Matches in SemOpenAlex for { <https://semopenalex.org/work/W2113226089> ?p ?o ?g. }
Showing items 1 to 54 of
54
with 100 items per page.
- W2113226089 abstract "The paper describes how to improve the robustness to occlusions in face recognition and detection. We propose a neural network architecture which integrates an auto-associative neural network into a simple classifier. The auto-associative network is employed to recall the original face from a partially occluded face image and to detect the occluded regions in the input image. The original face can be reconstructed by replacing those regions with the recalled pixels. By applying this reconstruction process recursively, the integrated network is able to classify occluded faces robustly. To confirm the effectiveness of this method, we performed experiments on face image classification and face detection. It is shown that the classification performance is not decreased even if 20-30% of the face image is occluded." @default.
- W2113226089 created "2016-06-24" @default.
- W2113226089 creator A5069942215 @default.
- W2113226089 creator A5083542428 @default.
- W2113226089 creator A5086456461 @default.
- W2113226089 date "2004-01-24" @default.
- W2113226089 modified "2023-09-23" @default.
- W2113226089 title "Recognition and detection of occluded faces by a neural network classifier with recursive data reconstruction" @default.
- W2113226089 cites W1968603670 @default.
- W2113226089 cites W1991848143 @default.
- W2113226089 cites W2078626246 @default.
- W2113226089 cites W2098693229 @default.
- W2113226089 cites W2104163856 @default.
- W2113226089 cites W2111231637 @default.
- W2113226089 cites W2489822048 @default.
- W2113226089 cites W4210310779 @default.
- W2113226089 doi "https://doi.org/10.1109/avss.2003.1217901" @default.
- W2113226089 hasPublicationYear "2004" @default.
- W2113226089 type Work @default.
- W2113226089 sameAs 2113226089 @default.
- W2113226089 citedByCount "12" @default.
- W2113226089 countsByYear W21132260892014 @default.
- W2113226089 countsByYear W21132260892015 @default.
- W2113226089 crossrefType "proceedings-article" @default.
- W2113226089 hasAuthorship W2113226089A5069942215 @default.
- W2113226089 hasAuthorship W2113226089A5083542428 @default.
- W2113226089 hasAuthorship W2113226089A5086456461 @default.
- W2113226089 hasConcept C153180895 @default.
- W2113226089 hasConcept C154945302 @default.
- W2113226089 hasConcept C41008148 @default.
- W2113226089 hasConcept C50644808 @default.
- W2113226089 hasConcept C95623464 @default.
- W2113226089 hasConceptScore W2113226089C153180895 @default.
- W2113226089 hasConceptScore W2113226089C154945302 @default.
- W2113226089 hasConceptScore W2113226089C41008148 @default.
- W2113226089 hasConceptScore W2113226089C50644808 @default.
- W2113226089 hasConceptScore W2113226089C95623464 @default.
- W2113226089 hasLocation W21132260891 @default.
- W2113226089 hasOpenAccess W2113226089 @default.
- W2113226089 hasPrimaryLocation W21132260891 @default.
- W2113226089 hasRelatedWork W2001652754 @default.
- W2113226089 hasRelatedWork W2167582322 @default.
- W2113226089 hasRelatedWork W2379065761 @default.
- W2113226089 hasRelatedWork W2549006548 @default.
- W2113226089 hasRelatedWork W2563096758 @default.
- W2113226089 hasRelatedWork W2784352036 @default.
- W2113226089 hasRelatedWork W2807311372 @default.
- W2113226089 hasRelatedWork W2972035100 @default.
- W2113226089 hasRelatedWork W3043252291 @default.
- W2113226089 hasRelatedWork W4214932115 @default.
- W2113226089 isParatext "false" @default.
- W2113226089 isRetracted "false" @default.
- W2113226089 magId "2113226089" @default.
- W2113226089 workType "article" @default.