EUFCC-CIR: a Composed Image Retrieval Dataset for GLAM Collections

Francesc Net, Lluis Gomez
10/2/2024
cs.CV

No official code found. Best implementation: cesc47/EUFCC-CIR (4 stars, last commit 2024-10-03).

Abstract

The intersection of Artificial Intelligence and Digital Humanities enables researchers to explore cultural heritage collections with greater depth and scale. In this paper, we present EUFCC-CIR, a dataset designed for Composed Image Retrieval (CIR) within Galleries, Libraries, Archives, and Museums (GLAM) collections. Our dataset is built on top of the EUFCC-340K image labeling dataset and contains over 180K annotated CIR triplets. Each triplet is composed of a multi-modal query (an input image plus a short text describing the desired attribute manipulations) and a set of relevant target images. The EUFCC-CIR dataset fills an existing gap in CIR-specific resources for Digital Humanities. We demonstrate the value of the EUFCC-CIR dataset by highlighting its unique qualities in comparison to other existing CIR datasets and evaluating the performance of several zero-shot CIR baselines.

View on arXivView PDF

Code Implementations(1)

cesc47/EUFCC-CIRCommunity100%

EUFCC-CIR: A Composed Image Retrieval Dataset for GLAM Collections

41Oct 2, 20242 years ago

Similar Papers

EUFCC-340K: A Faceted Hierarchical Dataset for Metadata Annotation in GLAM Collections

87% match1 repo72024

Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconography

82% match2025

IICONGRAPH: improved Iconographic and Iconological Statements in Knowledge Graphs

80% match2024

Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage

80% match1 repo62023

VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery

80% match1 repo92025

Optimization of Image Processing Algorithms for Character Recognition in Cultural Typewritten Documents

79% match2023

Cite this paper

@article{net2024eufcccir,
  title  = {EUFCC-CIR: a Composed Image Retrieval Dataset for GLAM Collections},
  author = {Francesc Net and Lluis Gomez},
  year   = {2024},
  eprint = {2410.01536},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.01536v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.01536.svg)](https://codeofpaper.com/paper/2410.01536)

Discussion