Atomic: An Image/text Retrieval Test Collection To Support Multimedia Content Creation

Abstract

This paper presents the AToMiC (Authoring Tools for Multimedia Content) dataset, designed to advance research in image/text cross-modal retrieval. While vision-language pretrained transformers have led to significant improvements in retrieval effectiveness, existing research has relied on image-caption datasets that feature only simplistic image-text relationships and underspecified user models of retrieval tasks. To address the gap between these oversimplified settings and real-world applications for multimedia content creation, we introduce a new approach for building retrieval test collections. We leverage hierarchical structures and diverse domains of texts, styles, and types of images, as well as large-scale image-document associations embedded in Wikipedia. We formulate two tasks based on a realistic user model and validate our dataset through retrieval experiments using baseline models. AToMiC offers a testbed for scalable, diverse, and reproducible multimedia retrieval research

Stats

• citations6
• S2 citations—
• github stars21
• HF likes0
• heat score9.02
• arxiv keyyang2023atomic

Related papers

• Embedding Arithmetic Of Multimodal Queries For Image Retrieval (2021)9.03
• Tevatron 2.0: Unified Document Retrieval Toolkit Across Scale, Language, And Modality (2025)3.58
• Entity Image And Mixed-modal Image Retrieval Datasets (2025)1.56
• Scimmir: Benchmarking Scientific Multi-modal Information Retrieval (2024)8.07
• Docmmir: A Framework For Document Multi-modal Information Retrieval (2025)3.46
• Rethinking Benchmarks For Cross-modal Image-text Retrieval (2023)13.11
• Learning Audio-video Modalities From Image Captions (2022)12.54
• Stacmr: Scene-text Aware Cross-modal Retrieval (2020)10.48