Related papers: SpoT-Mamba: Learning Long-Range Dependency on Spat…
Traffic flow prediction, a critical aspect of intelligent transportation systems, has been increasingly popular in the field of artificial intelligence, driven by the availability of extensive traffic data. The current challenges of traffic…
Spatial-Temporal Graph (STG) data is characterized as dynamic, heterogenous, and non-stationary, leading to the continuous challenge of spatial-temporal graph learning. In the past few years, various GNN-based methods have been proposed to…
Accurate traffic prediction plays a vital role in intelligent transportation systems by enabling efficient routing, congestion mitigation, and proactive traffic control. However, forecasting is challenging due to the combined effects of…
Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. Bottlenecked by the quadratic computational cost, attention mechanisms fail to scale in large graphs. Recent improvements in…
Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D…
Traffic flow estimation (TFE) is crucial for urban intelligent traffic systems. While traditional on-road detectors are hindered by limited coverage and high costs, cloud computing and data mining of vehicular network data, such as driving…
Gait disorder recognition plays a crucial role in the early diagnosis and monitoring of movement disorders. Existing approaches, including spatio-temporal graph convolutional networks (ST-GCNs), often face high memory demands and struggle…
Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise in capturing long-range dependencies in temporal graph data,…
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…
Traffic forecasting requires modeling complex temporal dynamics and long-range spatial dependencies over large sensor networks. Existing methods typically face a trade-off between expressiveness and efficiency: Transformer-based models…
Accurate and timely traffic flow forecasting is crucial for intelligent transportation systems. This paper presents a novel deep learning model, the Spatial-Temporal Unified Graph Attention Network (STGAtt). By leveraging a unified graph…
Time series forecasting has made significant advances, including with Transformer-based models. The attention mechanism in Transformer effectively captures temporal dependencies by attending to all past inputs simultaneously. However, its…
Learning useful representations for continuous-time dynamic graphs (CTDGs) is challenging, due to the concurrent need to span long node interaction histories and grasp nuanced temporal details. In particular, two problems emerge: (1)…
Recently, spatio-temporal time-series prediction has developed rapidly, yet existing deep learning methods struggle with learning complex long-term spatio-temporal dependencies efficiently. The long-term spatio-temporal dependency learning…
We propose a novel spatial-temporal graph Mamba (STG-Mamba) for the music-guided dance video synthesis task, i.e., to translate the input music to a dance video. STG-Mamba consists of two translation mappings: music-to-skeleton translation…
Visual tracking aims to automatically estimate the state of a target object in a video sequence, which is challenging especially in dynamic scenarios. Thus, numerous methods are proposed to introduce temporal cues to enhance tracking…
We propose ss-Mamba, a novel foundation model that enhances time series forecasting by integrating semantic-aware embeddings and adaptive spline-based temporal encoding within a selective state-space modeling framework. Building upon the…
Human trajectory forecasting is crucial for safe navigation in crowded environments, requiring models that balance accuracy with computational efficiency. Efficiently modeling social interactions is key to performance in dense crowds. Yet,…
In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state…
Video anomaly detection (VAD) has been extensively researched due to its potential for intelligent video systems. However, most existing methods based on CNNs and transformers still suffer from substantial computational burdens and have…