2nd Edition of the IJCV Special Issue on Audio-Visual Generation

Overview

CALL FOR PAPERS
We're accepting high-quality papers on the topic of audio-visual generation (and learning).

This special issue aims to spotlight the exciting yet underexplored field of audiovisual generation as a key stepping stone towards achieving multi-modal world simulators. Our goal is to prioritize innovative approaches that explore multimodal integration, advancing both the generation and analysis of audio-visual content. Advances in audiovisual generation can foster improvements in analysis and understanding methods, reinforcing the symbiotic relationship between these two areas. This research holds the potential to form a fundamental building block for more advanced, human-like AI systems.

Topics of Interest

Audio and image/video generation — Joint audio-visual generation, audio-to-image/video translation, audio-guided editing, and world simulator components.

Audio-conditional image/video/3D/4D generation — Audio-driven generation of 3D/4D scenes, human motion, dance, gestures, virtual avatars, and any-to-any generation.

Speech and talking avatar generation — Talking faces, head movements, and gestures in 2D/3D for authentic human-machine interaction.

Audio-visual adapters or interfaces — Adapter modules bridging heterogeneous audio-visual feature spaces, including multi-modal LLM interfaces.

Benchmarks and datasets — New datasets and evaluation metrics for audio-visual generation.

Ethical considerations and social impact — Privacy, deepfakes, algorithmic bias, and responsible use of synthetic media.

Generic topics and applications — Novel architectures, learning algorithms, fusion methods, and downstream applications (robotics, games, film).

Guest Editors

The team is led by Tae-Hyun Oh

Tae-Hyun Oh

Associate Professor, KAIST

Joon Son Chung

Associate Professor, KAIST

Joanna Hong

Research Scientist, Google DeepMind

Rodrigo Mira

Research Scientist, Google DeepMind

Stavros Petridis

GenAI Research Director, NatWest Group

Honorary Research Fellow, Imperial College London

Arda Senocak

Assistant Professor, UNIST

Zhixiang Wang

Researcher/Team Leader, CyberAgent AI Lab

Ming-Hsuan Yang

Professor, UC Merced; Yonsei University

Shiqi Yang

Research Scientist, SB Intuitions, SoftBank

Submission Guidelines

Please submit via IJCV Editorial Manager: www.editorialmanager.com/visi. Choose SI: Audio-Visual Generation from the article type dropdown.

Submitted papers should present original, unpublished work, relevant to one of the topics of the Special Issue. All submitted papers will be evaluated on the basis of relevance, significance of contribution, technical quality, scholarship, and quality of presentation, by at least two independent reviewers.

It is the policy of the journal that no submission, or substantially overlapping submission, be published or be under review at another journal or conference at any time during the review process.

FAQ

Q: Will you accept conference extensions? A: Yes. Conference-based extended papers are expected to have a minimum of 30% additional scientific contribution, e.g., in the form of new or improved algorithms or analysis, new experiments or qualitative/quantitative comparisons. Neither verbatim transfer of large parts of the conference paper nor reproduction of already published figures will be tolerated.

Q: Will audio-visual learning (discriminative learning rather than generation) be suitable for the special issue? A: Yes. We welcome submissions from relevant topics.

For full author guidelines, see the official CFP on Springer Nature and the IJCV manuscript guidelines.

Important Dates

Manuscript Submission Deadline	February 01 '27 11:59 PM AoE
First Review Notification	June 01 '27
Revised Manuscript Submission	August 01 '27
Final Review Notification	September 01 '27
Final Manuscript Submission	October '27
Publication	Fall 2027