Related papers: Capturing Complex Spatial-Temporal Dependencies in…
Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…
Existing works typically treat spatial-temporal prediction as the task of learning a function $F$ to transform historical observations to future observations. We further decompose this cross-time transformation into three processes: (1)…
3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed…
The ability to predict traffic flow over time for crowded areas during rush hours is increasingly important as it can help authorities make informed decisions for congestion mitigation or scheduling of infrastructure development in an area.…
The next location recommendation is at the core of various location-based applications. Current state-of-the-art models have attempted to solve spatial sparsity with hierarchical gridding and model temporal relation with explicit time…
Accurate traffic forecasting is crucial for intelligent transportation systems, supporting effective traffic management, congestion reduction, and informed urban planning. However, traditional models often fail to adequately capture the…
First-person action recognition is a challenging task in video understanding. Because of strong ego-motion and a limited field of view, many backgrounds or noisy frames in a first-person video can distract an action recognition model during…
In this paper, we have proposed STC-GEF, a novel Spatio-Temporal Cross-platform Graph Embedding Fusion approach for the urban traffic flow prediction. We have designed a spatial embedding module based on graph convolutional networks (GCN)…
Video-based gaze estimation methods aim to capture the inherently temporal dynamics of human eye gaze from multiple image frames. However, since models must capture both spatial and temporal relationships, performance is limited by the…
Many scientific prediction problems have spatiotemporal data- and modeling-related challenges in handling complex variations in space and time using only sparse and unevenly distributed observations. This paper presents a novel deep…
Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…
Fine-grained air pollution forecasting is crucial for urban management and the development of healthy buildings. Deploying portable sensors on mobile platforms such as cars and buses offers a low-cost, easy-to-maintain, and wide-coverage…
Inter-city highway transportation is significant for citizens' modern urban life and generates heterogeneous sensory data with spatio-temporal characteristics. As a routine analysis in transportation domain, daily traffic volume estimation…
Transformers have gained attention in atmospheric time series forecasting (ATSF) for their ability to capture global spatial-temporal correlations. However, their complex architectures lead to excessive parameter counts and extended…
Urban traffic speed prediction aims to estimate the future traffic speed for improving the urban transportation services. Enormous efforts have been made on exploiting spatial correlations and temporal dependencies of traffic speed evolving…
With rapid expansion of cellular networks and the proliferation of mobile devices, cellular traffic data exhibits complex temporal dynamics and spatial correlations, posing challenges to accurate traffic prediction. Previous methods often…
Predicting individual mobility patterns is crucial across various applications. While current methods mainly focus on predicting the next location for personalized services like recommendations, they often fall short in supporting broader…
This paper develops a data-driven toolkit for traffic forecasting using high-resolution (a.k.a. event-based) traffic data. This is the raw data obtained from fixed sensors in urban roads. Time series of such raw data exhibit heavy…
Existing traffic volume estimation methods typically address either forecasting traffic on sensor-equipped roads or spatially imputing missing volumes using nearby sensors. While forecasting models generally disregard unmonitored roads by…
In the domain of large foundation models, the Segment Anything Model (SAM) has gained notable recognition for its exceptional performance in image segmentation. However, tackling the video camouflage object detection (VCOD) task presents a…