{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/190407656","title":"The Verbal and Non Verbal Signals of Depression -- Combining Acoustics, Text and Visuals for Estimating Depression Level","arxiv_id":"1904.07656","date":"2019-04-02","proceeding":null,"authors":["Syed Arbaaz Qureshi","Mohammed Hasanuzzaman","Sriparna Saha","Gaël Dias"],"abstract":"Depression is a serious medical condition that is suffered by a large number\nof people around the world. It significantly affects the way one feels, causing\na persistent lowering of mood. In this paper, we propose a novel\nattention-based deep neural network which facilitates the fusion of various\nmodalities. We use this network to regress the depression level. Acoustic, text\nand visual modalities have been used to train our proposed network. Various\nexperiments have been carried out on the benchmark dataset, namely, Distress\nAnalysis Interview Corpus - a Wizard of Oz (DAIC-WOZ). From the results, we\nempirically justify that the fusion of all three modalities helps in giving the\nmost accurate estimation of depression level. Our proposed approach outperforms\nthe state-of-the-art by 7.17% on root mean squared error (RMSE) and 8.08% on\nmean absolute error (MAE).","url_abs":"http://arxiv.org/abs/1904.07656v1","url_pdf":"http://arxiv.org/pdf/1904.07656v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"190407656","repo_url":"https://github.com/jhaprince/multibully","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"190407656","repo_url":"https://github.com/arbaazQureshi/attention_based_multimodal_fusion_for_estimating_depression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"wizard","method_name":"Wizard"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}