D-vlog: Multimodal Vlog Dataset for Depression Detection
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Detecting depression based on non-verbal behaviors has received great attention. However, most prior work on detecting depression mainly focused on detecting depressed individuals in laboratory settings, which are difficult to be generalized in practice. In addition, little attention has been paid to analyzing the non-verbal behaviors of depressed individuals in the wild. Therefore, in this paper, we present a multimodal depression dataset, D-Vlog, which consists of 961 vlogs (i.e., around 160 hours) collected from YouTube, which can be utilized in developing depression detection models based on the non-verbal behavior of individuals in real-world scenario. We develop a multimodal deep learning model that uses acoustic and visual features extracted from collected data to detect depression. Our proposed model employs the cross-attention mechanism to effectively capture the relationship across acoustic and visual features, and generates useful multimodal representations for depression detection. The extensive experimental results demonstrate that the proposed model significantly outperforms other baseline models. We believe our dataset and the proposed model are useful for analyzing and detecting depressed individuals based on non-verbal behavior.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Multimodal Machine Learning: A Survey and Taxonomy
Baltrusaitis, T., Ahuja, C., & Morency, L.-P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2798607 · Cited by 5,018
Tensor Fusion Network for Multimodal Sentiment Analysis
Zadeh, A., Chen, M., Poria, S., Cambria, E., & Morency, L.-P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1115 · Cited by 2,102 · cited 7×
“…following six methods: (i) Logistic Regression ( LR ), (ii) Support Vector Machines ( SVM ), (iii) Random Forest ( RF ), (iv) K-Nearest Neighbors based Fusion ( KNN-Fusion ) (Pam-pouchidou et al. 2017), (v) Bi-directional LSTM ( BLSTM ), and (vi) Tensor Fusion Network ( TFN ) (Zadeh et al. 2017).”
BackgroundMethodInfluentialThe Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing
Eyben, F., Scherer, K. R., Schuller, B. W., Sundberg, J., Andre, E., Busso, C., Devillers, L. Y., Epps, J., Laukka, P., Narayanan, S. S., et al. (2016) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2015.2457417 · Cited by 1,818 · cited 2×
“Acoustic Features: To extract audio features from a given vlog, we employ OpenSmile (Eyben, W¨ollmer, and Schuller 2010), an open-source toolkit for audio processing, with the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) (Eyben et al. 2015).”
MethodWhy is depression more prevalent in women?
Albert, P. R. (2015) · Journal of Psychiatry and Neuroscience · doi:10.1503/jpn.150205 · Cited by 1,785 · cited 1×
“We find that there are twice more females than males in the depression vlogs, which is aligned with the prior work that showed major depression is more prevalent in women than men (Albert 2015).”
ResultGlobal burden of depressive disorders in the year 2000
Üstün, T. B., Ayuso-Mateos, J. L., Chatterji, S., Mathers, C., & Murray, C. J. L. (2004) · British Journal of Psychiatry · doi:10.1192/bjp.184.5.386 · Cited by 1,735 · cited 2×
“Major Depressive Disorder (MDD) is considered as one of the most common mental health disorders, and has become an important problem in society (Üstün et al. 2004).”
BackgroundPsychomotor symptoms of depression
(1997) · American Journal of Psychiatry · doi:10.1176/ajp.154.1.4 · Cited by 662 · cited 1×
“Scholars have shown that depressed and non-depressed groups can be distinguished by non-verbal signals such as facial expressions, body movements, and vocal intensity (Edition et al. 2013; Sobin and Sackeim 1997).”
BackgroundThe distress analysis interview corpus of human and computer interviews
Gratch, J., Artstein, R., Lucas, G., Stratou, G., Scherer, S., Nazarian, A., Wood, R., Boberg, J., DeVault, D., Marsella, S., et al. (2014) · Proceedings of the Language Resources and Evaluation Conference · doi:10.63317/3o7bccg9xequ · Cited by 599 · cited 8×
“The experimental result shows that the model trained with the proposed dataset also achieves a high depression detection performance for DAIC-WOZ, where videos are recorded in a clinical interview format.”
BackgroundInfluentialNicolaou, M. A., Gunes, H., & Pantic, M. (2011) · IEEE Transactions on Affective Computing · doi:10.1109/t-affc.2011.9 · Cited by 450 · cited 1×
“With the advancements in deep learning techniques, neural networks can be used for multimodal fusion (W¨ollmer et al. 2010; Nicolaou, Gunes, and Pantic 2011; W ¨ ollmer et al. 2013).”
