PlaceSeek：通过语义 grounding 与情感对齐实现以人类为中心的城市户外地点地理空间检索
PlaceSeek: Human-Centered Geospatial Retrieval of Urban Outdoor Places via Semantic Grounding and Affective Alignment
浏览论文内容
中文总结 AI 辅助
该研究针对现有地理空间检索难以满足情感/活动类需求的问题，提出 PlaceSeek 框架，通过语义 grounding 与情感对齐实现城市户外地点检索，在米兰数据集上的表现优于多种基线方法。
中文摘要 AI 辅助
人们搜索城市户外地点时，不仅会依据地点的类别或功能，还会考虑该地点能支持的活动类型以及人们对它的感知。现有的地理空间检索大多以兴趣点（POI）为中心且由元数据驱动，难以满足开放性、情感性或面向活动的需求。本文提出 PlaceSeek，这是一种以人类为中心的户外地点检索框架，可将自然语言查询映射到带地理定位的街景图像。PlaceSeek 引入了一种意图感知检索机制，能将用户查询分解为功能与情感两类子意图；其中语义 grounding 模块会验证候选街景结果是否包含支持目标活动所需的物理证据，情感对齐模块则使用基于人类城市感知判断训练的 LoRA 适配视觉-语言模型对物理上有效的候选结果进行重新排序。我们在米兰的 31956 个街景地点上，通过 10 个由 5 名人类评估者标注的自然语言查询对 PlaceSeek 进行评估，PlaceSeek 实现了 88.0% 的 Precision@5、3.39/4.0 的平均匹配得分以及 0.920 的 nDCG@5，表现优于 CLIP、微调后的 CLIP、SigLIP 以及基于视觉问答（VQA）的基线方法。 ablation 结果表明，物理 grounding 对检索有效性至关重要，而情感对齐则能提升物理有效候选结果间的排序质量。这些发现说明，复杂的城市空间查询需要同时对可验证的视觉证据与人类感知偏好进行建模，PlaceSeek 为以人类为中心的下一代地理空间检索系统提供了潜在框架。
英文摘要
People search for urban outdoor places not only by category or function, but also by what activities a place can support and how it is perceived. Existing geospatial retrieval remains largely POIcentric and metadata-driven, making it difficult to satisfy openended, affective, or activity-oriented needs. We present PlaceSeek, a human-centered outdoor place retrieval framework that maps natural-language queries to geolocated street-view imagery. PlaceSeek introduces an intent-aware retrieval mechanism that decomposes user queries into functional and affective sub-intents. A Semantic Grounding Module verifies whether candidate street-view results contain the physical evidence needed to support the intended activity, while an Affective Alignment Module re-ranks physically valid candidates using a LoRA-adapted vision-language model trained on human urban perception judgments. We evaluate PlaceSeek on 31,956 street-view locations in Milan across 10 naturallanguage queries annotated by five human evaluators. PlaceSeek achieves 88.0% Precision@5, a mean match score of 3.39/4.0, and 0.920 nDCG@5, outperforming CLIP, fine-tuned CLIP, SigLIP, and a VQA-based baseline. Ablation results show that physical grounding is essential for retrieval validity, while affective alignment improves ranking quality among physically valid candidates. These findings highlight that complex urban spatial queries require modeling both verifiable visual evidence and human perceptual preferences. PlaceSeek provides a potential framework for human-centered nextgeneration geospatial retrieval systems.
发表机构
- University of British Columbia（不列颠哥伦比亚大学）
- University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）
- San Diego State University（圣地亚哥州立大学）
机构由 AI 辅助整理，请以论文原文为准。
