中文
相关论文

相关论文: NARA: Anchor-Conditioned Relation-Aware Contextual…

200 篇论文

Recent healthcare foundation models have achieved strong predictive performance through large scale self supervised learning, yet their latent representations frequently entangle physiologic severity, intervention intensity, observational…

机器学习 · 计算机科学 2026-05-19 Yuanyun Zhang , Shi Li

Recent advances in remote sensing have led to an increase in the number of available foundation models; each trained on different modalities, datasets, and objectives, yet capturing only part of the vast geospatial knowledge landscape.…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Joelle Hanna , Damian Falk , Stella X. Yu , Damian Borth

We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch,…

计算机视觉与模式识别 · 计算机科学 2019-01-31 Zuxuan Wu , Larry S. Davis , Leonid Sigal

Contrastive learning methods have significantly narrowed the gap between supervised and unsupervised learning on computer vision tasks. In this paper, we explore their application to geo-located datasets, e.g. remote sensing, where…

计算机视觉与模式识别 · 计算机科学 2022-03-09 Kumar Ayush , Burak Uzkent , Chenlin Meng , Kumar Tanmay , Marshall Burke , David Lobell , Stefano Ermon

In human reading and communication, individuals tend to engage in geospatial reasoning, which involves recognizing geographic entities and making informed inferences about their interrelationships. To mimic such cognitive process, current…

计算与语言 · 计算机科学 2024-08-22 Yibo Yan , Joey Lee

When modeling geo-spatial data, it is critical to capture spatial correlations for achieving high accuracy. Spatial Auto-Regression (SAR) is a common tool used to model such data, where the spatial contiguity matrix (W) encodes the spatial…

计算机视觉与模式识别 · 计算机科学 2016-10-18 Archith J. Bency , Swati Rallapalli , Raghu K. Ganti , Mudhakar Srivatsa , B. S. Manjunath

Entity alignment (EA) is the task to discover entities referring to the same real-world object from different knowledge graphs (KGs), which is the most crucial step in integrating multi-source KGs. The majority of the existing…

计算与语言 · 计算机科学 2021-03-02 Renbo Zhu , Meng Ma , Ping Wang

Large-scale pretraining on Earth observation imagery has yielded powerful representations of the natural and built environment. However, most existing geospatial foundation models do not directly model the structured socioeconomic…

机器学习 · 计算机科学 2026-05-15 Yuhao Liu , Sadeer Al-Kindi , Ashok Veeraraghavan , Guha Balakrishnan

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

机器学习 · 计算机科学 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

Biological network alignment (NA) aims to find a node mapping between species' molecular networks that uncovers similar network regions, thus allowing for transfer of functional knowledge between the aligned nodes. However, current NA…

分子网络 · 定量生物学 2020-09-09 Shawn Gu , Tijana Milenkovic

Graph neural networks (GNNs) provide a powerful and scalable solution for modeling continuous spatial data. However, they often rely on Euclidean distances to construct the input graphs. This assumption can be improbable in many real-world…

机器学习 · 计算机科学 2023-02-20 Konstantin Klemmer , Nathan Safir , Daniel B. Neill

Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method…

图像与视频处理 · 电气工程与系统科学 2022-07-08 Li Sun , Ke Yu , Kayhan Batmanghelich

Named geographic entities (geo-entities for short) are the building blocks of many geographic datasets. Characterizing geo-entities is integral to various application domains, such as geo-intelligence and map comprehension, while a key…

计算与语言 · 计算机科学 2022-10-25 Zekun Li , Jina Kim , Yao-Yi Chiang , Muhao Chen

The graph-based variational autoencoder represents an architecture that can handle the uncertainty of different geological scenarios, such as depositional or structural, through the concept of a lowerdimensional latent space. The main…

应用统计 · 统计学 2025-07-15 Gleb Shishaev , Vasily Demyanov , Daniel Arnold

Robust generalization under climate change remains a major challenge for machine learning applications in climate science. Most existing approaches struggle to extrapolate beyond the climate they were trained on, leading to a strong…

大气与海洋物理 · 物理学 2025-09-03 Shuchang Liu , Paul A. O'Gorman

Precipitation nowcasting (up to a few hours) remains a challenge due to the highly complex local interactions that need to be captured accurately. Convolutional Neural Networks rely on convolutional kernels convolving with grid data and the…

机器学习 · 计算机科学 2023-09-13 Shan Zhao , Sudipan Saha , Zhitong Xiong , Niklas Boers , Xiao Xiang Zhu

Efficient target localization and autonomous navigation in complex environments are fundamental to real-world embodied applications. While recent advances in multimodal foundation models have enabled zero-shot object goal navigation,…

机器人学 · 计算机科学 2026-04-02 Ming-Ming Yu , Yi Chen , Börje F. Karlsson , Wenjun Wu

Transformer-based general visual geometry frameworks have shown promising performance in camera pose estimation and 3D scene understanding. Recent advancements in Visual Geometry Grounded Transformer (VGGT) models have shown great promise…

计算机视觉与模式识别 · 计算机科学 2026-04-03 Yangfan Xu , Lilian Zhang , Xiaofeng He , Pengdong Wu , Wenqi Wu , Jun Mao

Representation learning on heterogeneous graphs aims to obtain meaningful node representations to facilitate various downstream tasks, such as node classification and link prediction. Existing heterogeneous graph learning methods are…

机器学习 · 计算机科学 2022-04-19 Le Yu , Leilei Sun , Bowen Du , Chuanren Liu , Weifeng Lv , Hui Xiong

Spatial-temporal graph representations play a crucial role in urban sensing applications, including traffic analysis, human mobility behavior modeling, and citywide crime prediction. However, a key challenge lies in the noisy and sparse…

机器学习 · 计算机科学 2025-08-15 Qianru Zhang , Xinyi Gao , Haixin Wang , Dong Huang , Siu-Ming Yiu , Hongzhi Yin
‹ 上一页 1 2 3 10 下一页 ›