The ACM Multimedia 2025 Grand Challenge of Avatar-based Multimodal Empathetic Conversation
The Ava-MERG Challenge at ACM Multimedia 2025 explores avatar-based multimodal empathetic response generation by advancing dialogue systems that respond with emotional awareness across text, speech, and talking-face video. To support this goal, we constructed a high-quality dataset featuring aligned multimodal responses in diverse conversational scenarios. The challenge comprises two progressively complex subtasks centering around multimodal-aware empathetic response generation. We aim to promote research in empathetic AI and affective computing.
Authors
- Hong Han (ORCID: https://orcid.org/0000-0002-8019-3740)
- Lizi Liao (ORCID: https://orcid.org/0000-0002-9973-3305)
- Erik Cambria (ORCID: https://orcid.org/0000-0002-3030-1280)
- Han Zhang (ORCID: https://orcid.org/0009-0006-9219-5598)
- Min Zhang (ORCID: https://orcid.org/0000-0003-4659-1822)
Institutions
- Xidian University (CN)
- National University of Singapore (SG)
- Nanyang Technological University (SG)
- Harbin Institute of Technology (CN)
- Singapore Management University (SG)
Publication Details
- Published
- 2025-10-25
- DOI
- https://doi.org/10.1145/3746027.3762028
- Primary Topic
- AI in Service Interactions
- Type
- article
- Field-Weighted Citation Impact
- 0.00