English
Related papers

Related papers: Sphere2Vec: Multi-Scale Representation Learning ov…

200 papers

Generating learning-friendly representations for points in space is a fundamental and long-standing problem in ML. Recently, multi-scale encoding schemes (such as Space2Vec and NeRF) were proposed to directly encode any point in 2D/3D…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Gengchen Mai , Yao Xuan , Wenyun Zuo , Yutong He , Jiaming Song , Stefano Ermon , Krzysztof Janowicz , Ni Lao

Spatial representation learning is essential for GeoAI applications such as urban analytics, enabling the encoding of shapes, locations, and spatial relationships (topological and distance-based) of geo-entities like points, polylines, and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Chen Chu , Cyrus Shahabi

Unsupervised text encoding models have recently fueled substantial progress in NLP. The key idea is to use neural networks to convert words in texts to vector space representations based on word positions in a sentence and their contexts,…

Computer Vision and Pattern Recognition · Computer Science 2020-03-03 Gengchen Mai , Krzysztof Janowicz , Bo Yan , Rui Zhu , Ling Cai , Ni Lao

Encoding geospatial objects is fundamental for geospatial artificial intelligence (GeoAI) applications, which leverage machine learning (ML) models to analyze spatial information. Common approaches transform each object into known formats,…

Machine Learning · Computer Science 2025-05-13 Maria Despoina Siampou , Jialiang Li , John Krumm , Cyrus Shahabi , Hua Lu

Learning representations of geographical space is vital for any machine learning model that integrates geolocated data, spanning application domains such as remote sensing, ecology, or epidemiology. Recent work embeds coordinates using sine…

Machine Learning · Computer Science 2024-04-16 Marc Rußwurm , Konstantin Klemmer , Esther Rolf , Robin Zbinden , Devis Tuia

Vector-mode geospatial data -- points, lines, and polygons -- must be encoded into an appropriate form in order to be used with traditional machine learning and artificial intelligence models. Encoding methods attempt to represent a given…

Machine Learning · Computer Science 2025-06-06 John Collins

Learning and recognition is a fundamental process performed in many robot operations such as mapping and localization. The majority of approaches share some common characteristics, such as attempting to extract salient features, landmarks…

Robotics · Computer Science 2017-07-21 Adam Jacobson , Walter Scheirer , Michael Milford

Urban region profiling can benefit urban analytics. Although existing studies have made great efforts to learn urban region representation from multi-source urban data, there are still three limitations: (1) Most related methods focused…

Artificial Intelligence · Computer Science 2022-02-07 Y. Luo , F. Chung , K. Chen

Geographic data is fundamentally local. Disease outbreaks cluster in population centers, ecological patterns emerge along coastlines, and economic activity concentrates within country borders. Machine learning models that encode geographic…

Machine Learning · Computer Science 2026-02-03 Arjun Rao , Ruth Crasto , Tessa Ooms , David Rolnick , Konstantin Klemmer , Marc Rußwurm

Existing single-view 3D generative models typically adopt multiview diffusion priors to reconstruct object surfaces, yet they remain prone to inter-view inconsistencies and are unable to faithfully represent complex internal structure or…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Jingdong Zhang , Weikai Chen , Yuan Liu , Jionghao Wang , Zhengming Yu , Zhuowen Shen , Bo Yang , Wenping Wang , Xin Li

Positional encoding has become the de facto standard for grounding deep neural networks on discrete point-wise positions, and it has achieved remarkable success in tasks where the input can be represented as a one-dimensional sequence.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yuhang He

Predicting the pose of objects from a single image is an important but difficult computer vision problem. Methods that predict a single point estimate do not predict the pose of objects with symmetries well and cannot represent uncertainty.…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 David M. Klee , Ondrej Biza , Robert Platt , Robin Walters

Cross-view object geo-localization enables high-precision object localization through cross-view matching, with critical applications in autonomous driving, urban management, and disaster response. However, existing methods rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Shuhan Hu , Yiru Li , Yuanyuan Li , Yingying Zhu

Scalable general-purpose representations of the built environment are crucial for geospatial artificial intelligence applications. This paper introduces S2Vec, a novel self-supervised framework for learning such geospatial embeddings. S2Vec…

Social and Information Networks · Computer Science 2026-01-08 Shushman Choudhury , Elad Aharoni , Chandrakumari Suvarna , Iveel Tsogsuren , Abdul Rahman Kreidieh , Chun-Ta Lu , Neha Arora

Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention. However, existing position encoding…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Xi Chen , Shiyang Zhou , Muqi Huang , Jiaxu Feng , Yun Xiong , Kun Zhou , Biao Yang , Yuhui Zhang , Huishuai Bao , Sijia Peng , Chuan Li , Feng Shi

Most real-world 3D measurements from depth sensors are incomplete, and to address this issue the point cloud completion task aims to predict the complete shapes of objects from partial observations. Previous works often adapt an…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Junming Zhang , Haomeng Zhang , Ram Vasudevan , Matthew Johnson-Roberson

Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Tuo Feng , Wenguan Wang , Ruijie Quan , Yi Yang

Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction methods use a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Thomas Walker , Octave Mariotti , Amir Vaxman , Hakan Bilen

A common need for artificial intelligence models in the broader geoscience is to represent and encode various types of spatial data, such as points (e.g., points of interest), polylines (e.g., trajectories), polygons (e.g., administrative…

Machine Learning · Computer Science 2022-03-14 Gengchen Mai , Krzysztof Janowicz , Yingjie Hu , Song Gao , Bo Yan , Rui Zhu , Ling Cai , Ni Lao

Detecting navigable space is the first and also a critical step for successful robot navigation. In this work, we treat the visual navigable space segmentation as a scene decomposition problem and propose a new network, NSS-VAEs (Navigable…

Robotics · Computer Science 2021-11-03 Zheng Chen , Lantao Liu
‹ Prev 1 2 3 10 Next ›