In this paper, we present Memento 2.0, an improved version of our
system which first participated in the Lifelog Search Challenge 2021.
Memento 2.0 employs image-text embeddings derived from two
CLIP models (ViT-L/14 and ResNet-50x64) and adopts a weighted
ensemble approach to derive a combined final ranking. Our approach significantly improves the performance over the baseline
LSC’21 system. We additionally make important updates to the
system’s user interface after analysing the shortcomings to make it
more efficient and better suited to the needs of the Lifelog Search
Challenge.