Distributional and spatial-temporal robust representation learning for transportation activity recognition
Transportation activity recognition (TAR) provides valuable support for intelligent
transportation applications, such as urban transportation planning, driving behavior …
transportation applications, such as urban transportation planning, driving behavior …
Quantifying the uncertainty of mobility flow predictions using Gaussian processes
A Steentoft, BS Lee, M Schläpfer - Transportation, 2023 - Springer
The ability to understand and predict the flows of people in cities is crucial for the planning of
transportation systems and other urban infrastructures. Deep-learning approaches are …
transportation systems and other urban infrastructures. Deep-learning approaches are …
SRNDiff: Short-term Rainfall Nowcasting with Condition Diffusion Model
X Ling, C Li, F Qin, P Yang, Y Huang - arXiv preprint arXiv:2402.13737, 2024 - arxiv.org
Diffusion models are widely used in image generation because they can generate high-
quality and realistic samples. This is in contrast to generative adversarial networks (GANs) …
quality and realistic samples. This is in contrast to generative adversarial networks (GANs) …
RecMoDiffuse: Recurrent Flow Diffusion for Human Motion Generation
Human motion generation has paramount importance in computer animation. It is a
challenging generative temporal modelling task due to the vast possibilities of human …
challenging generative temporal modelling task due to the vast possibilities of human …
Understanding evolving user choices: a neural network analysis of TAXI and ride-hailing services in Barcelona
Urban mobility stands as a fundamental element worthy of consideration by both society and
its leaders. Often, decisions in this realm are made by governing figures without duly …
its leaders. Often, decisions in this realm are made by governing figures without duly …
Entropy-Informed Weighting Channel Normalizing Flow
Normalizing Flows (NFs) have gained popularity among deep generative models due to
their ability to provide exact likelihood estimation and efficient sampling. However, a crucial …
their ability to provide exact likelihood estimation and efficient sampling. However, a crucial …
TU2Net-GAN: A temporal precipitation nowcasting model with multiple decoding modules
XD Ling, CR Li, P Yang, Y Huang, F Qin - Pattern Recognition Letters, 2024 - Elsevier
With the Earth's temperature rising and abnormal weather events becoming frequent, the
mechanisms of precipitation formation have become increasingly complex, leading to more …
mechanisms of precipitation formation have become increasingly complex, leading to more …
FRMDN: Flow-based Recurrent Mixture Density Network
The class of recurrent mixture density networks is an important class of probabilistic models
used extensively in sequence modeling and sequence-to-sequence mapping applications …
used extensively in sequence modeling and sequence-to-sequence mapping applications …
FRMDN: Flow-based Recurrent Mixture Density Network
The class of recurrent mixture density networks is an important class of probabilistic models
used extensively in sequence modeling and sequence-to-sequence mapping applications …
used extensively in sequence modeling and sequence-to-sequence mapping applications …