SOMHunter for Lifelog Search
František Mejzlík, Patrik Veselý, Miroslav Kratochvíl, Tomáš Souček, Jakub Lokoč
Abstract
We present an extended version of SOMHunter, an interactive retrieval tool designed for known-item and ad-hoc search tasks over image and video datasets. Even though SOMHunter has achieved significant success at the most recent Video Browser Showdown 2020 competition, lifelog datasets and related search tasks constitute a different challenge with specific problems to be addressed. The presented version of SOMHunter integrates functionality required to deal with lots of highly similar images collected in typical lifelogs. Additionally, we employ search in available metadata including date and time filters.
Topics & Concepts
LifelogComputer scienceMetadataInformation retrievalKeyword searchSearch engineWorld Wide WebHuman–computer interactionMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesVideo Analysis and Summarization