Matches in SemOpenAlex for { <https://semopenalex.org/work/W3018442006> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3018442006 abstract "Unlike RBG cameras, thermal cameras perform well under very low lighting conditions and can capture information beyond the human visible spectrum. This provides many advantages for security and surveillance applications. However, performing face recognition tasks in the thermal domain is very challenging given the limited visual information embedded in thermal images and the inherent similarities among facial heat maps. Attempting to perform recognition across modalities, such as recognizing a face captured in the thermal domain given the corresponding visible light domain ground truth database or vice versa is also a challenge. In this paper, a Thermal to RGB Generative Adversarial Network (TRGAN) to automatically synthesize face images captured in the thermal domain, to their RBG counterparts, with a goal of reducing current inter-domain gaps and significantly improving cross-modal facial recognition capabilities is proposed. Experimental results on the TUFTS Face Dataset using the VGG-Face recognition model without retraining, demonstrates that performing image translation with the proposed TR-GAN model almost doubles the cross-modal recognition accuracy and also performs better than other state-of-the-art GAN models on the same task. The generator in our network uses a UNET like architecture with cascaded-in-cascaded blocks to reuse features from earlier convolutions, which helps generate high quality images. To further guide the generator to synthesize images with fine details, we optimize a training loss as the weighted sum of the perceptual, adversarial, and cycle-consistent loss. Simulation results demonstrate that the proposed model generates more realistic and more visually appealing images, with finer details and better reconstruction of intricate details such sunglasses and facial emotions, than similar GAN models." @default.
- W3018442006 created "2020-05-01" @default.
- W3018442006 creator A5022533698 @default.
- W3018442006 creator A5026968324 @default.
- W3018442006 creator A5048285657 @default.
- W3018442006 creator A5069074343 @default.
- W3018442006 date "2020-04-21" @default.
- W3018442006 modified "2023-09-30" @default.
- W3018442006 title "TR-GAN: thermal to RGB face synthesis with generative adversarial network for cross-modal face recognition" @default.
- W3018442006 doi "https://doi.org/10.1117/12.2558166" @default.
- W3018442006 hasPublicationYear "2020" @default.
- W3018442006 type Work @default.
- W3018442006 sameAs 3018442006 @default.
- W3018442006 citedByCount "12" @default.
- W3018442006 countsByYear W30184420062020 @default.
- W3018442006 countsByYear W30184420062021 @default.
- W3018442006 countsByYear W30184420062022 @default.
- W3018442006 countsByYear W30184420062023 @default.
- W3018442006 crossrefType "proceedings-article" @default.
- W3018442006 hasAuthorship W3018442006A5022533698 @default.
- W3018442006 hasAuthorship W3018442006A5026968324 @default.
- W3018442006 hasAuthorship W3018442006A5048285657 @default.
- W3018442006 hasAuthorship W3018442006A5069074343 @default.
- W3018442006 hasConcept C115961682 @default.
- W3018442006 hasConcept C121332964 @default.
- W3018442006 hasConcept C134306372 @default.
- W3018442006 hasConcept C144024400 @default.
- W3018442006 hasConcept C153180895 @default.
- W3018442006 hasConcept C154945302 @default.
- W3018442006 hasConcept C163258240 @default.
- W3018442006 hasConcept C185592680 @default.
- W3018442006 hasConcept C188027245 @default.
- W3018442006 hasConcept C2779304628 @default.
- W3018442006 hasConcept C2779757391 @default.
- W3018442006 hasConcept C2780992000 @default.
- W3018442006 hasConcept C31510193 @default.
- W3018442006 hasConcept C31972630 @default.
- W3018442006 hasConcept C33923547 @default.
- W3018442006 hasConcept C36289849 @default.
- W3018442006 hasConcept C36503486 @default.
- W3018442006 hasConcept C41008148 @default.
- W3018442006 hasConcept C62520636 @default.
- W3018442006 hasConcept C71139939 @default.
- W3018442006 hasConcept C82990744 @default.
- W3018442006 hasConceptScore W3018442006C115961682 @default.
- W3018442006 hasConceptScore W3018442006C121332964 @default.
- W3018442006 hasConceptScore W3018442006C134306372 @default.
- W3018442006 hasConceptScore W3018442006C144024400 @default.
- W3018442006 hasConceptScore W3018442006C153180895 @default.
- W3018442006 hasConceptScore W3018442006C154945302 @default.
- W3018442006 hasConceptScore W3018442006C163258240 @default.
- W3018442006 hasConceptScore W3018442006C185592680 @default.
- W3018442006 hasConceptScore W3018442006C188027245 @default.
- W3018442006 hasConceptScore W3018442006C2779304628 @default.
- W3018442006 hasConceptScore W3018442006C2779757391 @default.
- W3018442006 hasConceptScore W3018442006C2780992000 @default.
- W3018442006 hasConceptScore W3018442006C31510193 @default.
- W3018442006 hasConceptScore W3018442006C31972630 @default.
- W3018442006 hasConceptScore W3018442006C33923547 @default.
- W3018442006 hasConceptScore W3018442006C36289849 @default.
- W3018442006 hasConceptScore W3018442006C36503486 @default.
- W3018442006 hasConceptScore W3018442006C41008148 @default.
- W3018442006 hasConceptScore W3018442006C62520636 @default.
- W3018442006 hasConceptScore W3018442006C71139939 @default.
- W3018442006 hasConceptScore W3018442006C82990744 @default.
- W3018442006 hasLocation W30184420061 @default.
- W3018442006 hasOpenAccess W3018442006 @default.
- W3018442006 hasPrimaryLocation W30184420061 @default.
- W3018442006 hasRelatedWork W1775397219 @default.
- W3018442006 hasRelatedWork W2283162247 @default.
- W3018442006 hasRelatedWork W2347601237 @default.
- W3018442006 hasRelatedWork W2897995864 @default.
- W3018442006 hasRelatedWork W2908959303 @default.
- W3018442006 hasRelatedWork W2989983239 @default.
- W3018442006 hasRelatedWork W3204276937 @default.
- W3018442006 hasRelatedWork W4210401281 @default.
- W3018442006 hasRelatedWork W4212983513 @default.
- W3018442006 hasRelatedWork W4303182286 @default.
- W3018442006 isParatext "false" @default.
- W3018442006 isRetracted "false" @default.
- W3018442006 magId "3018442006" @default.
- W3018442006 workType "article" @default.