中文
相关论文

相关论文: Unsupervised dynamic modeling of medical image tra…

200 篇论文

Longitudinal data are important in numerous fields, such as healthcare, sociology and seismology, but real-world datasets present notable challenges for practitioners because they can be high-dimensional, contain structured missingness…

机器学习 · 计算机科学 2024-07-01 Maksim Sinelnikov , Manuel Haussmann , Harri Lähdesmäki

Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…

计算机视觉与模式识别 · 计算机科学 2018-09-12 Xiaolin Song , Cuiling Lan , Wenjun Zeng , Junliang Xing , Jingyu Yang , Xiaoyan Sun

Dynamic Mode Decomposition (DMD) is a data-driven technique to identify a low dimensional linear time invariant dynamics underlying high-dimensional data. For systems in which such underlying low-dimensional dynamics is time-varying, a…

信号处理 · 电气工程与系统科学 2020-04-09 Mustaffa Alfatlawi , Vaibhav Srivastava

Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of the environment for motion prediction. This modularity…

机器学习 · 计算机科学 2021-01-05 Todor Davchev , Michael Burke , Subramanian Ramamoorthy

Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for…

计算机视觉与模式识别 · 计算机科学 2023-12-15 Zhouqiang Jiang , Bowen Wang , Tong Xiang , Zhaofeng Niu , Hong Tang , Guangshun Li , Liangzhi Li

We consider the problem of integrating non-imaging information into segmentation networks to improve performance. Conditioning layers such as FiLM provide the means to selectively amplify or suppress the contribution of different feature…

计算机视觉与模式识别 · 计算机科学 2020-08-25 Grzegorz Jacenków , Alison Q. O'Neil , Brian Mohr , Sotirios A. Tsaftaris

Ambiguity is inevitable in medical images, which often results in different image interpretations (e.g. object boundaries or segmentation maps) from different human experts. Thus, a model that learns the ambiguity and outputs a probability…

计算机视觉与模式识别 · 计算机科学 2020-10-22 Linchen Qian , Jiasong Chen , Timur Urakov , Weiyong Gu , Liang Liang

Medical image segmentation is crucial for clinical diagnosis and treatment planning. Traditional methods typically produce a single segmentation mask, failing to capture inherent uncertainty. Recent generative models enable the creation of…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Huynh Trinh Ngoc , Toan Nguyen Hai , Ba Luong Son , Long Tran Quoc

We present a dynamic subspace approach for efficiently approximating large-scale systems by learning time-continuous trajectories on the Grassmannian manifold. By parameterizing a low-dimensional basis as a geodesic path, the method allows…

数值分析 · 数学 2026-05-26 Jack DeChant , Rudy Geelen , Shane A. McQuarrie , Johann Guilleminot

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…

计算机视觉与模式识别 · 计算机科学 2020-03-03 Matthias Minderer , Chen Sun , Ruben Villegas , Forrester Cole , Kevin Murphy , Honglak Lee

Large-scale dynamic inverse problems are often ill-posed due to model complexity and the high dimensionality of the unknown parameters. Regularization is commonly employed to mitigate ill-posedness by incorporating prior information and…

数值分析 · 数学 2026-01-21 Aryeh Keating , Mirjeta Pasha

Latent Video Diffusion Models (LVDMs) rely on Variational Autoencoders (VAEs) to compress videos into compact latent representations. For continuous Variational Autoencoders (VAEs), achieving higher compression rates is desirable; yet, the…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Yubo Dong , Linchao Zhu

Wild animals are commonly fitted with trackers that record their position through time, and statistical models for tracking data broadly fall into two categories: models focused on small-scale movement decisions, and models for large-scale…

应用统计 · 统计学 2025-10-07 Théo Michelot , Ephraim M. Hanks

Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of…

Modelling longitudinal data is an important yet challenging task. These datasets can be high-dimensional, contain non-linear effects and time-varying covariates. Gaussian process (GP) prior-based variational autoencoders (VAEs) have emerged…

机器学习 · 计算机科学 2024-09-18 Priscilla Ong , Manuel Haußmann , Otto Lönnroth , Harri Lähdesmäki

Rapid developments in advanced sensing and imaging have significantly enhanced information visibility, opening opportunities for predictive modeling of complex dynamic systems. However, sensing signals acquired from such complex systems are…

机器学习 · 统计学 2025-05-02 Xizhuo Zhang , Bing Yao

We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds. We redevelop the VAE framework…

机器学习 · 计算机科学 2026-01-21 Andrew Gracyk

Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion models with bidirectional generation, which limits temporal…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Qing Yu , Akihisa Watanabe , Kent Fujiwara

Variational Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora and other latent video diffusion generation models. While most of existing video VAEs inflate a…

计算机视觉与模式识别 · 计算机科学 2024-11-12 Pingyu Wu , Kai Zhu , Yu Liu , Liming Zhao , Wei Zhai , Yang Cao , Zheng-Jun Zha

Analysis of heterogeneous patterns in complex spatio-temporal data finds usage across various domains in applied science and engineering, including training autonomous vehicles to navigate in complex traffic scenarios. Motivated by…

机器学习 · 统计学 2021-02-16 Sunrit Chakraborty , Aritra Guha , Rayleigh Lei , XuanLong Nguyen