Corpus ID: 231699067

Weakly Supervised Learning for Facial Behavior Analysis : A Review

@article{GnanaPraveen2021WeaklySL,
  title={Weakly Supervised Learning for Facial Behavior Analysis : A Review},
  author={R GnanaPraveen and {\'E}ric Granger and Patrick Cardinal},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.09858}
}
In the recent years, there has been a shift in facial behavior analysis from the laboratory-controlled conditions to the challenging in-the-wild conditions due to the superior performance of deep learning based approaches for many real world applications. However, the performance of deep learning approaches relies on the amount of training data. One of the major problems with data acquisition is the requirement of annotations for large amount of training data. Labeling process of huge training… Expand
1 Citations

Figures and Tables from this paper

Deep domain adaptation with ordinal regression for pain assessment using weakly-labeled videos
TLDR
A new DL model for weakly-supervised DA with ordinal regression (WSDA-OR) that can be adapted using target domain videos with coarse labels provided on a periodic basis that can significantly improve performance over the state-of-the-art models, allowing to achieve a greater pain localization accuracy. Expand

References

SHOWING 1-10 OF 135 REFERENCES
Regularized Multi-Concept MIL for weakly-supervised facial behavior categorization
TLDR
This work addresses the problem of estimating high-level semantic labels for videos of recorded people by means of analysing their facial expressions and proposes a novel MIL method called Regularized Multi-Concept MIL, which outperforms state-of-the-art results in the UNBC data-set for pain detection. Expand
A Weakly Supervised learning technique for classifying facial expressions
TLDR
This work proposes a weakly supervised learning technique for expression classification, which leverages the information of unannotated data, and demonstrates that the proposed method achieves to learn different expression intensities, even when trained with categorical samples. Expand
Deep Facial Expression Recognition: A Survey
TLDR
This survey provides a comprehensive review on deep FER, including datasets and algorithms that provide insights into overfitting caused by a lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias. Expand
Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition
TLDR
Experiments show that the proposed approach can effectively leverage large datasets of unlabeled face images to improve the AU recognition robustness and outperform the state-of-the-art semi-supervised AU recognition methods. Expand
A Deep Learning Perspective on the Origin of Facial Expressions
TLDR
This paper employs CNN understanding methods to study the relation between the features these computational networks are using, the FACS and Action Units and achieves state-of-the-art accuracy using a simple long-short-term-memory (LSTM) recurrent neural network (RNN). Expand
Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation
TLDR
This work proposes a novel knowledge-based semi-supervised deep convolutional neural network for AU intensity estimation with extremely limited AU annotations, which can achieve comparable or even better performance than the state-of-the-art methods. Expand
Regularizing face verification nets for pain intensity regression
TLDR
A network that fine-tunes a state-of-the-art face verification network using a regularized regression loss and additional data with expression labels is proposed, which can benefit from the rich feature representations trained on a huge amount of data for face verification. Expand
Facial action unit recognition under incomplete data based on multi-label learning with missing labels
TLDR
Facial action unit recognition under incomplete data as a multi-label learning with missing labels (MLML) problem is formulated and the superiority of the proposed method in comparison with several state-of-the-art works is demonstrated. Expand
Deep Weakly Supervised Domain Adaptation for Pain Localization in Videos
TLDR
A weakly-supervised domain adaptation (WSDA) technique that allows for training 3D CNNs for spatiotemporal pain intensity estimation using weakly labeled videos, where labels are provided on a periodic basis is proposed. Expand
Weakly Supervised Facial Action Unit Recognition With Domain Knowledge
TLDR
This paper proposes a novel weakly supervised AU recognition method to jointly learn multiple AU classifiers with expression annotations but without any AU annotations by leveraging domain knowledge, and demonstrates that the proposed method can successfully exploit domain knowledge for multiple AU recognition. Expand
...
1
2
3
4
5
...