MIS-24

Multi-modal Misinformation Governance in the Era of Foundation Models
Co-located with 2024 ACM Multimedia (ACM MM 2024)
28 October - 1 November 2024, Melbourne, Australia


Call for Papers

In recent years, the emergence of foundation models, such as GPT (Generative Pre-trained Transformer) and CLIP (Contrastive Language-Image Pre-training), has revolutionized the field of artificial intelligence, enabling significant advancements in natural language processing and computer vision tasks. However, these large-scale multimodal models also pose serious challenges in combating the spread of misinformation across multiple modalities. This workshop aims to bring together researchers and practitioners to discuss and address the following topics (but not limited):

  1. New Datasets and Benchmarks
    Developing new datasets and benchmarks to facilitate progress in multi-modal misinformation detection and analysis.
  2. Theoretical foundations and challenges
    Theoretical foundations and challenges of multi-modal misinformation detection and analysis in the era of foundation models
  3. Evaluating Techniques
    Techniques for evaluating the effectiveness and robustness of multimodal misinformation detection systems
  4. Ethical and Societal Thinking
    Ethical considerations and societal impacts of misinformation governance using foundation models
  5. Novel Methodologies
    Progress and advancements in developing novel methodologies and approaches for detecting and combating multi-modal misinformation
  6. Case and Applications
    Case studies and real-world applications showcasing successful strategies for mitigating the spread of misinformation
  7. Future Directions
    Future directions and research agendas in the field of multi-modal misinformation governance leveraging foundation models

programme

The proposed workshop will include 3 invited talks and 3 or more paper presentations. The workshop will be considered for a half-day meeting.

Duration Title Speaker
5 min Welcome + Opening Zheng Wang, Wuhan University
20 min A Multi-modal Framework for Fake News Detection Rajiv Ratn Shah, IIIT-Delhi (TBD)
20 min Detecting and Grounding Multi-Modal Media Manipulation Rui Shao, Harbin Institute of Technology (Shenzhen) (TBD)
10 min Coffee Break
15 min Paper1 Presentation TBD
15 min Paper2 Presentation TBD
15 min Paper3 Presentation TBD
... ... ...
30 min Round Table Discussion Workshop Host

Submission

Organizers

Shaojing Fan

NUS
Senior Research Fellow

Zheng Wang

WHU
Professor

Rui Shao

HIT (Shenzhen)
Professor

Song Bai

ByteDance
Adjunct Assistant Professor at NUS

Hongyuan Zhu

I^2R, A*STAR


Liqiang Nie

HIT (Shenzhen)
Professor

Shin'ichi Satoh

NII/UTokyo
Professor

Program Committee


IMPORTANT DATES


TENTATIVE KEYNOTES (updating)