C-MIND, a 169-participant clinically diagnosed multimodal depression dataset, is introduced, and the paper reports audio/video from picture description as the strongest signals and that clinical-expertise prompts improve LLM diagnosis.
Classical Feature Set
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unveiling the Landscape of Clinical Depression Assessment: From Behavioral Signatures to Psychiatric Reasoning
C-MIND, a 169-participant clinically diagnosed multimodal depression dataset, is introduced, and the paper reports audio/video from picture description as the strongest signals and that clinical-expertise prompts improve LLM diagnosis.