# lifeXplore at the Lifelog Search Challenge 2020

## TL;DR

This paper presents lifeXplore, a video retrieval system developed for the Lifelog Search Challenge 2020, integrating multiple advanced features like deep concept detection, OCR, and sketching to enhance lifelog retrieval.

## Contribution

The paper introduces an improved version of the lifeXplore system with new deep learning-based concept detection, OCR integration, and alternative shot segmentation methods.

## Key findings

- Enhanced retrieval accuracy with deep YOLO9000 concepts
- Effective use of OCR for text-based search
- Improved shot segmentation with uniform sampling

## Abstract

Since its first iteration in 2018, the Lifelog Search Challenge (LSC) - an interactive competition for retrieving lifelogging moments - is co-located at the annual ACM International Conference on Multimedia Retrieval (ICMR) and has drawn international attention. With the goal of making an ever growing public lifelogging dataset searchable, several teams develop systems for quickly solving time-limited queries during the challenge. Having participated in both previous LSC iterations, i.e. LSC2018 and LSC2019, we present our lifeXplore system - a video exploration and retrieval tool combining feature map browsing, concept search and filtering as well as hand-drawn sketching. The system is improved by including additional deep concept YOLO9000, optical character recognition (OCR) as well as adding uniform sampling as an alternative to the system's traditional underlying shot segmentation.