Related papers: Volume-Based Space-Time Cube for Large-Scale Conti…
Video inpainting aims to fill the given spatiotemporal holes with realistic appearance but is still a challenging task even with prosperous deep learning approaches. Recent works introduce the promising Transformer architecture into deep…
Longitudinal analysis of sequential radiological images is hampered by a fundamental data challenge: how to effectively model a sequence of high-resolution images captured at irregular time intervals. This data structure contains…
Using functional magnetic resonance imaging (fMRI) and deep learning to explore functional brain networks (FBNs) has attracted many researchers. However, most of these studies are still based on the temporal correlation between the sources…
Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly,…
This paper reports on ongoing research investigating more expressive approaches to spatial-temporal trajectory clustering. Spatial-temporal data is increasingly becoming universal as a result of widespread use of GPS and mobile devices,…
We propose and study a novel cross-reality environment that seamlessly integrates a monoscopic 2D surface (an interactive screen with touch and pen input) with a stereoscopic 3D space (an augmented reality HMD) to jointly host spatial data…
While Large Language Models (LLMs) dominate tasks like natural language processing and computer vision, harnessing their power for spatial-temporal forecasting remains challenging. The disparity between sequential text and complex…
Today, huge amounts of data are being collected with spatial and temporal components from sources such as meteorological, satellite imagery etc. Efficient visualisation as well as discovery of useful knowledge from these datasets is…
Camera-based 3D Semantic Scene Completion (SSC) is a critical task for autonomous driving and robotic scene understanding. It aims to infer a complete 3D volumetric representation of both semantics and geometry from a single image. Existing…
Spatial and temporal interactions are central and fundamental in many activities in our world. A common problem faced when visualizing this type of data is how to provide an overview that helps users navigate efficiently. Traditional…
The growth of computational astrophysics and complexity of multidimensional datasets evidences the need for new versatile visualization tools for both analysis and presentation of the data. In this work we show how to use the open source…
Accurate spatiotemporal traffic forecasting is a critical prerequisite for proactive resource management in dense urban mobile networks. While large language models have shown promise in time series analysis, they inherently struggle to…
Climate science produces a wealth of complex, high-dimensional, multivariate data from observations and numerical models. These data are critical for understanding climate changes and their socioeconomic impacts. Climate scientists are…
This paper presents a novel method to involve both spatial and temporal features for semantic video segmentation. Current work on convolutional neural networks(CNNs) has shown that CNNs provide advanced spatial features supporting a very…
Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with token count. To address this, we propose a training-free…
The novel STEVE (i.e., Space-Time-Enclosing Volume Extraction) algorithm is described here for the very first time. It generates iso-valued hypersurfaces that may be implicitly contained in four-dimensional (4D) data sets, such as temporal…
In spatially located, large scale systems, time and space dynamics interact and drives the behaviour. Examples of such systems can be found in many smart city applications and Cyber-Physical Systems. In this paper we present the Signal…
Time-series representation learning is a fundamental task for time-series analysis. While significant progress has been made to achieve accurate representations for downstream applications, the learned representations often lack…
In this paper, we present a unified, end-to-end trainable spatiotemporal CNN model for VOS, which consists of two branches, i.e., the temporal coherence branch and the spatial segmentation branch. Specifically, the temporal coherence branch…
Recent advancements in Earth system science have been marked by the exponential increase in the availability of diverse, multivariate datasets characterised by moderate to high spatio-temporal resolutions. Earth System Data Cubes (ESDCs)…