Representation Learning: A report on three machine learning contestscited by 302
  13. 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
  14. 2019Probabilistic Face Embeddingscited by 173
  15. 2019Adaptive Attention Span in Transformerscited by 149
  16. 2020Multi-Head Attention: Collaborate Instead of Concatenatecited by 60
  17. 2019Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Networkcited by 37
  18. 2020Loss Function Search for Face Recognitioncited by 22
  19. 2021Facial Emotion Recognition: State of the Art Performance on FER2013cited by 20
  20. 2016Facial Expression Recognition using Convolutional Neural Networks: State of the Artcited by 17
  21. 2021LARNet: Lie Algebra Residual Network for Face Recognitioncited by 14
  22. 2019Self Multi-Head Attention for Speaker Recognitioncited by 13
  23. 2021Depth as Attention for Face Representation Learningcited by 5
  24. 2020A Novel Global Spatial Attention Mechanism in Convolutional Neural Network for Medical Image Classificationcited by 4
  25. 2020More Information Supervised Probabilistic Deep Face Embedding Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 4.

7 papers.

  1. 2024ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognitioncited by 9
  2. 2023PAtt-Lite: Lightweight Patch and Attention MobileNet for Challenging Facial Expression Recognitioncited by 7
  3. 2022Cluster-level pseudo-labelling for source-free cross-domain facial expression recognitioncited by 5
  4. 2025EmoNeXt: an Adapted ConvNeXt for Facial Emotion Recognitioncited by 4
  5. 2025Multi-face emotion detection for effective Human-Robot Interactioncited by 1
  6. 20252D-3D Attention and Entropy for Pose Robust 2D Facial Recognitioncited by 1
  7. 2025Achieving 3D Attention via Triplet Squeeze and Excitation Blockcited by 0