FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2948781670> ?p ?o ?g. }

• W2948781670 abstract "Hashing methods, which encode high-dimensional images with compact discrete codes, have been widely applied to enhance large-scale image retrieval. In this paper, we put forward Deep Spherical Quantization (DSQ), a novel method to make deep convolutional neural networks generate supervised and compact binary codes for efficient image search. Our approach simultaneously learns a mapping that transforms the input images into a low-dimensional discriminative space, and quantizes the transformed data points using multi-codebook quantization. To eliminate the negative effect of norm variance on codebook learning, we force the network to L_2 normalize the extracted features and then quantize the resulting vectors using a new supervised quantization technique specifically designed for points lying on a unit hypersphere. Furthermore, we introduce an easy-to-implement extension of our quantization technique that enforces sparsity on the codebooks. Extensive experiments demonstrate that DSQ and its sparse variant can generate semantically separable compact binary codes outperforming many state-of-the-art image retrieval methods on three benchmarks." @default.
• W2948781670 created "2019-06-14" @default.
• W2948781670 creator A5026015983 @default.
• W2948781670 creator A5062839888 @default.
• W2948781670 date "2019-06-07" @default.
• W2948781670 modified "2023-09-27" @default.
• W2948781670 title "Deep Spherical Quantization for Image Search" @default.
• W2948781670 cites W138284169 @default.
• W2948781670 cites W1910300841 @default.
• W2948781670 cites W1974647172 @default.
• W2948781670 cites W1977182282 @default.
• W2948781670 cites W1992371516 @default.
• W2948781670 cites W2005876975 @default.
• W2948781670 cites W2007972815 @default.
• W2948781670 cites W2041878876 @default.
• W2948781670 cites W2077815765 @default.
• W2948781670 cites W2083042020 @default.
• W2948781670 cites W2108598243 @default.
• W2948781670 cites W2113307832 @default.
• W2948781670 cites W2113606819 @default.
• W2948781670 cites W2124509324 @default.
• W2948781670 cites W2142881874 @default.
• W2948781670 cites W2148554573 @default.
• W2948781670 cites W2155541015 @default.
• W2948781670 cites W2164338181 @default.
• W2948781670 cites W2171149307 @default.
• W2948781670 cites W2293824885 @default.
• W2948781670 cites W2411707397 @default.
• W2948781670 cites W2464915613 @default.
• W2948781670 cites W2473499128 @default.
• W2948781670 cites W2520774990 @default.
• W2948781670 cites W2520799877 @default.
• W2948781670 cites W2562322388 @default.
• W2948781670 cites W2753634799 @default.
• W2948781670 cites W2772529866 @default.
• W2948781670 cites W2792096654 @default.
• W2948781670 cites W2798834175 @default.
• W2948781670 cites W2798956329 @default.
• W2948781670 cites W2799214875 @default.
• W2948781670 cites W2895046713 @default.
• W2948781670 cites W2897656415 @default.
• W2948781670 cites W2919919296 @default.
• W2948781670 cites W2944725912 @default.
• W2948781670 cites W2962849264 @default.
• W2948781670 cites W2962898354 @default.
• W2948781670 cites W2963276379 @default.
• W2948781670 cites W2963398644 @default.
• W2948781670 cites W2963540428 @default.
• W2948781670 cites W2963839334 @default.
• W2948781670 cites W2964280870 @default.
• W2948781670 cites W3118608800 @default.
• W2948781670 cites W2600537992 @default.
• W2948781670 hasPublicationYear "2019" @default.
• W2948781670 type Work @default.
• W2948781670 sameAs 2948781670 @default.
• W2948781670 citedByCount "0" @default.
• W2948781670 crossrefType "posted-content" @default.
• W2948781670 hasAuthorship W2948781670A5026015983 @default.
• W2948781670 hasAuthorship W2948781670A5062839888 @default.
• W2948781670 hasConcept C108583219 @default.
• W2948781670 hasConcept C11413529 @default.
• W2948781670 hasConcept C127759330 @default.
• W2948781670 hasConcept C153180895 @default.
• W2948781670 hasConcept C154945302 @default.
• W2948781670 hasConcept C199833920 @default.
• W2948781670 hasConcept C2776562905 @default.
• W2948781670 hasConcept C28855332 @default.
• W2948781670 hasConcept C33923547 @default.
• W2948781670 hasConcept C38652104 @default.
• W2948781670 hasConcept C40567965 @default.
• W2948781670 hasConcept C41008148 @default.
• W2948781670 hasConcept C48372109 @default.
• W2948781670 hasConcept C63435697 @default.
• W2948781670 hasConcept C81363708 @default.
• W2948781670 hasConcept C93372532 @default.
• W2948781670 hasConcept C94375191 @default.
• W2948781670 hasConcept C97931131 @default.
• W2948781670 hasConcept C99138194 @default.
• W2948781670 hasConceptScore W2948781670C108583219 @default.
• W2948781670 hasConceptScore W2948781670C11413529 @default.
• W2948781670 hasConceptScore W2948781670C127759330 @default.
• W2948781670 hasConceptScore W2948781670C153180895 @default.
• W2948781670 hasConceptScore W2948781670C154945302 @default.
• W2948781670 hasConceptScore W2948781670C199833920 @default.
• W2948781670 hasConceptScore W2948781670C2776562905 @default.
• W2948781670 hasConceptScore W2948781670C28855332 @default.
• W2948781670 hasConceptScore W2948781670C33923547 @default.
• W2948781670 hasConceptScore W2948781670C38652104 @default.
• W2948781670 hasConceptScore W2948781670C40567965 @default.
• W2948781670 hasConceptScore W2948781670C41008148 @default.
• W2948781670 hasConceptScore W2948781670C48372109 @default.
• W2948781670 hasConceptScore W2948781670C63435697 @default.
• W2948781670 hasConceptScore W2948781670C81363708 @default.
• W2948781670 hasConceptScore W2948781670C93372532 @default.
• W2948781670 hasConceptScore W2948781670C94375191 @default.
• W2948781670 hasConceptScore W2948781670C97931131 @default.
• W2948781670 hasConceptScore W2948781670C99138194 @default.
• W2948781670 hasLocation W29487816701 @default.
• W2948781670 hasOpenAccess W2948781670 @default.
• W2948781670 hasPrimaryLocation W29487816701 @default.

• next