M4D - Multimodal Data Fusion and Analytics Group
Published January 29, 2026 | Version v1
Conference paper Embargoed

VERGE in VBS 2026

Authors/Creators

  • 1. ROR icon Centre for Research and Technology Hellas
  • 2. CERTH
  • 3. Centre for Research and Technology-Hellas

Description

This paper describes VERGE, an interactive system for retrieving video content, supporting searches over images extracted from videos. The system retains its core retrieval modalities and fusion techniques in an improved form, while introducing new modalities, including optical character recognition, video question answering, underwater object detection, image quality-based retrieval, and surgical scenes understanding. VERGE’s web application continues to offer its user-friendly interface, helping users create queries and efficiently explore the top search results. The system now incorporates newly extracted keyframes for the V3C dataset, generated with a new algorithm developed for this purpose.

Files

Embargoed

The files will be made publicly available on January 31, 2027.

Additional details

Funding

European Commission
UP2030 - Urban Planning and design ready for 2030 101096405
European Commission
NAMOR - A Novel compact and Advanced hybrid Microalgae-membrane photobioreactor Optimized for Retrofitting decentralized water and wastewater management systems 101182365
European Commission
AQUAMON - AQUAMON: Advanced QUAlity MOnitoring system of water in urbaN areas 101181380
European Commission
AI4TRUST - AI-based-technologies for trustworthy solutions against disinformation 101070190
European Commission
TransMIXR - Ignite the Immersive Media Sector by Enabling New Narrative Visions 101070109
European Commission
PERIVALLON - Protecting the EuRopean terrItory from organised enVironmentAl crime through inteLLigent threat detectiON tools 101073952

Dates

Submitted
2026-01-29