Embedded Files
The Cross-Cultural Misogynistic Meme Detection (CC-MMD) challenge is hosted as an ICMI 2026 Grand Challenge. It benchmarks culturally robust multimodal systems for binary misogyny classification in memes across Indian, Chinese, and Western (English) contexts. Online misogyny increasingly appears in multimodal formats such as memes. Memes combine text and images to convey humor, sarcasm, and ideology. Misogynistic meaning is often implicit and culturally grounded. A meme interpreted as harmful in one cultural setting may be perceived differently in another.
Current multimodal models achieve strong performance in high-resource settings but often lack cultural grounding. They struggle under cross-lingual and cross-cultural distribution shifts. Prior findings show that cultural background significantly influences misogyny annotation and interpretation. CC-MMD dataset addresses this challenge through multilingual data and systematic cross-cultural annotation. The benchmark explicitly evaluates robustness across cultural partitions rather than a single pooled test set.
This Grand Challenge invites participants to build culture-aware multimodal systems that generalize reliably under cultural shifts.
Submission Google Form Link: https://forms.gle/qLZpZz6y7dYjNuhu9
(Update) The rank list is released—find it in the results tab on the codabench competition page.
Check out our starter code, baseline code, and baseline results in the below link.
Starter code: https://github.com/rahulponnusamy/CC-MMD/blob/main/starter_code.ipynb
Baseline code: https://github.com/rahulponnusamy/CC-MMD/tree/main/baseline_codes
Why It Matters
Content moderation systems are often trained in dominant cultural contexts. This risks biased predictions and inconsistent decisions across regions. Misogyny detection requires sensitivity to implicit language, humor, symbolism, and local norms.
By explicitly evaluating cultural robustness, this challenge advances research toward more inclusive, reliable, and globally deployable multimodal systems.
Paper Submission Guidelines:
All participating teams in the CC-MMD 2026 Grand Challenge are invited to submit a system description paper. Submission is open to all participating teams, but participation in the challenge does not guarantee paper acceptance. All papers will undergo peer review, and acceptance will depend on the quality of the submission and the review process.
Paper Format
Paper Format
System description papers should follow the official ACM ICMI 2026 submission guidelines and use the ACM ICMI 2026 paper template.
Paper length: Maximum 4 pages, excluding references.
Authors using LaTeX should use the ACM conference format with: \documentclass[sigconf,anonymous,review]{acmart}
Latex template: https://portalparts.acm.org/hippo/latex_templates/acmart-primary.zip (Note:The reason we recommend LaTeX is to avoid unnecessary formatting issues.)
For more details you can visit ICMI 2026 author guidelines page: https://icmi.acm.org/2026/guidelines/
Submission Link
Submission Link
Papers must be submitted through the ACM ICMI 2026 PCS submission system: https://new.precisionconference.com/submissions/icmi26a
Please select the track: ICMI 2026 Grand Challenge: CC-MMD
Title Format
Title Format
The paper title should follow this format: TEAM_NAME@CC-MMD 2026: Title of the Paper
Example: UOG@CC-MMD 2026: Cross-Cultural Misogynistic Meme Detection using Multimodal Transformers
Paper Content
Paper Content
Papers should briefly describe the submitted system, including the main methodology, task setting, experimental setup, and official results. Authors are encouraged to include implementation details, analysis, and discussion of cross-cultural aspects where relevant.
If available, authors may also include a GitHub link to their code repository, but we highly recommend it.
Review and Ethics
Review and Ethics
All submissions must follow a double-blind review format. Author names, affiliations, acknowledgements, and other identifying information should not be included in the review version.
Authors should cite the relevant source datasets used in the challenge; refer to the Term tab for BibTeX..
Submissions should follow ACM ethical standards and include any required responsible research or broader impact statement according to the ACM ICMI 2026 guidelines.
Important Note
Important Note
In case of any conflict between the CC-MMD instructions and the official ACM ICMI 2026 guidelines, the ACM ICMI 2026 guidelines will take precedence.
Call for Participation
We invite researchers, students, and practitioners to participate in the ICMI 2026 Grand Challenge. Join us in building culturally robust multimodal systems for responsible and cross-cultural content moderation.
How to participate
Read the terms from the Terms tab before registering to the compitition.
Complete the registration on Codabench link: https://www.codabench.org/competitions/14187/
After registration, you will receive access to the training and development data.
Develop a system for Task A and/or Task B using the provided data and guidelines.
Generate predictions for the test sets once after they are released and submit them through the Google_Forms:https://forms.gle/qLZpZz6y7dYjNuhu9 (Update)
Check the results tab in the codabench for final run scores.
Page updated
Google Sites
Report abuse