Combining Contrast Invariant L1 Data Fidelities with Nonlinear Spectral Image Decomposition [PDF]
, 2017 This paper focuses on multi-scale approaches for variational methods and corresponding gradient flows. Recently, for convex regularization functionals such as total variation, new theory and algorithms for nonlinear eigenvalue problems via nonlinear ...
A Chambolle +22 more
core +3 more sources
A semantic-based platform for the digital analysis of architectural heritage [PDF]
, 2011 This essay focuses on the fields of architectural documentation and digital representation. We present a research paper concerning the development of an information system at the scale of architecture, taking into account the relationships that can be ...
BUSAYARAT, Chawee +4 more
core +5 more sources
Edge detection with multi-scale representation and refined Network
IET Conference Proceedings, 2022 Edge detection is a representation of boundaries between objects and regions in an image. Due to the variations of types, scales, intensities as well as background, the detection of these boundaries represents a challenge for different computer vision algorithms.
Elharrouss, Omar +3 more
openaire +2 more sources
Multi-scale object detection by bottom-up feature pyramid network
The Journal of Engineering, 2019 The deep neural networks has been developed fast and shown great successes in many significant fields, such as smart surveillance, self-driving and face recognition.
Zhao Boya +3 more
doaj +1 more source
Multi-scale Representation of DEM Based on Fractional Contourlet Transform [PDF]
Jisuanji gongcheng, 2018 Most of the existing Digital Elevation Model(DEM) multi-resolution representation method are redundant transformation.The redundancy increases sharply with the increase of the scale of the transformation,so it cannot effectively express the multi-scale ...
WANG Haijiang,YAO Fuqi,LI Lihong,MA Yongqiang,YANG Qinke,WANG Jingpu
doaj +1 more source
Selective Multi-Scale Feature Learning by Discriminative Local Representation
IEEE Access, 2019 In the computer vision community, the general trend has been to capture and select discriminative features in order to yield significantly better performance.
Chengji Xu, Xiaofeng Wang, Yadong Yang
doaj +1 more source
From PIace2Vec to Multi-Scale Built-Environment Representation [PDF]
Proceedings of the 4th ACM SIGSPATIAL Workshop on Location-Based Recommendations, Geosocial Networks, and Geoadvertising, 2020 Built environments like cities, roads, communities are rich sources of urban data. Many downstream applications require comprehensive analysis like geographic information retrieval, recommender systems, geographic knowledge graphs, and in general, understanding urban spaces [28]. Points of Interests (POI), as one of the most researched aspects of urban
Zhangyu Wang, Vahid Moosavi
openaire +1 more source
Multi-Modal Image Fusion via Sparse Representation and Multi-Scale Anisotropic Guided Measure
IEEE Access, 2020 The multi-modal image fusion plays an important role in various fields. In this paper, a novel multi-modal image fusion method based on robust principal component analysis (RPCA) is proposed, which consists of low-rank components fusion and sparse ...
Shuai Zhang +5 more
doaj +1 more source
Decentralized Control of Partially Observable Markov Decision Processes using Belief Space Macro-actions [PDF]
, 2015 The focus of this paper is on solving multi-robot planning problems in continuous spaces with partial observability. Decentralized partially observable Markov decision processes (Dec-POMDPs) are general models for multi-robot coordination problems, but ...
Agha-mohammadi, Ali-akbar +3 more
core +4 more sources
A Multi-Scale Virtual Terrain for Hierarchically Structured Non-Location Data
ISPRS International Journal of Geo-Information, 2021 Metaphor are commonly used rhetorical devices in linguistics. Among the various types, spatial metaphors are relatively common because of their intuitive and sensible nature.
Rui Xin +5 more
doaj +1 more source