Transferring Face Verification Nets To Pain and Expression Regression

@article{Wang2017TransferringFV,
  title={Transferring Face Verification Nets To Pain and Expression Regression},
  author={Feng Wang and Xiang Xiang and Chang Liu and Trac D. Tran and Austin Reiter and Gregory Hager and Harry Quon and Jian Cheng and Alan Loddon Yuille},
  journal={ArXiv},
  year={2017},
  volume={abs/1702.06925}
}
Limited labeled data are available for the research of estimating facial expression intensities. For instance, the ability to train deep networks for automated pain assessment is limited by small datasets with labels of patient-reported pain intensities. Fortunately, fine-tuning from a data-extensive pre-trained domain, such as face verification, can alleviate this problem. In this paper, we propose a network that fine-tunes a state-of-the-art face verification network using a regularized… 

Figures and Tables from this paper

Saliency Supervision: An Intuitive and Effective Approach for Pain Intensity Regression

This work proposes a novel approach called saliency supervision, where deep networks are regularized to focus on facial area that is discriminative for pain regression, and can learn sparse and robust features, which are proved helpful for pain intensity regression.

Weakly supervised facial expression recognition via transferred DAL-CNN and active incremental learning

In order to make better use of facial expression data from Web site and further improve the FER accuracy, Unconstrained Facial Expression Database from Web website database is built in this paper.

FATAUVA-Net: An Integrated Deep Learning Framework for Facial Attribute Recognition, Action Unit Detection, and Valence-Arousal Estimation

This paper proposes an integrated deep learning framework for facial attribute recognition, AU detection, and V-A estimation, and the key idea is to apply AUs to estimate the V- A intensity since both AUs andV-A space could be utilized to recognize some emotion categories.

Detecting discomfort in infants through facial expressions

This study exploits deep convolutional neural network algorithms to address the problem of discomfort detection for infants by analyzing their facial expressions by employing a pre-trained CNN model and fine-tuning the networks using a public dataset with labeled facial expressions.

Unconstrained Facial Action Unit Detection via Latent Feature Domain

This paper proposes an end-to-end unconstrained facial AU detection framework based on domain adaptation, which transfers accurate AU labels from a constrained source domain to an unconStrained target domain by exploiting labels of AU-related facial landmarks.

Semi-Supervised Unconstrained Action Unit Detection via Latent Feature Domain.

An end-to-end semi-supervised unconstrained AU detection framework, which transfers accurate AU labels from a constrained source domain to an unconStrained target domain by exploiting accurate labels of AU-related facial landmarks, and introduces a novel landmark adversarial loss which can solve the multi-player minimax game in adversarial learning.

Recognition of Action Units in the Wild with Deep Nets and a New Global-Local Loss

A novel global-local loss is derived that yields superior recognition of AUs than state-of-the-art algorithms and is shown to yield fast globally meaningful convergences and locally accurate results.

EmotioNet Challenge: Recognition of facial expressions of emotion in the wild

It is shown that current algorithms are not affected by mild resolution changes, small occluders, gender or age, but that 3D pose is a major limiting factor on performance.

Automatic Detection of Protective Behavior in Chronic Pain Physical Rehabilitation: A Recurrent Neural Network Approach

A stacked-LSTM network is investigated to detect events of protective behavior within each activity rather than estimate the overall presence of such behavior, based on wearable motion capture and electromyography data of healthy and chronic lower-back pain people engaged in five functional activities.

Machine Learning Approach to Predict Air Temperature and Relative Humidity inside Mechanically and Naturally Ventilated Duck Houses: Application of Recurrent Neural Network

The duck industry ranks sixth as one of the fastest-growing major industries for livestock production in South Korea. However, there are few studies quantitatively predicting the internal thermal and

References

SHOWING 1-10 OF 28 REFERENCES

Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition

A deep learning technique, which is regarded as a tool to automatically extract useful features from raw data, is adopted and is combined using a new integration method in order to boost the performance of the facial expression recognition.

Peak-Piloted Deep Network for Facial Expression Recognition

This work presents a novel peak-piloted deep network (PPDN) that uses a sample with peak expression to supervise the intermediate feature responses for a sample of non-peak expression (hard sample) of the same type and from the same subject.

Facial Expression Intensity Estimation Using Ordinal Information

By taking advantage of the natural onset-apex-offset evolution pattern of facial expression, the proposed method can handle different amounts of annotations to perform frame-level expression intensity estimation and an efficient optimization algorithm is developed for solving the optimization problem associated with parameter learning.

Learning Face Representation from Scratch

A semi-automatical way to collect face images from Internet is proposed and a large scale dataset containing about 10,000 subjects and 500,000 images, called CASIAWebFace is built, based on which a 11-layer CNN is used to learn discriminative representation and obtain state-of-theart accuracy on LFW and YTF.

A Discriminative Feature Learning Approach for Deep Face Recognition

This paper proposes a new supervision signal, called center loss, for face recognition task, which simultaneously learns a center for deep features of each class and penalizes the distances between the deep features and their corresponding class centers.

Facial Expression Recognition via a Boosted Deep Belief Network

A novel Boosted Deep Belief Network for performing the three training stages iteratively in a unified loopy framework and showed that the BDBN framework yielded dramatic improvements in facial expression analysis.

Disentangling Factors of Variation for Facial Expression Recognition

A semi-supervised approach to solve the task of emotion recognition in 2D face images using recent ideas in deep learning for handling the factors of variation present in data, beating the state-of-the-art on a recently proposed dataset for facial expression recognition.

Towards Pain Monitoring: Facial Expression, Head Pose, a new Database, an Automatic System and Remaining

This work proposes a fully automatic recognition system utilizing facial expression, head pose information and their dynamics, and analyzes the relevance of head pose Information for pain recognition and compares person-specific and general classification models.

Recurrent Convolutional Neural Network Regression for Continuous Pain Intensity Estimation in Video

A real-time regression framework based on the recurrent convolutional neural network for automatic frame-level pain intensity estimation that can predict the pain intensity of each frame by considering a sufficiently large historical frames while limiting the scale of the parameters within the model.

Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks

A deep cascaded multitask framework that exploits the inherent correlation between detection and alignment to boost up their performance and achieves superior accuracy over the state-of-the-art techniques on the challenging face detection dataset and benchmark.