We are excited to invite you to participate in the IntentVC Challenge, held in conjunction with the 33rd ACM International Conference on Multimedia (ACM MM 2025).
Website: https://sites.google.com/view/intentvc/
[Challenge Overview]
The IntentVC Challenge addresses a fundamental limitation in video captioning by introducing user-controllable, intention-oriented outputs. Unlike traditional approaches that generate general-purpose descriptions, this challenge focuses on creating captions tailored to specific user-defined intentions, enhancing video understanding across various aspects.
Participants are encouraged to develop models capable of generating captions that align with different user intentions, thereby improving accessibility, personalization, and adaptability in multimedia applications.
[Important Dates]
21.06.2025: Paper invitation decisions
30.06.2025: Paper submission deadline
24.07.2025: Paper notifications
26.08.2025: Camera-ready submissions
(Please refer to the official website for any updates.)
[How to Participate]
1. Register: https://forms.gle/GbAMxY1TZ9upfEVk6
2. Access the dataset: https://sites.google.com/view/intentvc/dataset
3. Submit your results: https://sites.google.com/view/intentvc/evaluation
Top-ranked teams will be invited to submit a paper to ACM Multimedia 2025 and present at the conference, subject to peer review.
[Contact]
For any questions or further information, please contact us at: intentvc@gmail.com
We look forward to your participation and contributions to advancing intention-oriented controllable video captioning!
Best regards,
The IntentVC Organizing Committee
ACM Multimedia 2025 Challenge