A Multimodal Dataset for Mixed Emotion Recognition with Physiological and Video Data

A Multimodal Dataset for Mixed Emotion Recognition contains physiological and video data from 73 participants watching emotion-inducing video clips. The dataset includes EEG, GSR, PPG, and frontal face video signals, alongside self-reported ratings on PANAS, VAD, and amusement-disgust dimensions. It was created by Pei Yang from Tsinghua University and shared via Papers with Code.

Use Cases

• Training classifiers for mixed emotion recognition based on EEG, GSR, PPG, and facial video data.
• Validating emotion induction methods based on physiological responses to curated video stimuli.
• Correlating subjective self-assessment ratings with objective physiological signal patterns.
• Benchmarking multimodal fusion models for affective computing tasks.

Strengths

• Data from 73 participants provides a foundation for model training.
• Includes four signal types: EEG, GSR, PPG, and frontal face videos.
• Emotion induction was validated through a rule-based video filtering step and technical validation.

Limitations

• Row count and dataset size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Tsinghua University

Collection Method

Data recorded from 80 participants watching selected video clips; data from 73 participants was retained after quality filtering.