Christian S. Jensen
YOU?
Author Swipe
View article: Comprehending Spatio-temporal Data via Cinematic Storytelling using Large Language Models
Comprehending Spatio-temporal Data via Cinematic Storytelling using Large Language Models Open
Spatio-temporal data captures complex dynamics across both space and time, yet traditional visualizations are complex, require domain expertise and often fail to resonate with broader audiences. Here, we propose MapMuse, a storytelling-bas…
View article: Skeleton-Guided Learning for Shortest Path Search
Skeleton-Guided Learning for Shortest Path Search Open
Shortest path search is a core operation in graph-based applications, yet existing methods face important limitations. Classical algorithms such as Dijkstra's and A* become inefficient as graphs grow more complex, while index-based techniq…
View article: TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting
TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting Open
Time Series Forecasting (TSF) is key functionality in numerous fields, such as financial investment, weather services, and energy management. Although increasingly capable TSF methods occur, many of them require domain-specific data collec…
View article: Unsupervised Time Series Anomaly Prediction with Importance-based Generative Contrastive Learning
Unsupervised Time Series Anomaly Prediction with Importance-based Generative Contrastive Learning Open
We study the problem of time series anomaly prediction, which is relevant to a range of real-world applications. Existing anomaly prediction methods rely on labeled training data for achieving acceptable accuracy. However, such data may be…
View article: MH-GIN: Multi-scale Heterogeneous Graph-based Imputation Network for AIS Data (Extended Version)
MH-GIN: Multi-scale Heterogeneous Graph-based Imputation Network for AIS Data (Extended Version) Open
Location-tracking data from the Automatic Identification System, much of which is publicly available, plays a key role in a range of maritime safety and monitoring applications. However, the data suffers from missing values that hamper dow…
View article: Prioritizing Alignment Paradigms over Task-Specific Model Customization in Time-Series LLMs
Prioritizing Alignment Paradigms over Task-Specific Model Customization in Time-Series LLMs Open
Recent advances in Large Language Models (LLMs) have enabled unprecedented capabilities for time-series reasoning in diverse real-world applications, including medical, financial, and spatio-temporal domains. However, existing approaches t…
View article: Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review
Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review Open
Spatio-temporal deep learning models aims to utilize useful patterns in such data to support tasks like prediction. However, previous deep learning models designed for specific tasks typically require separate training for each use case, l…
View article: Data Driven Decision Making with Time Series and Spatio-Temporal Data
Data Driven Decision Making with Time Series and Spatio-Temporal Data Open
Time series data captures properties that change over time. Such data occurs widely, ranging from the scientific and medical domains to the industrial and environmental domains. When the properties in time series exhibit spatial variations…
View article: Web-Centric Human Mobility Analytics: Methods, Applications, and Future Directions in the LLM Era
Web-Centric Human Mobility Analytics: Methods, Applications, and Future Directions in the LLM Era Open
Human mobility analytics is essential to enabling a broad range of web-related applications, such as navigation, urban planning, and point-of-interest (POI) recommendation. The proliferation of mobility data, including geo-social media che…
View article: A Multi-Modal Knowledge-Enhanced Framework for Vessel Trajectory Prediction
A Multi-Modal Knowledge-Enhanced Framework for Vessel Trajectory Prediction Open
Accurate vessel trajectory prediction facilitates improved navigational safety, routing, and environmental protection. However, existing prediction methods are challenged by the irregular sampling time intervals of the vessel tracking data…
View article: ACE: A Cardinality Estimator for Set-Valued Queries
ACE: A Cardinality Estimator for Set-Valued Queries Open
Cardinality estimation is a fundamental functionality in database systems. Most existing cardinality estimators focus on handling predicates over numeric or categorical data. They have largely omitted an important data type, set-valued dat…
View article: ACE: A Cardinality Estimator for Set-Valued Queries
ACE: A Cardinality Estimator for Set-Valued Queries Open
Cardinality estimation is a fundamental functionality in database systems. Most existing cardinality estimators focus on handling predicates over numeric or categorical data. They have largely omitted an important data type, set-valued dat…
View article: K Nearest Neighbor-Guided Trajectory Similarity Learning
K Nearest Neighbor-Guided Trajectory Similarity Learning Open
Trajectory similarity is fundamental to many spatio-temporal data mining applications. Recent studies propose deep learning models to approximate conventional trajectory similarity measures, exploiting their fast inference time once traine…
