Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387561432> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4387561432 abstract "Learning feature 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 mostly embeds coordinates using sine and cosine projections based on Double Fourier Sphere (DFS) features -- these embeddings assume a rectangular data domain even on global data, which can lead to artifacts, especially at the poles. At the same time, relatively little attention has been paid to the exact design of the neural network architectures these functional embeddings are combined with. This work proposes a novel location encoder for globally distributed geographic data that combines spherical harmonic basis functions, natively defined on spherical surfaces, with sinusoidal representation networks (SirenNets) that can be interpreted as learned Double Fourier Sphere embedding. We systematically evaluate the cross-product of positional embeddings and neural network architectures across various classification and regression benchmarks and synthetic evaluation datasets. In contrast to previous approaches that require the combination of both positional encoding and neural networks to learn meaningful representations, we show that both spherical harmonics and sinusoidal representation networks are competitive on their own but set state-of-the-art performances across tasks when combined. We provide source code at www.github.com/marccoru/locationencoder" @default.
- W4387561432 created "2023-10-12" @default.
- W4387561432 creator A5005192117 @default.
- W4387561432 creator A5012237329 @default.
- W4387561432 creator A5035995921 @default.
- W4387561432 creator A5041276152 @default.
- W4387561432 creator A5047182302 @default.
- W4387561432 date "2023-10-10" @default.
- W4387561432 modified "2023-10-13" @default.
- W4387561432 title "Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks" @default.
- W4387561432 doi "https://doi.org/10.48550/arxiv.2310.06743" @default.
- W4387561432 hasPublicationYear "2023" @default.
- W4387561432 type Work @default.
- W4387561432 citedByCount "0" @default.
- W4387561432 crossrefType "posted-content" @default.
- W4387561432 hasAuthorship W4387561432A5005192117 @default.
- W4387561432 hasAuthorship W4387561432A5012237329 @default.
- W4387561432 hasAuthorship W4387561432A5035995921 @default.
- W4387561432 hasAuthorship W4387561432A5041276152 @default.
- W4387561432 hasAuthorship W4387561432A5047182302 @default.
- W4387561432 hasBestOaLocation W43875614321 @default.
- W4387561432 hasConcept C101738243 @default.
- W4387561432 hasConcept C102519508 @default.
- W4387561432 hasConcept C11413529 @default.
- W4387561432 hasConcept C115961682 @default.
- W4387561432 hasConcept C125411270 @default.
- W4387561432 hasConcept C126990412 @default.
- W4387561432 hasConcept C134306372 @default.
- W4387561432 hasConcept C153180895 @default.
- W4387561432 hasConcept C154945302 @default.
- W4387561432 hasConcept C17744445 @default.
- W4387561432 hasConcept C178009071 @default.
- W4387561432 hasConcept C186661526 @default.
- W4387561432 hasConcept C199539241 @default.
- W4387561432 hasConcept C2221639 @default.
- W4387561432 hasConcept C2524010 @default.
- W4387561432 hasConcept C2776359362 @default.
- W4387561432 hasConcept C33923547 @default.
- W4387561432 hasConcept C3768446 @default.
- W4387561432 hasConcept C41008148 @default.
- W4387561432 hasConcept C41608201 @default.
- W4387561432 hasConcept C50644808 @default.
- W4387561432 hasConcept C59404180 @default.
- W4387561432 hasConcept C80444323 @default.
- W4387561432 hasConcept C94625758 @default.
- W4387561432 hasConceptScore W4387561432C101738243 @default.
- W4387561432 hasConceptScore W4387561432C102519508 @default.
- W4387561432 hasConceptScore W4387561432C11413529 @default.
- W4387561432 hasConceptScore W4387561432C115961682 @default.
- W4387561432 hasConceptScore W4387561432C125411270 @default.
- W4387561432 hasConceptScore W4387561432C126990412 @default.
- W4387561432 hasConceptScore W4387561432C134306372 @default.
- W4387561432 hasConceptScore W4387561432C153180895 @default.
- W4387561432 hasConceptScore W4387561432C154945302 @default.
- W4387561432 hasConceptScore W4387561432C17744445 @default.
- W4387561432 hasConceptScore W4387561432C178009071 @default.
- W4387561432 hasConceptScore W4387561432C186661526 @default.
- W4387561432 hasConceptScore W4387561432C199539241 @default.
- W4387561432 hasConceptScore W4387561432C2221639 @default.
- W4387561432 hasConceptScore W4387561432C2524010 @default.
- W4387561432 hasConceptScore W4387561432C2776359362 @default.
- W4387561432 hasConceptScore W4387561432C33923547 @default.
- W4387561432 hasConceptScore W4387561432C3768446 @default.
- W4387561432 hasConceptScore W4387561432C41008148 @default.
- W4387561432 hasConceptScore W4387561432C41608201 @default.
- W4387561432 hasConceptScore W4387561432C50644808 @default.
- W4387561432 hasConceptScore W4387561432C59404180 @default.
- W4387561432 hasConceptScore W4387561432C80444323 @default.
- W4387561432 hasConceptScore W4387561432C94625758 @default.
- W4387561432 hasLocation W43875614321 @default.
- W4387561432 hasOpenAccess W4387561432 @default.
- W4387561432 hasPrimaryLocation W43875614321 @default.
- W4387561432 hasRelatedWork W1511441395 @default.
- W4387561432 hasRelatedWork W1775321609 @default.
- W4387561432 hasRelatedWork W2028663913 @default.
- W4387561432 hasRelatedWork W2063166054 @default.
- W4387561432 hasRelatedWork W2358475213 @default.
- W4387561432 hasRelatedWork W2588864086 @default.
- W4387561432 hasRelatedWork W3011035056 @default.
- W4387561432 hasRelatedWork W3142213391 @default.
- W4387561432 hasRelatedWork W4316092752 @default.
- W4387561432 hasRelatedWork W4385749744 @default.
- W4387561432 isParatext "false" @default.
- W4387561432 isRetracted "false" @default.
- W4387561432 workType "article" @default.