Research map / Vision-language and multimodal / Human and embodied modeling
HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual Geolocation
Hari Krishna Gadi, Daniel Matos, Hongyi Luo, Lu Liu, Yongliang Wang, Yanfeng Zhang, Liqiu Meng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use hyperbolic instead of Euclidean embedding space (ablation) | HierLoc · OSV5M | GeoScore: 3865 -> 3963 | Improved |
| use hyperbolic instead of spherical space (ablation) | HierLoc · OSV5M | GeoScore: 3364 -> 3963 | Improved |
| use GWH-InfoNCE instead of standard InfoNCE (ablation) | HierLoc · OSV5M | GeoScore: 3840 -> 3963 | Improved |
| add cross-modal attention (ablation) | HierLoc · OSV5M | GeoScore: 2904 -> 3963 | Improved |
| use squared distance in loss (ablation) | HierLoc · OSV5M | GeoScore: 3752 -> 3963 | Improved |
| add text and location features (ablation) | HierLoc · OSV5M | GeoScore: 3890 -> 3963 | Improved |
| use hierarchical beam search (k=10) instead of flat search (ablation) | HierLoc · OSV5M | city accuracy: 22.1 -> 23.3 | Improved |
| use hierarchical search with beam 1 instead of flat (ablation) | HierLoc · OSV5M | city accuracy: 22.1 -> 21.9 | No clear effect |
| swap DINOv3 for ViT-L/14 backbone (ablation) | HierLoc · OSV5M | GeoScore: 3963 -> 3850 | Hurt |
| use DINOv3 instead of DINOv2 (ablation) | HierLoc · YFCC4K | GeoScore: 3106 -> 3189 | Improved |
Closest papers by meaning
- Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation (CVPR 2025 · similarity 0.88)
- GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization (NeurIPS 2025 · similarity 0.87)
- Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach (AAAI 2026 · similarity 0.87)
- G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models (NeurIPS 2024 · similarity 0.87)
- GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization (NeurIPS 2026 · similarity 0.86)
- LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert Space (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
