Zero-shot urban function inference with street view images through prompting a pretrained vision-language model
Author:
Affiliation:
1. School of Computer Science and Engineering, Nanyang Technological University, Singapore
2. Future Cities Laboratory, Singapore-ETH Centre, Singapore
Funder
the Knut and Alice Wallenberg Foundation
the National Research Foundation
Singapore MOE AcRF Tier-2
Singapore MOE AcRF Tier-1
Publisher
Informa UK Limited
Link
https://www.tandfonline.com/doi/pdf/10.1080/13658816.2024.2347322
Reference52 articles.
1. Allingham J.U. et al. 2023. A simple zero-shot prompt weighting technique to improve prompt ensembling in text-image models. In: International Conference on Machine Learning. PMLR 547–568.
2. Geographic mapping with unsupervised multi-modal representation learning from VHR images and POIs
3. Mining Geospatial Relationships from Text
4. Vlmo: Unified vision-language pre-training with mixture-of-modality-experts;Bao H.;Advances in Neural Information Processing Systems,2022
5. Interpreting clip with sparse linear concept embeddings (splice);Bhalla U.;arXiv Preprint arXiv:2402.10376,2024
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3