mlsanityData to 14 Oct 2026

Optimal Transport-based Identity Matching for Identity-invariant Facial Expression Recognition

arXiv 2209.12172 ↗First posted 25 Sep 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Identity-invariant facial expression recognition (FER) has been one of the challenging computer vision tasks. Since conventional FER schemes do not explicitly address the inter-identity variation of facial expressions, their neural network models still operate depending on facial identity. This paper proposes to quantify the inter-identity variation by utilizing pairs of similar expressions explored through a specific matching process. We formulate the identity matching process as an Optimal Transport (OT) problem. Specifically, to find pairs of similar expressions from different identities, we define the inter-feature similarity as a transportation cost. Then, optimal identity matching to find the optimal flow with minimum transportation cost is performed by Sinkhorn-Knopp iteration. The proposed matching method is not only easy to plug in to other models, but also requires only acceptable computational overhead. Extensive simulations prove that the proposed FER method improves the PCC/CCC performance by up to 10% or more compared to the runner-up on wild datasets. The source code and software demo are available at https://github.com/kdhht2334/ELIMFER.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 30 of its 63 references that are in the map. First posted on arXiv 25 Sep 2022.

Builds on

30 of 63 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  6. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  8. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  9. 2014How transferable are features in deep neural networks?cited by 1,225
  10. 2020In Search of Lost Domain Generalizationcited by 1,054
  11. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 903
  12. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 876
18 more
  1. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 599
  2. 2021Domain Generalization with MixStylecited by 566
  3. 2017AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wildcited by 492
  4. 2017Near-linear time approximation algorithms for optimal transport via Sinkhorn iterationcited by 223
  5. 2019Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFacecited by 222
  6. 2018Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyondcited by 216
  7. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 211
  8. 2020Understanding the Failure Modes of Out-of-Distribution Generalizationcited by 146
  9. 2021Adversarially Adaptive Normalization for Single Domain Generalizationcited by 85
  10. 2018Boosting Domain Adaptation by Discovering Latent Domainscited by 46
  11. 2019Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimationcited by 40
  12. 2018EmotiW 2018: Audio-Video, Student Engagement and Group-Level Affect Predictioncited by 18
  13. 2019MIMAMO Net: Integrating Micro- and Macro-motion for Video Emotion Recognitioncited by 17
  14. 2021Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognitioncited by 16
  15. 2021Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transportcited by 16
  16. 2020BReG-NeXt: Facial Affect Computing Using Adaptive Residual Networks With Bounded Gradientcited by 13
  17. 2021Domain Generalisation for Apparent Emotional Facial Expression Recognition across Age-Groupscited by 4
  18. 2017Facial Affect Estimation in the Wild Using Deep Residual and Convolutional Networkscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 4; 2026: 1.

8 papers.

  1. 2024Norface: Improving Facial Expression Analysis by Identity Normalizationcited by 10
  2. 2023A multimodal dynamical variational autoencoder for audiovisual speech representation learningcited by 6
  3. 2024OTCXR: Rethinking Self-supervised Alignment using Optimal Transport for Chest X-ray Analysiscited by 3
  4. 2025ReactDiff: Latent Diffusion for Facial Reaction Generationcited by 2
  5. 2025ID-Consistent, Precise Expression Generation with Blendshape-Guided Diffusioncited by 1
  6. 2025Reverse Personalizationcited by 1
  7. 2026The Circumplex Degeneracy Behind the Rare-Class Limit in Affect Recognitioncited by 1
  8. 2025Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detectioncited by 0