Interactive Retrieval System for Multi-Stream Collections: multiXview at CASTLE 2025 Interactive Grand Challenge

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.

Authors

Institutions

Publication Details

Published
2025-10-25
DOI
https://doi.org/10.1145/3746027.3760243
Citations
1
Primary Topic
Advanced Image and Video Retrieval Techniques
Type
article
Field-Weighted Citation Impact
1.28
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Interactive Retrieval System for Multi-Stream Collections: multiXview at CASTLE 2025 Interactive Grand Challenge

Gonçalo Marcelino, Aaron Duane, Ujjwal Sharma, Marcel Worring et al.
1 citations
Advanced Image and Video Retrieval Techniques
1.28
article

Interactive Retrieval System for Multi-Stream Collections: multiXview at CASTLE 2025 Interactive Grand Challenge

Gonçalo Marcelino, Aaron Duane, Ujjwal Sharma, Marcel Worring, Omar Shahbaz Khan, Stevan Rudinac, Björn Þór Jónsson
article en
1 citations

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.

Reykjavík University (IS), Copenhagen Hospitality College (DK), Amsterdam University of the Arts (NL), University of Amsterdam (NL)
Openalex Percentile: Top 15%
Advanced Image and Video Retrieval Techniques
1.28
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.