Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313854477> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4313854477 abstract "Obtaining realistic fire images using deep learning models and recent versions of Generative adversarial networks (GAN) has been proven to be a difficult task due to the unnatural appearance of the generated results. This paper provides a novel approach based on StarGANv2 to generate fire kernels from any input provided as a reference. In addition, a deep learning-based image blending technique performs the migration of the fire kernels to the target scenes. By using any input as a reference, the generated fire image could be controlled to accommodate different environmental factors, resulting in a diverse but equally pseudo-real synthetic dataset. The proposed method generates images that achieve better FID and LPIPS values than StarGANv2 for both a public dataset (AI Hub) and a privately-owned dataset (Visionin). In addition, YOLOv4 is used as a fire detection model to evaluate the synthetic data on improving the performance of the detected network. Compared to the model trained on the real data, the model trained on the combined dataset outperforms 2%~14% higher." @default.
- W4313854477 created "2023-01-10" @default.
- W4313854477 creator A5011602242 @default.
- W4313854477 creator A5037300814 @default.
- W4313854477 date "2022-11-27" @default.
- W4313854477 modified "2023-10-12" @default.
- W4313854477 title "Generating High-Resolution Fire Images with Controllable Attributes via Generative Adversarial Networks" @default.
- W4313854477 cites W2962785568 @default.
- W4313854477 cites W2981036610 @default.
- W4313854477 cites W3034600949 @default.
- W4313854477 cites W4288086194 @default.
- W4313854477 doi "https://doi.org/10.23919/iccas55662.2022.10003687" @default.
- W4313854477 hasPublicationYear "2022" @default.
- W4313854477 type Work @default.
- W4313854477 citedByCount "0" @default.
- W4313854477 crossrefType "proceedings-article" @default.
- W4313854477 hasAuthorship W4313854477A5011602242 @default.
- W4313854477 hasAuthorship W4313854477A5037300814 @default.
- W4313854477 hasConcept C108583219 @default.
- W4313854477 hasConcept C115961682 @default.
- W4313854477 hasConcept C119857082 @default.
- W4313854477 hasConcept C127413603 @default.
- W4313854477 hasConcept C153180895 @default.
- W4313854477 hasConcept C154945302 @default.
- W4313854477 hasConcept C167966045 @default.
- W4313854477 hasConcept C201995342 @default.
- W4313854477 hasConcept C2780451532 @default.
- W4313854477 hasConcept C2988773926 @default.
- W4313854477 hasConcept C31972630 @default.
- W4313854477 hasConcept C37736160 @default.
- W4313854477 hasConcept C39890363 @default.
- W4313854477 hasConcept C41008148 @default.
- W4313854477 hasConceptScore W4313854477C108583219 @default.
- W4313854477 hasConceptScore W4313854477C115961682 @default.
- W4313854477 hasConceptScore W4313854477C119857082 @default.
- W4313854477 hasConceptScore W4313854477C127413603 @default.
- W4313854477 hasConceptScore W4313854477C153180895 @default.
- W4313854477 hasConceptScore W4313854477C154945302 @default.
- W4313854477 hasConceptScore W4313854477C167966045 @default.
- W4313854477 hasConceptScore W4313854477C201995342 @default.
- W4313854477 hasConceptScore W4313854477C2780451532 @default.
- W4313854477 hasConceptScore W4313854477C2988773926 @default.
- W4313854477 hasConceptScore W4313854477C31972630 @default.
- W4313854477 hasConceptScore W4313854477C37736160 @default.
- W4313854477 hasConceptScore W4313854477C39890363 @default.
- W4313854477 hasConceptScore W4313854477C41008148 @default.
- W4313854477 hasFunder F4320322120 @default.
- W4313854477 hasFunder F4320326288 @default.
- W4313854477 hasLocation W43138544771 @default.
- W4313854477 hasOpenAccess W4313854477 @default.
- W4313854477 hasPrimaryLocation W43138544771 @default.
- W4313854477 hasRelatedWork W2792680412 @default.
- W4313854477 hasRelatedWork W2891804512 @default.
- W4313854477 hasRelatedWork W3024390022 @default.
- W4313854477 hasRelatedWork W3048537737 @default.
- W4313854477 hasRelatedWork W3120345119 @default.
- W4313854477 hasRelatedWork W3156291593 @default.
- W4313854477 hasRelatedWork W4224932539 @default.
- W4313854477 hasRelatedWork W4309299543 @default.
- W4313854477 hasRelatedWork W4313479464 @default.
- W4313854477 hasRelatedWork W4362495648 @default.
- W4313854477 isParatext "false" @default.
- W4313854477 isRetracted "false" @default.
- W4313854477 workType "article" @default.