Litcius/Paper detail

Exquisitor at the Lifelog Search Challenge 2020

Omar Shahbaz Khan, Mathias Dybkjær Larsen, Liam Alex Sonto Poulsen, Björn Þór Jónsson, Jan Zahálka, Stevan Rudinac, D.C. Koelma, Marcel Worring

202016 citationsDOIOpen Access PDF

Abstract

We present an enhanced version of Exquisitor, our interactive and scalable media exploration system. At its core, Exquisitor is an interactive learning system using relevance feedback on media items to build a model of the users' information need. Relying on efficient media representation and indexing, it facilitates real-time user interaction. The new features for the Lifelog Search Challenge 2020 include support for timeline browsing, search functionality for finding positive examples, and significant interface improvements. Participation in the Lifelog Search Challenge allows us to compare our paradigm, relying predominantly on interactive learning, with more traditional search-based multimedia retrieval systems.

Topics & Concepts

LifelogTimelineComputer scienceSearch engine indexingScalabilityRelevance (law)Information retrievalRelevance feedbackInterface (matter)World Wide WebMultimediaHuman–computer interactionArtificial intelligenceImage retrievalDatabaseArchaeologyLawPolitical scienceImage (mathematics)Maximum bubble pressure methodHistoryBubbleParallel computingMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesVideo Analysis and Summarization
Exquisitor at the Lifelog Search Challenge 2020 | Litcius