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

Almenn færsla
dc.contributor.authorKhan, Omar Shahbaz
dc.contributor.authorSharma, Ujjwal
dc.contributor.authorMarcelino, Gonçalo
dc.contributor.authorDuane, Aaron
dc.contributor.authorRudinac, Stevan
dc.contributor.authorWorring, Marcel
dc.contributor.authorJónsson, Björn Pór
dc.contributor.departmentDepartment of Computer Science
dc.date.accessioned2026-09-24T13:51:01Z
dc.date.available2026-09-24T13:51:01Z
dc.date.issued2025-10-27
dc.descriptionPublisher Copyright: © 2025 Copyright held by the owner/author(s).en
dc.description.abstractWe 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.en
dc.description.versionPeer revieweden
dc.format.extent7
dc.format.extent2954679
dc.format.extent14273-14279
dc.format.extent
dc.identifier.citationKhan, O S, Sharma, U, Marcelino, G, Duane, A, Rudinac, S, Worring, M & Jónsson, B P 2025, Interactive Retrieval System for Multi-Stream Collections : MultiXview at CASTLE 2025 Interactive Grand Challenge. in MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025. MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025, Association for Computing Machinery, Inc, pp. 14273-14279, 33rd ACM International Conference on Multimedia, MM 2025, Dublin, Ireland, 27/10/25. https://doi.org/10.1145/3746027.3760243en
dc.identifier.citationconferenceen
dc.identifier.doi10.1145/3746027.3760243
dc.identifier.isbn9798400720352
dc.identifier.other251043256
dc.identifier.other6b000831-5fe1-46cf-9045-49d6701325f4
dc.identifier.other105024069106
dc.identifier.urihttps://hdl.handle.net/20.500.11815/8353
dc.language.isoen
dc.publisherAssociation for Computing Machinery, Inc
dc.relation.ispartofseriesMM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025; ()en
dc.relation.ispartofseriesMM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025; ()en
dc.relation.urlhttps://www.scopus.com/pages/publications/105024069106en
dc.rightsinfo:eu-repo/semantics/openAccessen
dc.subjectcastleen
dc.subjectmulti-stream interfaceen
dc.subjectmultimedia analyticsen
dc.subjectmultimedia retrievalen
dc.subjectHuman-Computer Interactionen
dc.subjectSoftwareen
dc.subjectArtificial Intelligenceen
dc.subjectComputer Graphics and Computer-Aided Designen
dc.titleInteractive Retrieval System for Multi-Stream Collections : MultiXview at CASTLE 2025 Interactive Grand Challengeen
dc.type/dk/atira/pure/researchoutput/researchoutputtypes/contributiontobookanthology/conferenceen

Skrár

Original bundle

Niðurstöður 1 - 1 af 1
Nafn:
3746027.3760243.pdf
Stærð:
2.82 MB
Snið:
Adobe Portable Document Format
Hlaða niður

Undirflokkur

Háskólinn í Reykjavík

Öll gögn í Opnum vísindum eru vernduð af ákvæðum höfundalaga og með öllum réttindum áskildum, nema annað sé tekið fram.