MethodDeep learning for robust feature generation in audiovisual emotion recognition
Kim, Y., Lee, H., & Provost, E. M. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638346 · Cited by 401 · cited 3×
“The scholars created multimodal representations by simple concatenating, adding, or multiplying feature/decision level vectors to perform prediction tasks (Kim, Lee, and Provost 2013; Liu, Zheng, and Lu 2016; Gunes and Piccardi 2007; Liu et al. 2018).”
MethodBi-modal emotion recognition from expressive face and body gestures
Gunes, H., & Piccardi, M. (2007) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2006.09.007 · Cited by 382
Mundt, J. C., Snyder, P. J., Cannizzaro, M. S., Chappie, K., & Geralts, D. S. (2007) · Journal of Neurolinguistics · doi:10.1016/j.jneuroling.2006.04.001 · Cited by 380 · cited 1×
“This implies that depressive speakers have distinctive features in their speech (Mundt et al. 2007).”
BackgroundLSTM-Modeling of continuous emotions in an audiovisual affect recognition framework
Wöllmer, M., Kaiser, M., Eyben, F., Schuller, B., & Rigoll, G. (2013) · Image and Vision Computing · doi:10.1016/j.imavis.2012.03.001 · Cited by 288 · cited 1×
“With the advancements in deep learning techniques, neural networks can be used for multimodal fusion (Wöllmer et al. 2010; Nicolaou, Gunes, and Pantic 2011; Wöllmer et al. 2013).”
MethodWöllmer, M., Metallinou, A., Eyben, F., Schuller, B., & Narayanan, S. S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-646 · Cited by 201 · cited 2×
“With the advancements in deep learning techniques, neural networks can be used for multimodal fusion (Wöllmer et al. 2010; Nicolaou, Gunes, and Pantic 2011; Wöllmer et al. 2013).”
MethodLearn to combine modalities in multimodal deep learning
Liu, K., Li, Y., Xu, N., & Natarajan, P. (2018) · arXiv · doi:10.48550/arxiv.1805.11730 · Cited by 136 · cited 4×
“…used multimodal fusion operations: (i) Concat (Kim, Lee, and Provost 2013; Liu, Zheng, and Lu 2016; Bargal et al. 2016), (ii) Add (Gunes and Pic-cardi 2007; Castellano, Kessous, and Caridakis 2008), and (iii) Multiply (Liu et al. 2018; Mittal et al. 2020) in fusing audio and visual representations.”
MethodInfluentialA multitask framework to detect depression, sentiment and multi-label emotion from suicide notes
Ghosh, S., Ekbal, A., & Bhattacharyya, P. (2022) · Cognitive Computation · doi:10.1007/s12559-021-09828-7 · Cited by 102 · cited 1×
“If the depression is left untreated, it can cause severe outcomes such as addiction, reckless behavior, and even suicide (Ghosh, Ekbal, and Bhattacharyya 2021).”
BackgroundModel Fusion for Multimodal Depression Classification and Level Detection
Senoussaoui, M., Sarria-Paja, M., Santos, J. F., & Falk, T. H. (2014) · Proceedings of the 4th International Workshop on Audio/Visual Emotion Challenge · doi:10.1145/2661806.2661819 · Cited by 80
Cited by
Zhao, F., Zhang, C., & Geng, B. (2024) · ACM Computing Surveys · doi:10.1145/3649447 · Cited by 480
A Review of Machine Learning and Deep Learning Approaches on Mental Health Diagnosis
Iyortsuun, N. K., Kim, S.-H., Jhon, M., Yang, H.-J., & Pant, S. (2023) · Healthcare · doi:10.3390/healthcare11030285 · Cited by 276
Self-citationZheng, W., Yu, J., Xia, R., & Wang, S. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.861 · Cited by 51
Chou, H.-C., Goncalves, L., Leem, S.-G., Salman, A. N., Lee, C.-C., & Busso, C. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3411290 · Cited by 22
Multimodal fusion network for ICU patient outcome prediction
Wang, C., Yang, X., Sun, M., Gu, Y., Niu, J., & Zhang, W. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106672 · Cited by 16
Metadata
- Authors
- Yoon, J., Kang, C., Kim, S., & Han, J.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2022-06-28
- Volume
- 36
- Issue
- 11
- Pages
- 12226-12234
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W4283815599
- Cited by
- 116
- References
- 17
- FWCI
- 29.50
- Type
- conference paper
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.