chore: update publications from Google Scholar

Author: github-actions[bot]

_data/pub/delete.bib

@@ -1,7 +1,7 @@
 % Publications that should not be visible on the lab webpage
 % PLEASE COPY AND PASTE IT FROM THE DYNAMIC.BIB FILE
 % If changes need to made for files in static.bib DO DIRECTLY IN STATIC.BIB
-% Updated on 2026-02-04T20:06:06Z
+% Updated on 2026-02-04T20:18:07Z
 
 @misc{Qasemi2025_mapqa_opendomain_geospatial_question_answering_on,
   abstract = {Geospatial question answering (QA) is a fundamental task in navigation and point of interest (POI) searches. While existing geospatial QA datasets exist, they are limited in both scale and diversity, often relying solely on textual descriptions of geo-entities without considering their geometries. A major challenge in scaling geospatial QA datasets for reasoning lies in the complexity of geospatial relationships, which require integrating spatial structures, topological dependencies, and multi-hop reasoning capabilities that most text-based QA datasets lack. To address these limitations, we introduce MapQA, a novel dataset that not only provides question-answer pairs but also includes the geometries of geo-entities referenced in the questions. MapQA is constructed using SQL query templates to extract question-answer pairs from OpenStreetMap (OSM) for two study regions: Southern California and Illinois. It consists of 3,154 QA pairs spanning nine question types that require geospatial reasoning, such as neighborhood inference and geo-entity type identification. Compared to existing datasets, MapQA expands both the number and diversity of geospatial question types. We explore two approaches to tackle this challenge: (1) a retrieval-based language model that ranks candidate geo-entities by embedding similarity, and (2) a large language model (LLM) that generates SQL queries from natural language questions and geo-entity attributes, which are then executed against an OSM database. Our findings indicate that retrieval-based methods effectively capture concepts like closeness and direction but struggle with questions that require explicit computations (e.g., distance calculations). LLMs (e.g., GPT and Gemini) excel at generating SQL queries for one-hop reasoning but face challenges with multi-hop reasoning, highlighting a key bottleneck in advancing geospatial QA systems.},

_data/pub/dynamic.bib

@@ -1,5 +1,5 @@
 % AUTO-GENERATED FILE. DO NOT EDIT.
-% Updated on 2026-02-04T20:06:06Z
+% Updated on 2026-02-04T20:18:07Z
 
 @inproceedings{10.1007/978-3-032-04617-8_3,
   abstract = {Historical maps contain valuable, detailed survey data often unavailable elsewhere. Automatically extracting linear objects, such as fault lines, from scanned historical maps benefits diverse application areas, such as mining resource prediction. However, existing models encounter challenges in capturing adequate image context and spatial context. Insufficient image context leads to false detections by failing to distinguish desired linear objects from others with similar appearances. Meanwhile, insufficient spatial context hampers the accurate delineation of elongated, slender-shaped linear objects. This paper introduces the Linear Object Detection TRansformer (LDTR), which directly generates accurate vector graphs for linear objects from scanned map images. LDTR leverages multi-scale deformable attention to capture representative image context, reducing false detections. Furthermore, LDTR's innovative N-hop connectivity component explicitly encourages interactions among nodes within an N-hop neighborhood, enabling the model to learn sufficient spatial context for generating graphs with accurate connectivity. Experiments show that LDTR improves detection precision by 6{\%} and enhances line connectivity by 20{\%} over state-of-the-art baselines.},

_data/pub/override.bib

@@ -1,3 +1,3 @@
 % PLEASE use the same reference ID when overriding information
-% Updated on 2026-02-04T20:06:06Z
+% Updated on 2026-02-04T20:18:07Z
 

_data/pub/static.bib

@@ -1,6 +1,6 @@
 % STATIC BIBS - FEEL FREE TO EDIT
 % DO NOT CHANGE ANY OF THE COMMENTS
-% Updated on 2026-02-04T20:06:06Z
+% Updated on 2026-02-04T20:18:07Z
 
 @inproceedings{10.1145/3589132.3625579,
   address = {New York, NY, USA},

publications.bib

@@ -1,5 +1,5 @@
 % AUTO-GENERATED FILE — DO NOT EDIT
-% Merged static.bib + dynamic.bib on 2026-02-04T18:43:36Z
+% Merged static.bib + dynamic.bib on 2026-02-04T20:18:07Z
 
 @inproceedings{10.1007/978-3-032-04617-8_3,
   abstract = {Historical maps contain valuable, detailed survey data often unavailable elsewhere. Automatically extracting linear objects, such as fault lines, from scanned historical maps benefits diverse application areas, such as mining resource prediction. However, existing models encounter challenges in capturing adequate image context and spatial context. Insufficient image context leads to false detections by failing to distinguish desired linear objects from others with similar appearances. Meanwhile, insufficient spatial context hampers the accurate delineation of elongated, slender-shaped linear objects. This paper introduces the Linear Object Detection TRansformer (LDTR), which directly generates accurate vector graphs for linear objects from scanned map images. LDTR leverages multi-scale deformable attention to capture representative image context, reducing false detections. Furthermore, LDTR's innovative N-hop connectivity component explicitly encourages interactions among nodes within an N-hop neighborhood, enabling the model to learn sufficient spatial context for generating graphs with accurate connectivity. Experiments show that LDTR improves detection precision by 6{\%} and enhances line connectivity by 20{\%} over state-of-the-art baselines.},