Important Dates (preliminary):

• 11 July 2025: Paper submission deadline

• 1 August 2025: Notification of acceptance

• 11 August 2025: Camera-ready paper due

• 27 October: Workshop

Submit your paper

• EasyChair submission link: https://easychair.org/my/conference?conf=muse2025 

Description

The MuSe 2025 is dedicated to multimodal signal processing, sentiment and emotion recognition. The workshop provides a stimulating environment for developing and evaluating novel approaches to multimedia processing and deep learning methods for automatic audiovisual, textual, and physiological affect modeling. The workshop is intended to appeal to a variety of research communities, encouraging synergies between different disciplines. Mainly, MuSe 2025 targets researchers interested in audio-visual emotion recognition, unimodal and multimodal representation learning, health informatics, and NLP-based emotion and sentiment analysis.

Scopes

• Affect Recognition & Sentiment Analysis
  Emotion, humor, irony, empathy, and social bonding detection

• Social Perception & Non-Verbal Cues
  Trust, dominance, deception, body language, and interpersonal rapport

• LLMs & Multimodal Fusion
  Using LLMs for embedding, fusion, and affect understanding

• Emotional TTS & Speech Synthesis
  Expressive, adaptive, and real-time emotion-based speech generation

• Fairness & Explainability
  Bias mitigation, transparent AI, and ethical considerations in emotion AI

• Conversational AI & Human-AI Interaction
  Empathetic, charismatic virtual agents and affect-aware systems.

• Continual Learning & Adaptation
  Lifelong learning, self-supervision, and domain adaptation in sentiment models.