Matches in SemOpenAlex for { <https://semopenalex.org/work/W2982243647> ?p ?o ?g. }
- W2982243647 abstract "Very low resolution (VLR) image recognition corresponds to classifying images with resolution 16×16 or less. Though it has widespread applicability when objects are captured at a very large stand-off distance (e.g. surveillance scenario) or from wide angle mobile cameras, it has received limited attention. This research presents a novel Dual Directed Capsule Network model, termed as DirectCapsNet, for addressing VLR digit and face recognition. The proposed architecture utilizes a combination of capsule and convolutional layers for learning an effective VLR recognition model. The architecture also incorporates two novel loss functions: (i) the proposed HR-anchor loss and (ii) the proposed targeted reconstruction loss, in order to overcome the challenges of limited information content in VLR images. The proposed losses use high resolution images as auxiliary data during training to direct discriminative feature learning. Multiple experiments for VLR digit classification and VLR face recognition are performed along with comparisons with state-of-the-art algorithms. The proposed DirectCapsNet consistently showcases state-of-the-art results; for example, on the UCCS face database, it shows over 95% face recognition accuracy when 16×16 images are matched with 80×80 images." @default.
- W2982243647 created "2019-11-01" @default.
- W2982243647 creator A5011779957 @default.
- W2982243647 creator A5050521702 @default.
- W2982243647 creator A5066262755 @default.
- W2982243647 creator A5084235091 @default.
- W2982243647 date "2019-10-01" @default.
- W2982243647 modified "2023-10-01" @default.
- W2982243647 title "Dual Directed Capsule Network for Very Low Resolution Image Recognition" @default.
- W2982243647 cites W1425104224 @default.
- W2982243647 cites W1968112912 @default.
- W2982243647 cites W1983781364 @default.
- W2982243647 cites W1985436611 @default.
- W2982243647 cites W2007146377 @default.
- W2982243647 cites W2020447345 @default.
- W2982243647 cites W2067023690 @default.
- W2982243647 cites W2067042811 @default.
- W2982243647 cites W2082498363 @default.
- W2982243647 cites W2084413241 @default.
- W2982243647 cites W2084658294 @default.
- W2982243647 cites W2172157973 @default.
- W2982243647 cites W2332698925 @default.
- W2982243647 cites W2895526696 @default.
- W2982243647 cites W2898408087 @default.
- W2982243647 cites W2899029915 @default.
- W2982243647 cites W2901505625 @default.
- W2982243647 cites W2912990735 @default.
- W2982243647 cites W2940483533 @default.
- W2982243647 cites W2952841512 @default.
- W2982243647 cites W2963102887 @default.
- W2982243647 cites W2963384288 @default.
- W2982243647 cites W2963470893 @default.
- W2982243647 cites W2963814095 @default.
- W2982243647 cites W2964204524 @default.
- W2982243647 cites W2966661 @default.
- W2982243647 doi "https://doi.org/10.1109/iccv.2019.00043" @default.
- W2982243647 hasPublicationYear "2019" @default.
- W2982243647 type Work @default.
- W2982243647 sameAs 2982243647 @default.
- W2982243647 citedByCount "26" @default.
- W2982243647 countsByYear W29822436472020 @default.
- W2982243647 countsByYear W29822436472021 @default.
- W2982243647 countsByYear W29822436472022 @default.
- W2982243647 countsByYear W29822436472023 @default.
- W2982243647 crossrefType "proceedings-article" @default.
- W2982243647 hasAuthorship W2982243647A5011779957 @default.
- W2982243647 hasAuthorship W2982243647A5050521702 @default.
- W2982243647 hasAuthorship W2982243647A5066262755 @default.
- W2982243647 hasAuthorship W2982243647A5084235091 @default.
- W2982243647 hasBestOaLocation W29822436472 @default.
- W2982243647 hasConcept C108583219 @default.
- W2982243647 hasConcept C127313418 @default.
- W2982243647 hasConcept C138885662 @default.
- W2982243647 hasConcept C144024400 @default.
- W2982243647 hasConcept C153180895 @default.
- W2982243647 hasConcept C154945302 @default.
- W2982243647 hasConcept C205372480 @default.
- W2982243647 hasConcept C2776401178 @default.
- W2982243647 hasConcept C2779304628 @default.
- W2982243647 hasConcept C3019883945 @default.
- W2982243647 hasConcept C3020199158 @default.
- W2982243647 hasConcept C31510193 @default.
- W2982243647 hasConcept C31972630 @default.
- W2982243647 hasConcept C36289849 @default.
- W2982243647 hasConcept C41008148 @default.
- W2982243647 hasConcept C41895202 @default.
- W2982243647 hasConcept C52622490 @default.
- W2982243647 hasConcept C62649853 @default.
- W2982243647 hasConcept C81363708 @default.
- W2982243647 hasConcept C97931131 @default.
- W2982243647 hasConceptScore W2982243647C108583219 @default.
- W2982243647 hasConceptScore W2982243647C127313418 @default.
- W2982243647 hasConceptScore W2982243647C138885662 @default.
- W2982243647 hasConceptScore W2982243647C144024400 @default.
- W2982243647 hasConceptScore W2982243647C153180895 @default.
- W2982243647 hasConceptScore W2982243647C154945302 @default.
- W2982243647 hasConceptScore W2982243647C205372480 @default.
- W2982243647 hasConceptScore W2982243647C2776401178 @default.
- W2982243647 hasConceptScore W2982243647C2779304628 @default.
- W2982243647 hasConceptScore W2982243647C3019883945 @default.
- W2982243647 hasConceptScore W2982243647C3020199158 @default.
- W2982243647 hasConceptScore W2982243647C31510193 @default.
- W2982243647 hasConceptScore W2982243647C31972630 @default.
- W2982243647 hasConceptScore W2982243647C36289849 @default.
- W2982243647 hasConceptScore W2982243647C41008148 @default.
- W2982243647 hasConceptScore W2982243647C41895202 @default.
- W2982243647 hasConceptScore W2982243647C52622490 @default.
- W2982243647 hasConceptScore W2982243647C62649853 @default.
- W2982243647 hasConceptScore W2982243647C81363708 @default.
- W2982243647 hasConceptScore W2982243647C97931131 @default.
- W2982243647 hasLocation W29822436471 @default.
- W2982243647 hasLocation W29822436472 @default.
- W2982243647 hasOpenAccess W2982243647 @default.
- W2982243647 hasPrimaryLocation W29822436471 @default.
- W2982243647 hasRelatedWork W1775397219 @default.
- W2982243647 hasRelatedWork W2061273563 @default.
- W2982243647 hasRelatedWork W2279398222 @default.
- W2982243647 hasRelatedWork W2280716820 @default.
- W2982243647 hasRelatedWork W2285052147 @default.
- W2982243647 hasRelatedWork W2353840448 @default.