Research map / Vision-language and multimodal / Cross-modal learning
Voices, Faces, and Feelings: Multi-modal Emotion-Cognition Captioning for Mental Health Understanding
Zhiyuan Zhou, Yanrong Guo, Shijie Hao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add ECMC emotion-cognition profile as input to an LLM for depression detection | Qwen3-8B · Depression detection | ACC (%): 50.46 -> 70.64 | Improved |
| add ECMC profile for anxiety detection | Llama-3-8B · Anxiety detection | ACC (%): 38.54 -> 57.29 | Improved |
| add ECMC profile for anxiety detection | GLM4-9B · Anxiety detection | ACC (%): 43.75 -> 44.95 | No clear effect |
| use profiles from weaker captioners (e.g. MindChat) instead of none | LLM detectors · Depression/anxiety detection | F1: 1.01 decrease in avg F1 gain (MindChat) | Hurt |
| combine audio, video and text modalities rather than single modality (ablation) | ECMC · MMDA captioning | F BERT | Improved |
| add both emotion and cognition contrastive learning branches (ablation) | ECMC · MMDA captioning | F BERT: full model 34.09 | Improved |
| use multimodal ECMC vs text-only mental health LLMs for caption generation | ECMC · MMDA emotion captioning | BLEU-4: 2.33 -> 8.28 | Improved |
Closest papers by meaning
- Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning (NeurIPS 2024 · similarity 0.86)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.86)
- Mental-Perceiver: Audio-Textual Multi-Modal Learning for Estimating Mental Disorders (AAAI 2025 · similarity 0.86)
- Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive Learning (AAAI 2025 · similarity 0.85)
- MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models (ICLR 2026 · similarity 0.85)
- OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