View article: OneDB:A Distributed Multi-Metric Data Similarity Search System
OneDB:A Distributed Multi-Metric Data Similarity Search System Open
Increasingly massive volumes of multi-modal data are being accumulated in many {real world} settings, including in health care and e-commerce. This development calls for effective general-purpose data management solutions for multi-modal d…
View article: EasyTime: Time Series Forecasting Made Easy
EasyTime: Time Series Forecasting Made Easy Open
Time series forecasting has important applications across diverse domains. EasyTime, the system we demonstrate, facilitates easy use of time-series forecasting methods by researchers and practitioners alike. First, EasyTime enables one-cli…
View article: HIGGS: HIerarchy-Guided Graph Stream Summarization
HIGGS: HIerarchy-Guided Graph Stream Summarization Open
Graph stream summarization refers to the process of processing a continuous stream of edges that form a rapidly evolving graph. The primary challenges in handling graph streams include the impracticality of fully storing the ever-growing d…
View article: iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search
iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search Open
Range-filtering approximate nearest neighbor (RFANN) search is attracting increasing attention in academia and industry. Given a set of data objects, each being a pair of a high-dimensional vector and a numeric value, an RFANN query with a…
View article: RED: Effective Trajectory Representation Learning with Comprehensive Information
RED: Effective Trajectory Representation Learning with Comprehensive Information Open
Trajectory representation learning (TRL) maps trajectories to vectors that can then be used for various downstream tasks, including trajectory similarity computation, trajectory classification, and travel-time estimation. However, existing…
View article: Grid and Road Expressions Are Complementary for Trajectory Representation Learning
Grid and Road Expressions Are Complementary for Trajectory Representation Learning Open
Trajectory representation learning (TRL) maps trajectories to vectors that can be used for many downstream tasks. Existing TRL methods use either grid trajectories, capturing movement in free space, or road trajectories, capturing movement…
View article: Fully Automated Correlated Time Series Forecasting in Minutes
Fully Automated Correlated Time Series Forecasting in Minutes Open
Societal and industrial infrastructures and systems increasingly leverage sensors that emit correlated time series. Forecasting of future values of such time series based on recorded historical values has important benefits. Automatically …
View article: Less is More: Efficient Time Series Dataset Condensation via Two-fold Modal Matching--Extended Version
Less is More: Efficient Time Series Dataset Condensation via Two-fold Modal Matching--Extended Version Open
The expanding instrumentation of processes throughout society with sensors yields a proliferation of time series data that may in turn enable important applications, e.g., related to transportation infrastructures or power grids. Machine-l…
View article: Modeling and Monitoring of Indoor Populations using Sparse Positioning Data (Extension)
Modeling and Monitoring of Indoor Populations using Sparse Positioning Data (Extension) Open
In large venues like shopping malls and airports, knowledge on the indoor populations fuels applications such as business analytics, venue management, and safety control. In this work, we provide means of modeling populations in partitions…
View article: Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis
Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis Open
Multivariate Time Series (MTS) analysis is crucial to understanding and managing complex systems, such as traffic and energy systems, and a variety of approaches to MTS forecasting have been proposed recently. However, we often observe inc…
View article: TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting
TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting Open
Time Series Forecasting (TSF) is key functionality in numerous fields, such as financial investment, weather services, and energy management. Although increasingly capable TSF methods occur, many of them require domain-specific data collec…
View article: iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search
iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search Open
Range-filtering approximate nearest neighbor (RFANN) search is attracting increasing attention in academia and industry. Given a set of data objects, each being a pair of a high-dimensional vector and a numeric value, an RFANN query with a…
View article: Efficient Cost Modeling of Space-Filling Curves
Efficient Cost Modeling of Space-Filling Curves Open
A space-filling curve (SFC) maps points in a multi-dimensional space to one-dimensional points by discretizing the multi-dimensional space into cells and imposing a linear order on the cells. This way, an SFC enables computing a one-dimens…