News Event Retrieval and Explanation from Large Collection of TV News Videos

(a grand challenge in ACM Multimedia 2025, organized in Dublin, Ireland, from 27 to 31 October 2025)

🗞️ News

News Event Retrieval and Explanation from Large Collection of TV News Videos

The News Event Retrieval and Explanation Grand Challenge at ACM Multimedia 2025 is focused on retrieving, analyzing, and explaining news events from large-scale TV news video collections.

The challenge will be co-located with ACM Multimedia 2025, organized in Dublin, Ireland from 27 to 31 October, 2025

The challenge features two evaluation modes: Interactive Mode (similar to VBS and LSC), where users refine queries and interact with the system, and Automatic Mode, where AI autonomously retrieves and explains news events. In Interactive Mode, the focus is on real-time human-AI collaboration, while Automatic Mode tests autonomous retrieval and reasoning. Both modes assess efficiency, accuracy, and scalability.

Participants will work with a large, multimodal dataset of TV news videos from various sources, including CNN, BBC, Reuters, and Vietnamese news channels. The dataset will include annotations such as speech transcriptions, OCR-extracted text, and temporal event timestamps. The challenge will use AI models for multimodal retrieval, video segmentation, and event explanation.

Organizers

Cathal Gurrin

Dublin City University,

Ireland

Minh-Triet Tran

University of Science, VNUHCM, Vietnam

Klaus Schöffmann

Klagenfurt University,

Austria

Duc-Tien Dang-Nguyen

University of Bergen,

Norway

Trong-Le Do

University of Science, VNUHCM, Vietnam

Hai-Dang Nguyen

University of Science, VNUHCM, Vietnam

Thanh Duc Ngo

University of Information Technology, VNUHCM, Vietnam

Vinh-Tiep Nguyen

University of Information Technology, VNUHCM, Vietnam

Viet-Tham Huynh

University of Science, VNUHCM, Vietnam

Quang-Thuc Nguyen

University of Science, VNUHCM, Vietnam

Tu V. Ninh

Dublin City University,

Ireland

Tu-Khiem Le

Dublin City University,

Ireland

Mai-Khiem Tran

University of Science, VNUHCM, Vietnam

Tu-Trinh Ngo

Youth Scientific & Technological Promotion Center, Vietnam

Important Dates (Anywhere on Earth)

🔹 Team Registration Opens: April 25, 2025

📂 Public Dataset Release: June 1, 2025

🔒 Team Registration Closes: June 15, 2025

⚙️ First Automatic Evaluation Round: July 1, 2025

⚙️ Second Automatic Evaluation Round: July 15, 2025

🎥 Final Round (Online): July 30, 2025

📝 Results, Report, Paper submission deadline: August 1, 2025

Paper Submission

AUTHOR GUIDELINES

Submitted papers (.pdf format) must use the ACM Article Template (https://www.acm.org/publications/proceedings-template). Please remember to add Concepts and Keywords. Please use the template in traditional double-column format to prepare your submissions. For example, word users should use Word Interim Template, and LaTeX users should use sample-sigconf-authordraft template. When using sample-sigconf-authordraft template, for submission and review of manuscript you could use the following documentclass command instead of the example provided in the template:\documentclass[sigconf, screen, review, anonymous]{acmart}

Please ensure that you submit your papers subscribing to this format for full consideration during the review process.

SUBMISSION GUIDELINES

We would like to invite Top-3 performing teams to submit a technical paper (6+2 pages) via the CMT system by the deadline (August, 1, 2025).
Submissions are not required to be anonymous.
Papers must follow ACM formatting strictly and be ready for possible publication in the proceedings of ACM MM (Grand Challenge)

WHERE TO SUBMIT

Submissions are handled via the Microsoft CMT system: https://cmt3.research.microsoft.com/NewsVidEX2025

CMT Acknowledgment

The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.

Page updated

Report abuse