Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video
cs.CV, cs.LG
Submitted: 2026-04-09
Updated: 2026-04-17
Project page: https://chanhyeok-choi.github.io/C-MET
Terminology
Sources
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Affective Conversational Agents: Understanding Expectations and Personal Influences
- GPT-4o System Card
- FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
- MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations
- EmoHead: Emotional Talking Head via Manipulating Semantic Expression Parameters
- Gemini: A Family of Highly Capable Multimodal Models
- Towards Accurate Generative Models of Video: A New Metric & Challenges
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs