Interactive Retrieval System for Multi-Stream Collections: multiXview at CASTLE 2025 Interactive Grand Challenge
- ,
- Ujjwal Sharma,
- Gonçalo Marcelino,
- Aaron Duane,
- Stevan Rudinac,
- Marcel Worring
- Reykjavík University,
- University of Amsterdam
Research Output:
Journal Article or Conference Article in Journal
Conference article
Peer-reviewOpen access
Publication Information
Output type
Research Output:
Journal Article or Conference Article in Journal
Conference article
Peer-reviewOriginal language
EnglishPages from-to (Number of pages)
Pages 14273–14279 (7 pages)Journal (Volume, Issue Number)
MM '25Publication milestones
- Published - 25/10/2025
Publication status
Published - 25/10/2025
Publication IDs
- Scopus: 105024069106
Abstract
We introduce multiXview, an interactive retrieval framework for synchronized multi-camera video collections. It features a multi-index search engine that supports natural-language queries over visual embeddings, speech transcripts, and scene descriptions. It supports a synchronized multi-stream player offering parallel playback, and a timeline-based navigation view for temporal scoping and faceted exploration. These components address the redundancy and fragmentation of overlapping egocentric and exocentric video feeds and enable users to locate, aggregate, and reconstruct events across partial perspectives. This paper focuses on system design and implementation, with quantitative and qualitative evaluation to take place at the CASTLE 2025 Grand Challenge Interactive Track.
Publication metrics
PlumX, opens in new tab
Citations
1
Access to documents
Related Event
Title
ACM International Conference on Multimedia
Event type
ConferenceDate
27/10/2025 - 31/10/2025Location
Dublin Royal Convention Centre DublinIreland
