Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.3%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: YuanuanLi
  • Default Branch: main
  • Size: 773 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Created about 1 year ago · Last pushed 10 months ago
Metadata Files
Readme Citation

README.md

VIGOR-Building Dataset

VIGOR-Building Dataset Examples

Introduction

The VIGOR-Building dataset aims to evaluate the cross-view object geo-localization task in a more realistic setting, bridging the gap between many-to-many object localization and existing datasets. VIGOR-Building is built upon the VIGOR-GEN dataset1 and aims to provide a more comprehensive and realistic resource to support research and development in the field of cross-view object geo-localization.

Data Collection

The VIGOR-Building dataset includes images from three major cities: Chicago, New York, and San Francisco. We have randomly selected images from these cities to ensure diversity and comprehensive coverage.

Data Annotation

To facilitate object localization, we annotated the ground images using YOLOv9 and the satellite images using OpenStreetMap. Additionally, manual annotations were performed to refine the dataset.

Download

The download link is VIGOR-Building.

Citation

[1] Yang H, Li Y, Zhu Y. Retrieval-guided Cross-view Image Synthesis[J]. arXiv preprint arXiv:2411.19510, 2024.

[2] Li Y, Zhang Q, Zhu Y. Rethinking Cross-view Object Geo-Localization: Towards Many-to-Many Real-world Localization[C]//2025 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2025.

Owner

  • Login: YuanuanLi
  • Kind: user

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: Li
    given-names: Yuanyuan
    orcid: https://orcid.org/0009-0006-2045-1273
title: "VIGOR-Building Dataset"
version: 1.0.0
identifiers:
  - type: doi
    value: 10.5281/zenodo.14523573
date-released: 2024-12-19

GitHub Events

Total
  • Release event: 1
  • Push event: 11
  • Create event: 3
Last Year
  • Release event: 1
  • Push event: 11
  • Create event: 3