Related papers: M-STAR: Multi-Scale Spatiotemporal Autoregression …
In this work we investigate approaches to reconstruct generator models from measurements available at the generator terminal bus using machine learning (ML) techniques. The goal is to develop an emulator which is trained online and is…
Since 2023, Vector Quantization (VQ)-based discrete generation methods have rapidly dominated human motion generation, primarily surpassing diffusion-based continuous generation methods in standard performance metrics. However, VQ-based…
Lane segment topology reasoning constructs a comprehensive road network by capturing the topological relationships between lane segments and their semantic types. This enables end-to-end autonomous driving systems to perform road-dependent…
The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio-temporal…
Multivariate time series forecasting enables the prediction of future states by leveraging historical data, thereby facilitating decision-making processes. Each data node in a multivariate time series encompasses a sequence of multiple…
The ability to predict the future trajectories of traffic participants is crucial for the safe and efficient operation of autonomous vehicles. In this paper, a diffusion-based generative model for multi-agent trajectory prediction is…
Data-driven and controllable human motion synthesis and prediction are active research areas with various applications in interactive media and social robotics. Challenges remain in these fields for generating diverse motions given past…
Due to the complex and changing interactions in dynamic scenarios, motion forecasting is a challenging problem in autonomous driving. Most existing works exploit static road graphs to characterize scenarios and are limited in modeling…
Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we…
This paper explores potential improvements to the Spatial-Temporal Matching algorithm for aligning the GPS trajectories to road networks. While this algorithm is effective, it presents some limitations in computational efficiency and the…
Mobile app usage behavior reveals human patterns and is crucial for stakeholders, but data collection is costly and raises privacy issues. Data synthesis can address this by generating artificial datasets that mirror real-world data. In…
Road user trajectory prediction in dynamic environments is a challenging but crucial task for various applications, such as autonomous driving. One of the main challenges in this domain is the multimodal nature of future trajectories…
Essential to visual generation is efficient modeling of visual data priors. Conventional next-token prediction methods define the process as learning the conditional probability distribution of successive tokens. Recently, next-scale…
Forecasting high-resolution land subsidence is a critical yet challenging task due to its complex, non-linear dynamics. While standard architectures like ConvLSTM often fail to model long-range dependencies, we argue that a more fundamental…
Autoregressive models are a class of generative model that probabilistically predict the next output of a sequence based on previous inputs. The autoregressive sequence is by definition one-dimensional (1D), which is natural for language…
Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively…
Generative modeling has drawn much attention in creative and scientific data generation tasks. Score-based Diffusion Models, a type of generative model that iteratively learns to denoise data, have shown state-of-the-art results on tasks…
In computer animation, game design, and human-computer interaction, synthesizing human motion that aligns with user intent remains a significant challenge. Existing methods have notable limitations: textual approaches offer high-level…
Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary technical approaches in visual generation: diffusion models…
Reliable traffic flow prediction is crucial to creating intelligent transportation systems. Many big-data-based prediction approaches have been developed but they do not reflect complicated dynamic interactions between roads considering…