@inproceedings{1df59030f6c84ca19d48138650043797,
title = "LIMITR: Leveraging Local Information for Medical Image-Text Representation",
abstract = "Medical imaging analysis plays a critical role in the diagnosis and treatment of various medical conditions. This paper focuses on chest X-ray images and their corresponding radiological reports. It presents a new model that learns a joint X-ray image & report representation. The model is based on a novel alignment scheme between the visual data and the text, which takes into account both local and global information. Furthermore, the model integrates domain-specific information of two types - lateral images and the consistent visual structure of chest images. Our representation is shown to benefit three types of retrieval tasks: text-image retrieval, class-based retrieval, and phrase-grounding. Our code is publicly available.",
author = "Gefen Dawidowicz and Elad Hirsch and Ayellet Tal",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 ; Conference date: 02-10-2023 Through 06-10-2023",
year = "2023",
doi = "10.1109/ICCV51070.2023.01935",
language = "الإنجليزيّة",
series = "Proceedings of the IEEE International Conference on Computer Vision",
pages = "21108--21116",
booktitle = "Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023",
}