Scholar
Jina Kim
Google Scholar ID: kS2XsAsAAAAJ
Ph.D. Student, University of Minnesota
Citations & Impact
Citations
1,388
H-index
17
i10-index
19
Publications
20
Co-authors
7
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- November 2025: Participated in ACM SIGSPATIAL 2025 and presented multiple projects; June 2025: Co-organized a workshop at UCGIS 2025; April 2025: Interactive map selected for the Map Gallery at the 2025 Big Ten GIS Conference; October 2024: Published a paper at ACM SIGSPATIAL 2024; July 2024: Won Best Overall Map at the 2024 U-Spatial Mapping Prize; November 2023: Won first place in the Student Research Competition at ACM SIGSPATIAL '23; August 2023: Attended the kick-off meeting for the DARPA CriticalMAAS project.
Research Experience
- November 2025: Presented StreetLens in GeoHCC and RegionContext in UrbanAI at ACM SIGSPATIAL 2025, co-authored trajectory mining papers in GeoAnomalies and GeoGenAgent, and won 7th place in GISCUP; June 2025: Co-organized a workshop on capturing human perception of neighborhoods using online data with language and vision models at UCGIS 2025; March 2025: Presented ongoing work on points of interest data contextualization using a spatial language model for learning functional roles of regions at the 2025 AAG Annual Meeting; October 2024: Presented a paper on context-aware trajectory anomaly detection as the second author at the 1st GeoAnomalies workshop during ACM SIGSPATIAL 2024; Summer 2024: Joined Amazon as an Applied Scientist Intern, contributing to the development of multimodal models on video understanding.
Education
- PhD: Computer Science & Engineering Department at the University of Minnesota, advised by Prof. Yao-Yi Chiang; Master's: Interaction Science from Sungkyunkwan University, supervised by Prof. Eunil Park; Bachelor's: Computer Engineering from Hansung University.
Background
- Research interests: spatial artificial intelligence and multimodal learning. Focuses on developing techniques to automatically extract meaningful information from large-scale, multimodal spatial data, including overhead images, trajectories, and documents such as scanned images or natural language documents containing valuable geographic information. Also interested in validating technologies beyond accuracy using social science methodologies.
Miscellany
- Pronouns: she/her; Contact: kim01479@umn.edu; Involved in various social activities such as BPC co-chair, DEI networking event organizer, etc.; Co-teaching CSCI 5523: Introduction to Data Mining in Spring 2025.
