CMU-MOSEI

The CMU-MOSEI dataset is used for multimodal sentiment analysis, containing integrated text, audio, and visual modalities to evaluate sentiment across different contexts.

Papers using CMU-MOSEI (7)

Decoupled Hierarchical Distillation for Multimodal Emotion Recognition2026MIAR: Modality Interaction and Alignment Representation Fuison for Multimodal Emotion2026Gated Recursive Fusion: A Stateful Approach to Scalable Multimodal Transformers2025Multimodal Sentiment Analysis On CMU-MOSEI Dataset Using Transformer-based Models2025Exploring Fusion Strategies For Multimodal Vision-language Systems2025Leveraging CLIP Encoder for Multimodal Emotion Recognition2025Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention2024 · 1 cites