13 papers
XLocalizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization
Zichao Zeng, Weijia Fan, Yufan Chen +7
Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images. However, CVG approaches rely on fixed-length…
RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization
Junwei Zheng, Ruize Dai, Ruiping Liu +7
Metric Cross-View Geo-Localization (MCVGL) aims to estimate the 3-DoF camera pose (position and heading) by matching ground and satellite images. In this work, instead of pinhole a…
CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities
Junyuan Liu, Xinglei Wang, Zichao Zeng +5
Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundation models. However, current…
Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning
Zichao Zeng, June Moh Goo, Junwei Zheng +4
Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art methods employ Vision Transforme…
More than the Sum: Panorama-Language Models for Adverse Omni-Scenes
Weijia Fan, Ruiping Liu, Jiale Wei +7
Existing vision-language models (VLMs) are tailored for pinhole imagery, stitching multiple narrow field-of-view inputs to piece together a complete omni-scene understanding. Yet,…
Beyond AlphaEarth: Toward Human-Centered Geospatial Foundation Models via POI-Guided Contrastive Learning
Junyuan Liu, Quan Qin, Guangsheng Dong +4
Recent geospatial foundation models (GFMs) produce spatially extensive representations of the Earth's surface that capture rich physical and environmental patterns. Among them, the…