VIRET Tool with Advanced Visual Browsing and Feedback
Gregor Kovalčík, Vít Škrhák, Tomáš Souček, Jakub Lokoč
Abstract
VIRET is a video retrieval system that performed competitively in several recent interactive multimedia search competitions. For the Lifelog Search Challenge 2020, we implement several new features that focus on result set presentation based on dynamically computed self-organized maps, as well as additional feedback about the distribution of relevance scores for a query. The latter feature provides users with more insight to assess input queries and could help with the design of new ranking models in the future.
Topics & Concepts
Computer scienceRelevance feedbackRanking (information retrieval)LifelogFocus (optics)Information retrievalRelevance (law)Presentation (obstetrics)Feature (linguistics)Set (abstract data type)MultimediaHuman–computer interactionWorld Wide WebImage retrievalImage (mathematics)Artificial intelligenceLawLinguisticsMedicineRadiologyPhysicsPolitical scienceOpticsProgramming languagePhilosophyAdvanced Image and Video Retrieval TechniquesMultimodal Machine Learning ApplicationsVideo Analysis and Summarization