Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304013755> ?p ?o ?g. }
- W4304013755 abstract "The main focus of most existing face hallucination methods is to generate visually pleasing results. However, in many applications, the final goal is to identify the person in the low-resolution (LR) image. In this paper, we propose a texture and identity integration network (TIIN) to effectively incorporate identity information into face hallucination tasks. TIIN consists of an identity-preserving denormalization module (IDM) and an equalized texture enhance module (ETEM). The IDM exploits the identity prior and the ETEM improves image quality through histogram equalization. To extract identity information effectively, we propose a resolution-robust identity knowledge distillation network (RIKDN). RIKDN is specifically designed for LR face recognition and can be of independent interest. It employs two teacher-student streams. One stream narrows the performance gap between high-resolution (HR) and LR images. The other distills correlation information from the HR-HR teacher stream to guide learning in the LR-HR student stream. We conduct extensive experiments on multiple datasets to demonstrate the effectiveness of our methods." @default.
- W4304013755 created "2022-10-10" @default.
- W4304013755 creator A5009239895 @default.
- W4304013755 creator A5020418509 @default.
- W4304013755 creator A5026184280 @default.
- W4304013755 creator A5041649804 @default.
- W4304013755 creator A5067841122 @default.
- W4304013755 creator A5069668655 @default.
- W4304013755 date "2022-10-10" @default.
- W4304013755 modified "2023-10-16" @default.
- W4304013755 title "Distilling Resolution-robust Identity Knowledge for Texture-Enhanced Face Hallucination" @default.
- W4304013755 cites W1509693426 @default.
- W4304013755 cites W1834627138 @default.
- W4304013755 cites W1885185971 @default.
- W4304013755 cites W2006902452 @default.
- W4304013755 cites W2054515210 @default.
- W4304013755 cites W2055492845 @default.
- W4304013755 cites W2194775991 @default.
- W4304013755 cites W2295477204 @default.
- W4304013755 cites W2519340935 @default.
- W4304013755 cites W2740535357 @default.
- W4304013755 cites W2750486618 @default.
- W4304013755 cites W2752042386 @default.
- W4304013755 cites W2773435308 @default.
- W4304013755 cites W2792481260 @default.
- W4304013755 cites W2883638418 @default.
- W4304013755 cites W2963102887 @default.
- W4304013755 cites W2963372104 @default.
- W4304013755 cites W2963460857 @default.
- W4304013755 cites W2963466847 @default.
- W4304013755 cites W2963645458 @default.
- W4304013755 cites W2963676087 @default.
- W4304013755 cites W2963814095 @default.
- W4304013755 cites W2964167901 @default.
- W4304013755 cites W2969985801 @default.
- W4304013755 cites W2971225816 @default.
- W4304013755 cites W2979639244 @default.
- W4304013755 cites W2997694845 @default.
- W4304013755 cites W3035605421 @default.
- W4304013755 cites W3090533328 @default.
- W4304013755 cites W3091218347 @default.
- W4304013755 cites W3097167612 @default.
- W4304013755 cites W3099206234 @default.
- W4304013755 cites W3111002277 @default.
- W4304013755 cites W3124399606 @default.
- W4304013755 cites W3166906529 @default.
- W4304013755 cites W3167297682 @default.
- W4304013755 cites W3169770376 @default.
- W4304013755 cites W3173435145 @default.
- W4304013755 cites W3183110203 @default.
- W4304013755 cites W3193517049 @default.
- W4304013755 cites W3205004111 @default.
- W4304013755 doi "https://doi.org/10.1145/3503161.3548437" @default.
- W4304013755 hasPublicationYear "2022" @default.
- W4304013755 type Work @default.
- W4304013755 citedByCount "0" @default.
- W4304013755 crossrefType "proceedings-article" @default.
- W4304013755 hasAuthorship W4304013755A5009239895 @default.
- W4304013755 hasAuthorship W4304013755A5020418509 @default.
- W4304013755 hasAuthorship W4304013755A5026184280 @default.
- W4304013755 hasAuthorship W4304013755A5041649804 @default.
- W4304013755 hasAuthorship W4304013755A5067841122 @default.
- W4304013755 hasAuthorship W4304013755A5069668655 @default.
- W4304013755 hasBestOaLocation W43040137551 @default.
- W4304013755 hasConcept C115961682 @default.
- W4304013755 hasConcept C120665830 @default.
- W4304013755 hasConcept C121332964 @default.
- W4304013755 hasConcept C138268822 @default.
- W4304013755 hasConcept C144024400 @default.
- W4304013755 hasConcept C153180895 @default.
- W4304013755 hasConcept C154945302 @default.
- W4304013755 hasConcept C192209626 @default.
- W4304013755 hasConcept C205372480 @default.
- W4304013755 hasConcept C24890656 @default.
- W4304013755 hasConcept C2778355321 @default.
- W4304013755 hasConcept C2779304628 @default.
- W4304013755 hasConcept C31972630 @default.
- W4304013755 hasConcept C36289849 @default.
- W4304013755 hasConcept C41008148 @default.
- W4304013755 hasConcept C53533937 @default.
- W4304013755 hasConceptScore W4304013755C115961682 @default.
- W4304013755 hasConceptScore W4304013755C120665830 @default.
- W4304013755 hasConceptScore W4304013755C121332964 @default.
- W4304013755 hasConceptScore W4304013755C138268822 @default.
- W4304013755 hasConceptScore W4304013755C144024400 @default.
- W4304013755 hasConceptScore W4304013755C153180895 @default.
- W4304013755 hasConceptScore W4304013755C154945302 @default.
- W4304013755 hasConceptScore W4304013755C192209626 @default.
- W4304013755 hasConceptScore W4304013755C205372480 @default.
- W4304013755 hasConceptScore W4304013755C24890656 @default.
- W4304013755 hasConceptScore W4304013755C2778355321 @default.
- W4304013755 hasConceptScore W4304013755C2779304628 @default.
- W4304013755 hasConceptScore W4304013755C31972630 @default.
- W4304013755 hasConceptScore W4304013755C36289849 @default.
- W4304013755 hasConceptScore W4304013755C41008148 @default.
- W4304013755 hasConceptScore W4304013755C53533937 @default.
- W4304013755 hasLocation W43040137551 @default.
- W4304013755 hasOpenAccess W4304013755 @default.
- W4304013755 hasPrimaryLocation W43040137551 @default.
- W4304013755 hasRelatedWork W1892011953 @default.