Automatic Depression Scale Prediction using Facial Expression Dynamics and Regression

Jan, Asim; Meng, Hongying; Gaus, Yona Falinie A.; Zhang, Fan; Turabzadeh, Saeed

doi:10.1145/2661806.2661812

Cited by 84 publications

(49 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 3 compares the MAE and RMSE accuracy of proposed and related methods on the AVEC2014 dataset. The methods based on handcrafted features are in [22,23,24]. We can cite as an example, the baseline method provided by AVEC2014 competition which is based on Local Binary Pattern (LBP) and LPQ.…”

Section: Experimental Analysismentioning

confidence: 99%

Depression Detection Based on Deep Distribution Learning

Melo

Granger

Hadid

2019

2019 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Major depressive disorder is among the most common and harmful mental health problems. Several deep learning architectures have been proposed for video-based detection of depression based on the facial expressions of subjects. To predict the depression level, these architectures are often modeled for regression with Euclidean loss. Consequently, they do not leverage the data distribution, nor explore the ordinal relationship between facial images and depression levels, and have limited robustness to noisy and uncertain labeling. This paper introduces a deep learning architecture for accurately predicting depression levels through distribution learning. It relies on a new expectation loss function that allows to estimate the underlying data distribution over depression levels, where expected values of the distribution are optimized to approach the ground-truth levels. The proposed approach can produce accurate predictions of depression levels even under label uncertainty. Extensive experiments on the AVEC2013 and AVEC2014 datasets indicate that the proposed architecture represents an effective approach that can outperform state-of-the-art techniques.

show abstract

Section: Experimental Analysismentioning

confidence: 99%

Depression Detection Based on Deep Distribution Learning

Melo

Granger

Hadid

2019

2019 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Using AVEC and a few non-publicly available resources [25], audiovisual detection of depression has been proposed [26], [27] [28], [29], [30], [31], [32], [33]. In [28] for instance, visual bag-of-words (BoW) features computed from space time interest points (STIP), were combined with melfrequency cepstral coefficients (MFCCs) features.…”

Section: Introductionmentioning

confidence: 99%

“…The extracted audiovisual features were encoded using a Fisher Vector representation and a linear SVR was used to learn BDI score classification. In [31], visual Motion History Histogram (MHH) features were measured from three different visual texture features (Local Binary Patterns, Edge Orientation Histogram, and Local Phase Quantization) and combined with low-level audio descriptors provided in [21]. Partial Least Square (PLS) and Linear regression algorithms were used to model the mapping between the extracted features and BDI scores for face and voice features separately, followed by a decision based combination.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Multimodal Measurement of Depression Severity Using Deep Autoencoding

Dibeklioğlu

Hammal

Cohn

2018

IEEE J. Biomed. Health Inform.

144

View full text Add to dashboard Cite

Depression is one of the most common psychiatric disorders worldwide, with over 350 million people affected. Current methods to screen for and assess depression depend almost entirely on clinical interviews and self-report scales. While useful, such measures lack objective, systematic, and efficient ways of incorporating behavioral observations that are strong indicators of depression presence and severity. Using dynamics of facial and head movement and vocalization, we trained classifiers to detect three levels of depression severity. Participants were a community sample diagnosed with major depressive disorder. They were recorded in clinical interview (Hamilton Rating Scale for Depression, HRSD) at 7-week intervals over a period of 21 weeks. At each interview, they were scored by HRSD as moderately to severely depressed, mildly depressed, or remitted. Logistic regression classifiers using leave-one-participant-out validation were compared for facial movement, head movement, and vocal prosody individually and in combination. Accuracy of depression severity measurement from facial movement dynamics was higher than that for head movement dynamics; and each was substantially higher than that for vocal prosody. Accuracy using all three modalities combined only marginally exceeded that of face and head combined. These findings suggest that automatic detection of depression severity from behavioral indicators in patients is feasible and that multimodal measures afford most powerful detection.

show abstract

“…We will also extend the proposed method on the BlackDog Institute clinical depression data [17]. [32] 8.12 6.31 Bimodal (Au, Vi) Kachele et al [19] 9.70 7.28 Multimodal (Au, Vi, Meta) Jan et al [15] 10.26 8.30 Bimodal (Au, Vi) Perez et al [27] 10.82 8.99 Bimodal (Au, Vi) Perez et al [27] 11.91 9.35 Unimodal (Au) Jain et al [14] 10.24 8.39 Unimodal (Vi) Gupta et al [13] 10.33 -Multimodal (Au, Vi, Text) Kaya et al [20] 9.61 7.69 Bimodal (Au, Vi) Kaya et al [20] 9.97 7.96 Unimodal (Vi) Baseline [30] 9.98 7.89 Bimodal (Au, Vi) Video Baseline [30] 10.85 8.85 Unimodal (Vi) …”

Section: Discussionmentioning

confidence: 99%

A temporally piece-wise fisher vector approach for depression analysis

Dhall

Goecke

2015

2015 International Conference on Affective Computing and Intelligent Interaction (ACII)

View full text Add to dashboard Cite

Abstract-Depression and other mood disorders are common, disabling disorders with a profound impact on individuals and families. Inspite of its high prevalence, it is easily missed during the early stages. Automatic depression analysis has become a very active field of research in the affective computing community in the past few years. This paper presents a framework for depression analysis based on unimodal visual cues. Temporally piece-wise Fisher Vectors (FV) are computed on temporal segments. As a low-level feature, block-wise Local Binary PatternThree Orthogonal Planes descriptors are computed. Statistical aggregation techniques are analysed and compared for creating a discriminative representative for a video sample. The paper explores the strength of FV in representing temporal segments in a spontaneous clinical data. This creates a meaningful representation of the facial dynamics in a temporal segment. The experiments are conducted on the Audio Video Emotion Challenge (AVEC) 2014 German speaking depression database. The superior results of the proposed framework show the effectiveness of the technique as compared to the current state-of-art.

show abstract

Automatic Depression Scale Prediction using Facial Expression Dynamics and Regression

Cited by 84 publications

References 30 publications

Depression Detection Based on Deep Distribution Learning

Depression Detection Based on Deep Distribution Learning

Dynamic Multimodal Measurement of Depression Severity Using Deep Autoencoding

A temporally piece-wise fisher vector approach for depression analysis

Contact Info

Product

Resources

About