Matches in SemOpenAlex for { <https://semopenalex.org/work/W4212773097> ?p ?o ?g. }
- W4212773097 abstract "Scientific discoveries and studies about our physical world have long benefited from large-scale and planetary sensing, from weather forecasting to wildfire monitoring. However, the limited deployment of sensors in the environment due to cost or physical access constraints has lagged behind our ever-growing need for increased data coverage and higher resolution, impeding timely and precise monitoring and understanding of the environment. Therefore, we seek to extend the spatial coverage of analysis based on existing sensory data, that is, to generate data for locations where no historical data exists. This problem is fundamentally different and more challenging than the traditional spatio-temporal imputation that assumes data for any particular location are only partially missing across time. Inspired by the success of Generative Adversarial Network (GAN) in imputation, we propose a novel ESC-GAN. We observe that there are local patterns in nearby locations, as well as trends in a global manner (e.g., temperature drops as altitude increases regardless of the location). As local patterns may exhibit at different scales (from meters to kilometers), we employ a multi-branch generator to aggregate information of different granularity. More specifically, each branch in the generator contains 1) randomly masked 3D partial convolutions at different resolutions to capture the local patterns and 2) global attention modules for global similarity. Next, we adversarially train a 3D convolution-based discriminator to distinguish the generator's output from the ground truth. Extensive experiments on three geo-sensor datasets demonstrate that ESC-GAN outperforms state-of-the-art methods on extending spatial coverage and also achieves the best results on a traditional spatio-temporal imputation task." @default.
- W4212773097 created "2022-02-24" @default.
- W4212773097 creator A5039500313 @default.
- W4212773097 creator A5061783899 @default.
- W4212773097 creator A5067912458 @default.
- W4212773097 creator A5078959213 @default.
- W4212773097 creator A5088730125 @default.
- W4212773097 date "2022-02-11" @default.
- W4212773097 modified "2023-09-27" @default.
- W4212773097 title "ESC-GAN" @default.
- W4212773097 cites W1901129140 @default.
- W4212773097 cites W1975574615 @default.
- W4212773097 cites W2003938839 @default.
- W4212773097 cites W2014793248 @default.
- W4212773097 cites W2019126302 @default.
- W4212773097 cites W2031027346 @default.
- W4212773097 cites W2043607614 @default.
- W4212773097 cites W2124901782 @default.
- W4212773097 cites W2176956584 @default.
- W4212773097 cites W2194775991 @default.
- W4212773097 cites W2775387120 @default.
- W4212773097 cites W2798365772 @default.
- W4212773097 cites W2912818700 @default.
- W4212773097 cites W2963091558 @default.
- W4212773097 cites W2980537499 @default.
- W4212773097 cites W2982220924 @default.
- W4212773097 cites W2988407809 @default.
- W4212773097 cites W2997705255 @default.
- W4212773097 cites W2998048283 @default.
- W4212773097 cites W3003365835 @default.
- W4212773097 cites W3034803243 @default.
- W4212773097 cites W3080252065 @default.
- W4212773097 cites W3107634219 @default.
- W4212773097 cites W3115560852 @default.
- W4212773097 cites W3129272280 @default.
- W4212773097 doi "https://doi.org/10.1145/3488560.3498461" @default.
- W4212773097 hasPublicationYear "2022" @default.
- W4212773097 type Work @default.
- W4212773097 citedByCount "1" @default.
- W4212773097 countsByYear W42127730972022 @default.
- W4212773097 crossrefType "proceedings-article" @default.
- W4212773097 hasAuthorship W4212773097A5039500313 @default.
- W4212773097 hasAuthorship W4212773097A5061783899 @default.
- W4212773097 hasAuthorship W4212773097A5067912458 @default.
- W4212773097 hasAuthorship W4212773097A5078959213 @default.
- W4212773097 hasAuthorship W4212773097A5088730125 @default.
- W4212773097 hasBestOaLocation W42127730971 @default.
- W4212773097 hasConcept C105339364 @default.
- W4212773097 hasConcept C108583219 @default.
- W4212773097 hasConcept C111919701 @default.
- W4212773097 hasConcept C119857082 @default.
- W4212773097 hasConcept C121332964 @default.
- W4212773097 hasConcept C124101348 @default.
- W4212773097 hasConcept C146849305 @default.
- W4212773097 hasConcept C154945302 @default.
- W4212773097 hasConcept C163258240 @default.
- W4212773097 hasConcept C177774035 @default.
- W4212773097 hasConcept C2779803651 @default.
- W4212773097 hasConcept C2780992000 @default.
- W4212773097 hasConcept C2988773926 @default.
- W4212773097 hasConcept C41008148 @default.
- W4212773097 hasConcept C58041806 @default.
- W4212773097 hasConcept C62520636 @default.
- W4212773097 hasConcept C76155785 @default.
- W4212773097 hasConcept C79403827 @default.
- W4212773097 hasConcept C9357733 @default.
- W4212773097 hasConcept C94915269 @default.
- W4212773097 hasConceptScore W4212773097C105339364 @default.
- W4212773097 hasConceptScore W4212773097C108583219 @default.
- W4212773097 hasConceptScore W4212773097C111919701 @default.
- W4212773097 hasConceptScore W4212773097C119857082 @default.
- W4212773097 hasConceptScore W4212773097C121332964 @default.
- W4212773097 hasConceptScore W4212773097C124101348 @default.
- W4212773097 hasConceptScore W4212773097C146849305 @default.
- W4212773097 hasConceptScore W4212773097C154945302 @default.
- W4212773097 hasConceptScore W4212773097C163258240 @default.
- W4212773097 hasConceptScore W4212773097C177774035 @default.
- W4212773097 hasConceptScore W4212773097C2779803651 @default.
- W4212773097 hasConceptScore W4212773097C2780992000 @default.
- W4212773097 hasConceptScore W4212773097C2988773926 @default.
- W4212773097 hasConceptScore W4212773097C41008148 @default.
- W4212773097 hasConceptScore W4212773097C58041806 @default.
- W4212773097 hasConceptScore W4212773097C62520636 @default.
- W4212773097 hasConceptScore W4212773097C76155785 @default.
- W4212773097 hasConceptScore W4212773097C79403827 @default.
- W4212773097 hasConceptScore W4212773097C9357733 @default.
- W4212773097 hasConceptScore W4212773097C94915269 @default.
- W4212773097 hasFunder F4320306087 @default.
- W4212773097 hasLocation W42127730971 @default.
- W4212773097 hasOpenAccess W4212773097 @default.
- W4212773097 hasPrimaryLocation W42127730971 @default.
- W4212773097 hasRelatedWork W2583180462 @default.
- W4212773097 hasRelatedWork W2901581166 @default.
- W4212773097 hasRelatedWork W2910435382 @default.
- W4212773097 hasRelatedWork W2944269547 @default.
- W4212773097 hasRelatedWork W2975432854 @default.
- W4212773097 hasRelatedWork W3105974085 @default.
- W4212773097 hasRelatedWork W3162968855 @default.
- W4212773097 hasRelatedWork W3197610371 @default.
- W4212773097 hasRelatedWork W4212773097 @default.