LMVD: A Large-Scale Multimodal Vlog Dataset for Depression Detection in the Wild

TL;DR

This paper introduces LMVD, a large-scale multimodal vlog dataset designed for depression detection in natural settings, along with a novel deep learning architecture called MDDformer that effectively learns non-verbal cues.

Contribution

The paper presents the creation of LMVD, a comprehensive multimodal dataset for depression detection, and proposes MDDformer, a new model that improves detection accuracy in real-world scenarios.

Findings

LMVD contains 1823 samples from 1475 participants across four platforms.

MDDformer outperforms existing models in depression detection tasks.

Extensive validation confirms the effectiveness of the proposed approach.

Abstract

Depression can significantly impact many aspects of an individual's life, including their personal and social functioning, academic and work performance, and overall quality of life. Many researchers within the field of affective computing are adopting deep learning technology to explore potential patterns related to the detection of depression. However, because of subjects' privacy protection concerns, that data in this area is still scarce, presenting a challenge for the deep discriminative models used in detecting depression. To navigate these obstacles, a large-scale multimodal vlog dataset (LMVD), for depression recognition in the wild is built. In LMVD, which has 1823 samples with 214 hours of the 1475 participants captured from four multimedia platforms (Sina Weibo, Bilibili, Tiktok, and YouTube). A novel architecture termed MDDformer to learn the non-verbal behaviors of individuals is proposed. Extensive validations are performed on the LMVD dataset, demonstrating superior performance for depression detection. We anticipate that the LMVD will contribute a valuable function to the depression detection community. The data and code will released at the link: https://github.com/helang818/LMVD/.