Data for "Improving semantic video retrieval models by training with a relevance-aware online mining strategy"

This repository contains all the data available for the publication:

Alex Falcon, Giuseppe Serra, and Oswald Lanz. Improving semantic video retrieval models by training with a relevance-aware online mining strategy. Computer Vision and Image Understanding. 2024.

Code is available at: https://github.com/aranciokov/ranp/

The data includes:

pre-extracted features (ordered_feature_*.zip files)

annotations, such as pre-extracted semantic graphs, glove checkpoints, class annotations, etc (annotations_*.zip files)

train/val/test, when available, split information (public_split_*.zip) files

pretrained models for HGR and EAO (details in the github repo)