mlsanityData to 7 Oct 2026

MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition

arXiv 2503.00202 ↗First posted 28 Feb 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Dynamic facial expression recognition (DFER) is an important task in the field of computer vision. To apply automatic DFER in practice, it is necessary to accurately recognize ambiguous facial expressions, which often appear in data in the wild. In this paper, we propose MIDAS, a data augmentation method for DFER, which augments ambiguous facial expression data with soft labels consisting of probabilities for multiple emotion classes. In MIDAS, the training data are augmented by convexly combining pairs of video frames and their corresponding emotion class labels, which can also be regarded as an extension of mixup to soft-labeled video data. This simple extension is remarkably effective in DFER with ambiguous facial expression data. To evaluate MIDAS, we conducted experiments on the DFEW dataset. The results demonstrate that the model trained on the data augmented by MIDAS outperforms the existing state-of-the-art method trained on the original dataset.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 30 of its 55 references that are in the map. First posted on arXiv 28 Feb 2025.

Builds on

30 of 55 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  5. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  7. 2016An overview of gradient descent optimization algorithmscited by 1,021
  8. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  9. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  10. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  11. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
  12. 2020Suppressing Uncertainties for Large-Scale Facial Expression Recognitioncited by 157
18 more
  1. 2020SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularizationcited by 149
  2. 2020DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wildcited by 128
  3. 2021Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognitioncited by 89
  4. 2021TransMix: Attend to Mix for Vision Transformerscited by 79
  5. 2022FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videoscited by 69
  6. 2022MixGen: A New Multi-Modal Data Augmentationcited by 61
  7. 2019Frame attention networks for facial expression recognition in videoscited by 56
  8. 2021Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixingcited by 49
  9. 2022Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wildcited by 41
  10. 2022Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wildcited by 29
  11. 2016Peak-Piloted Deep Network for Facial Expression Recognitioncited by 22
  12. 2017Temporal Multimodal Fusion for Video Emotion Classification in the Wildcited by 18
  13. 2020PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networkscited by 12
  14. 2017Convolutional neural networks pretrained on large face recognition datasets for emotion classification from videocited by 9
  15. 2020Noisy Student Training using Body Language Dataset Improves Facial Expression Recognitioncited by 8
  16. 2017Deep generative-contrastive networks for facial expression recognitioncited by 7
  17. 2019Emotion Recognition with Spatial Attention and Temporal Softmax Poolingcited by 6
  18. 2016VIPLFaceNet: An Open Source Deep Face Recognition SDKcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentationcited by 1
  2. 2025Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognitioncited by 0
  3. 2026Beyond Universality: The GCC-FER Dataset and Culture-Aware Adaptation for Dynamic Facial Expression Recognitioncited by 0
  4. 2026Predicting Human Disagreement for Calibrated Dynamic Facial Expression Recognitioncited by 0