Retrieval-Augmented Search for Large-Scale Map Collections with ColPali

• URL: http://arxiv.org/abs/2510.25718v1
• Date: Wed, 29 Oct 2025 17:27:21 GMT
• Title: Retrieval-Augmented Search for Large-Scale Map Collections with ColPali
• Authors: Jamie Mahowald, Benjamin Charles Germain Lee,
• Abstract summary: We introduce map-RAS: a retrieval-augmented search system for historic maps.<n>We detail our publicly-hosted demo for searching 101,233 map images held by the Library of Congress.
• Score: 1.3177681589844814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal approaches have shown great promise for searching and navigating digital collections held by libraries, archives, and museums. In this paper, we introduce map-RAS: a retrieval-augmented search system for historic maps. In addition to introducing our framework, we detail our publicly-hosted demo for searching 101,233 map images held by the Library of Congress. With our system, users can multimodally query the map collection via ColPali, summarize search results using Llama 3.2, and upload their own collections to perform inter-collection search. We articulate potential use cases for archivists, curators, and end-users, as well as future work with our system in both machine learning and the digital humanities. Our demo can be viewed at: http://www.mapras.com.

Related papers

• Digital Collections Explorer: An Open-Source, Multimodal Viewer for Searching Digital Collections [0.09208007322096533]
  Digital Collections Explorer is a web-based, open-source exploratory search platform.<n>Our interface enables natural language queries and reverse image searches over digital collections with visual features.<n>This paper describes the system's architecture, implementation, and application to various cultural heritage collections.
  arXiv  Detail & Related papers  (2025-07-01T17:10:34Z)
• ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework [73.91207117772291]
  ManuSearch is a transparent and modular multi-agent framework designed to democratize deep search for large language models (LLMs)<n>ManuSearch decomposes the search and reasoning process into three collaborative agents: (1) a solution planning agent that iteratively formulates sub-queries, (2) an Internet search agent that retrieves relevant documents via real-time web search, and (3) a structured webpage reading agent that extracts key evidence from raw web content.
  arXiv  Detail & Related papers  (2025-05-23T17:02:02Z)
• MapExplorer: New Content Generation from Low-Dimensional Visualizations [60.02149343347818]
  Low-dimensional visualizations, or "projection maps," are widely used to interpret large-scale and complex datasets.<n>These visualizations not only aid in understanding existing knowledge spaces but also implicitly guide exploration into unknown areas.<n>We introduce MapExplorer, a novel knowledge discovery task that translates coordinates within any projection map into coherent, contextually aligned textual content.
  arXiv  Detail & Related papers  (2024-12-24T20:16:13Z)
• VecCity: A Taxonomy-guided Library for Map Entity Representation Learning [48.73446321300362]
  Map entity representation learning (MapRL) generates versatile and reusable data representations.<n>We propose a novel taxonomy for MapRL that organizes models based on functional module-such as encoders, pre-training tasks, and downstream tasks.<n>We present a taxonomy-driven library, VecCity, which offers easy-to-use interfaces for encoding, pre-training, fine-tuning, and evaluation.
  arXiv  Detail & Related papers  (2024-10-31T07:03:46Z)
• Integrating Visual and Textual Inputs for Searching Large-Scale Map Collections with CLIP [0.09208007322096533]
  We explore the potential for interactively searching large-scale map collections using natural language inputs. As a case study, we adopt 562,842 images of maps publicly accessible via the Library of Congress's API. We present results for example searches created in consultation with staff in the Library of Congress's Geography and Map Division.
  arXiv  Detail & Related papers  (2024-10-02T02:51:02Z)
• Masked Image Modeling: A Survey [73.21154550957898]
  Masked image modeling emerged as a powerful self-supervised learning technique in computer vision.<n>We construct a taxonomy and review the most prominent papers in recent years.<n>We aggregate the performance results of various masked image modeling methods on the most popular datasets.
  arXiv  Detail & Related papers  (2024-08-13T07:27:02Z)
• MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions [64.89284104414865]
  We introduce MagicLens, a series of self-supervised image retrieval models that support open-ended instructions. MagicLens is built on a key novel insight: image pairs that naturally occur on the same web pages contain a wide range of implicit relations. MagicLens achieves results comparable with or better than prior best on eight benchmarks of various image retrieval tasks.
  arXiv  Detail & Related papers  (2024-03-28T17:59:20Z)
• The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Maps [7.209761597734092]
  mapKurator is an end-to-end system integrating machine learning models with a comprehensive data processing pipeline. We deployed the mapKurator system and enabled the processing of over 60,000 maps and over 100 million text/place names in the David Rumsey Historical Map collection.
  arXiv  Detail & Related papers  (2023-06-29T16:05:40Z)
• Multi-View Document Representation Learning for Open-Domain Dense Retrieval [87.11836738011007]
  This paper proposes a multi-view document representation learning framework. It aims to produce multi-view embeddings to represent documents and enforce them to align with different queries. Experiments show our method outperforms recent works and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2022-03-16T03:36:38Z)
• An Automatic Approach for Generating Rich, Linked Geo-Metadata from Historical Map Images [6.962949867017594]
  This paper presents an end-to-end approach to address the real-world problem of finding and indexing historical map images. We have implemented the approach in a system called mapKurator.
  arXiv  Detail & Related papers  (2021-12-03T01:44:38Z)
• MapReader: A Computer Vision Pipeline for the Semantic Exploration of Maps at Scale [1.5894241142512051]
  We present MapReader, a free, open-source software library written in Python for analyzing large map collections (scanned or born-digital) MapReader allows users with little or no computer vision expertise to retrieve maps via web-servers. We show how the outputs from the MapReader pipeline can be linked to other, external datasets.
  arXiv  Detail & Related papers  (2021-11-30T17:37:01Z)
• Prioritized Architecture Sampling with Monto-Carlo Tree Search [54.72096546595955]
  One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network. In this paper, we introduce a sampling strategy based on Monte Carlo tree search (MCTS) with the search space modeled as a Monte Carlo tree (MCT) For a fair comparison, we construct an open-source NAS benchmark of a macro search space evaluated on CIFAR-10, namely NAS-Bench-Macro.
  arXiv  Detail & Related papers  (2021-03-22T15:09:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.