Depression Detection Based on Deep Distribution Learning

Melo, Wheidima Carneiro de; Granger, Éric; Hadid, Abdenour

doi:10.1109/icip.2019.8803467

Cited by 58 publications

(39 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, the existing prediction system takes the input sample from either in the form of online available datasets as discussed in the next section or data that needs to be captured through the device. The author's [10], [14], [15] and [16] proposed the technique where online datasets need to be loaded in the system whereas [6], [17], [18] and [19] used the data which were generated through the capturing device at stage one for the prediction based approach. The author's [6], [17], [18] and [19] uses the concept where the certain types of questions -answers, showing movies / videos /audios and the regular activities recorded through the camera then the frames were extracted.…”

Section: Figure 3 Block Diagram Of Prediction Systemmentioning

confidence: 99%

“…Apart from this procedure there are some depression datasets which are available online are: AVEC 2013-2014 [8], Emo-DB [8], DAIC-WOZ [8], Karolinska Directed Emotional Faces (KDEF) database [8], fMRI dataset [10], AVEC 2017 [16]. The limitations of these datasets are: 1.…”

Section: Current Dataset Generation Process and Limitationsmentioning

confidence: 99%

“…The author [16] has proposed a system in which depression has been detected from facial expression which has been captured through video. The author has applied a deep learning concept to implement the proposed system.…”

Section: Analysis Of Prediction Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Study of Mental Disorder Prediction Model approaches its issues and Challenges

Bhuva¹,

Mishra²

2021

JUSST

View full text Add to dashboard Cite

Mental disorder is becoming one of the major health issues in society today. (WHO) depression will be the leading mental disorder all over the world by 2030. The timely prediction of such disorders is very essential for maintaining the health of human beings. These mental disorders are associated with different symptoms, some of these symptoms are visible in the form of facial expressions, gestures, change in voice modulation, etc. and some of them even cannot be noticed by naked eyes. Therefore, it is highly important to collect appropriate verbal and non-verbal symptom details about any individual along with using best-suited algorithms for accurate prediction using information technology. This paper explores different types of such symptoms associated with different types of mental disorders, their causes, and existing prediction-based solutions. The paper further presents the critical analysis of these aspects and proposes usages of biometrics-based traits for building better prediction systems for mental disorders.

show abstract

Section: Figure 3 Block Diagram Of Prediction Systemmentioning

confidence: 99%

Section: Current Dataset Generation Process and Limitationsmentioning

confidence: 99%

See 1 more Smart Citation

Study of Mental Disorder Prediction Model approaches its issues and Challenges

Bhuva¹,

Mishra²

2021

JUSST

View full text Add to dashboard Cite

show abstract

“…The proposed method also outperforms the deep learning schemes proposed in [21,3,11,22,9] on AVEC2014, confirming the good performance of our model. In [25], the method is based on distribution learning with expectation loss function. The proposed method outperforms, in terms of RMSE, such method.…”

Section: Experimental Analysismentioning

confidence: 99%

Encoding Temporal Information For Automatic Depression Recognition From Facial Analysis

Melo

Granger

López

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Depression is a mental illness that may be harmful to an individual's health. Using deep learning models to recognize the facial expressions of individuals captured in videos has shown promising results for automatic depression detection. Typically, depression levels are recognized using 2D-Convolutional Neural Networks (CNNs) that are trained to extract static features from video frames, which impairs the capture of dynamic spatio-temporal relations. As an alternative, 3D-CNNs may be employed to extract spatiotemporal features from short video clips, although the risk of overfitting increases due to the limited availability of labeled depression video data. To address these issues, we propose a novel temporal pooling method to capture and encode the spatio-temporal dynamic of video clips into an image map. This approach allows fine-tuning a pre-trained 2D CNN to model facial variations, and thereby improving the training process and model accuracy. Our proposed method is based on two-stream model that performs late fusion of appearance and dynamic information. Extensive experiments on two benchmark AVEC datasets indicate that the proposed method is efficient and outperforms the state-of-the-art schemes.

show abstract

“…Mental illnesses have a significant impact on an individual's physical health (1), achievements (2,3), and life satisfaction (4). In addition to scales, behavioral recognition methods have been developed to judge the existence (5) or degree (6,7) of specific mental illnesses. However, identifying an individual's mental health status from a range of perspectives may be more helpful in non-professional scenarios such as self-monitoring or large-scale monitoring.…”

Section: Introductionmentioning

confidence: 99%

Identifying Psychological Symptoms Based on Facial Movements

Wang

Zhou

et al. 2020

Front. Psychiatry

View full text Add to dashboard Cite

Background: Many methods have been proposed to automatically identify the presence of mental illness, but these have mostly focused on one specific mental illness. In some non-professional scenarios, it would be more helpful to understand an individual's mental health status from all perspectives.Methods: We recruited 100 participants. Their multi-dimensional psychological symptoms of mental health were evaluated using the Symptom Checklist 90 (SCL-90) and their facial movements under neutral stimulation were recorded using Microsoft Kinect. We extracted the time-series characteristics of the key points as the input, and the subscale scores of the SCL-90 as the output to build facial prediction models. Finally, the convergent validity, discriminant validity, criterion validity, and the split-half reliability were respectively assessed using a multitrait-multimethod matrix and correlation coefficients.Results: The correlation coefficients between the predicted values and actual scores were 0.26 and 0.42 (P < 0.01), which indicated good criterion validity. All models except depression had high convergent validity but low discriminant validity. Results also indicated good levels of split-half reliability for each model [from 0.516 (hostility) to 0.817 (interpersonal sensitivity)] (P < 0.001).Conclusion: The validity and reliability of facial prediction models were confirmed for the measurement of mental health based on the SCL-90. Our research demonstrated that fine-grained aspects of mental health can be identified from the face, and provided a feasible evaluation method for multi-dimensional prediction models.

show abstract

Depression Detection Based on Deep Distribution Learning

Cited by 58 publications

References 22 publications

Study of Mental Disorder Prediction Model approaches its issues and Challenges

Study of Mental Disorder Prediction Model approaches its issues and Challenges

Encoding Temporal Information For Automatic Depression Recognition From Facial Analysis

Identifying Psychological Symptoms Based on Facial Movements

Contact Info

Product

Resources

About