Memento: A Prototype Lifelog Search Engine for LSC'21
Naushad Alam, Yvette Graham, Cathal Gurrin
Abstract
In this paper, we introduce a new lifelog retrieval system called Memento that leverages semantic representations of images and textual queries projected into a common latent space to facilitate effective retrieval. It bridges the semantic gap between complex visual scenes/events and user information needs expressed as textual and faceted queries. The system, developed for the 2021 Lifelog Search Challenge, also has a minimalist user interface that includes primary search, temporal search, and visual data filtering components.
Topics & Concepts
LifelogComputer scienceInformation retrievalSemantic gapSpace (punctuation)Search engine indexingSearch engineInterface (matter)World Wide WebArtificial intelligenceImage retrievalImage (mathematics)Human–computer interactionMaximum bubble pressure methodParallel computingOperating systemBubbleVideo Analysis and SummarizationAdvanced Image and Video Retrieval TechniquesMultimodal Machine Learning Applications