VERGE in VBS 2026

Read full text
Authors: Nick Pantelidis, Eleni Kosmidou, Damianos Galanopoulos, Dimitris Georgalis, Stefanos Pasios, Konstantinos Apostolidis, Andreas Goulas, Maria Eirini Pegia, Georgios Tsionkis, Konstantinos Gkountakos, Grigorios Kouvrakis, Anastasia Moumtzidou
+4 more Ilias Gialampoukidis, Stefanos Vrochidis, Vasileios Mezaris, Ioannis Yiannis Kompatsiaris
Cited by: 0

Abstract

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.

Fields of Study & Subjects

Video Analysis and Summarization Image Retrieval and Classification Techniques Information Retrieval and Search Behavior

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
29 January 2026