Related papers: ContextFlow: Context-Aware Flow Matching For Traje…
Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…
Traffic prediction is a fundamental task in many real applications, which aims to predict the future traffic volume in any region of a city. In essence, traffic volume in a region is the aggregation of traffic flows from/to the region.…
Understanding cellular trajectories via time-resolved single-cell transcriptomics is vital for studying development, regeneration, and disease. A key challenge is inferring continuous trajectories from discrete snapshots. Biological…
AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples include retrieval-augmented generation, agent memory layers, and multi-agent orchestration.…
Contextual information is vital for accurate trajectory prediction. For instance, the intricate flying behavior of migratory birds hinges on their analysis of environmental cues such as wind direction and air pressure. However, the diverse…
Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in the context of environmental perception for vehicles due to…
In the Internet of Things (IoT) environment, continuous interaction among a large number of devices generates complex and dynamic network traffic, which poses significant challenges to rule-based detection approaches. Machine learning…
Conditional Normalizing Flows (CNFs) are flexible generative models capable of representing complicated distributions with high dimensionality and large interdimensional correlations, making them appealing for structured output learning.…
Human motion and behaviour in crowded spaces is influenced by several factors, such as the dynamics of other moving agents in the scene, as well as the static elements that might be perceived as points of attraction or obstacles. In this…
Flow matching (FM) is increasingly used in scientific domains for time series generation and forecasting, where data often arise from underlying dynamical systems. However, it is not well-understood whether it learns transferable dynamical…
Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between…
A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…
Prior flow matching methods in robotics have primarily learned velocity fields to morph one distribution of trajectories into another. In this work, we extend flow matching to capture second-order trajectory dynamics, incorporating…
Occlusions between consecutive frames have long posed a significant challenge in optical flow estimation. The inherent ambiguity introduced by occlusions directly violates the brightness constancy constraint and considerably hinders…
Exposing latent knowledge in geospatial trajectories has the potential to provide a better understanding of the movements of individuals and groups. Motivated by such a desire, this work presents the context tree, a new hierarchical data…
Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling multiple types of…
Forecasting conditional stochastic nonlinear dynamical systems is a fundamental challenge repeatedly encountered across the biological and physical sciences. While flow-based models can impressively predict the temporal evolution of…
Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to improve the accuracy…
The trajectory patterns of a moving object in a spatio-temporal domain offers varied information in terms of the management of the data generated from the movement. A trajectory data warehouse is a data repository for the data and…
Optical flow is a classical task that is important to the vision community. Classical optical flow estimation uses two frames as input, whilst some recent methods consider multiple frames to explicitly model long-range information. The…