Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896580719> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2896580719 abstract "Product Quantisation (PQ) has been recognised as an effective encoding technique for scalable multimedia content analysis. In this paper, we propose a novel learning framework that enables an end-to-end encoding strategy from raw images to compact PQ codes. The system aims to learn both PQ encoding functions and codewords for content-based image retrieval. In detail, we first design a trainable encoding layer that is pluggable into neural networks, so the codewords can be trained in back-forward propagation. Then we integrate it into a Deep Convolutional Generative Adversarial Network (DC-GAN). In our proposed encoding framework, the raw images are directly encoded by passing through the convolutional and encoding layers, and the generator aims to use the codewords as constrained inputs to generate full image representations that are visually similar to the original images. By taking the advantages of the generative adversarial model, our proposed system can produce high-quality PQ codewords and encoding functions for scalable multimedia retrieval tasks. Experiments show that the proposed architecture GA-PQ outperforms the state-of-the-art encoding techniques on three public image datasets." @default.
- W2896580719 created "2018-10-26" @default.
- W2896580719 creator A5045140292 @default.
- W2896580719 creator A5058623879 @default.
- W2896580719 creator A5071549690 @default.
- W2896580719 date "2018-10-15" @default.
- W2896580719 modified "2023-09-24" @default.
- W2896580719 title "Generative Adversarial Product Quantisation" @default.
- W2896580719 cites W1974647172 @default.
- W2896580719 cites W2077815765 @default.
- W2896580719 cites W2124509324 @default.
- W2896580719 cites W2133995768 @default.
- W2896580719 cites W2724949466 @default.
- W2896580719 cites W2747853580 @default.
- W2896580719 cites W2765440071 @default.
- W2896580719 cites W2771872884 @default.
- W2896580719 doi "https://doi.org/10.1145/3240508.3240590" @default.
- W2896580719 hasPublicationYear "2018" @default.
- W2896580719 type Work @default.
- W2896580719 sameAs 2896580719 @default.
- W2896580719 citedByCount "3" @default.
- W2896580719 countsByYear W28965807192019 @default.
- W2896580719 countsByYear W28965807192022 @default.
- W2896580719 crossrefType "proceedings-article" @default.
- W2896580719 hasAuthorship W2896580719A5045140292 @default.
- W2896580719 hasAuthorship W2896580719A5058623879 @default.
- W2896580719 hasAuthorship W2896580719A5071549690 @default.
- W2896580719 hasConcept C108583219 @default.
- W2896580719 hasConcept C11413529 @default.
- W2896580719 hasConcept C115961682 @default.
- W2896580719 hasConcept C121332964 @default.
- W2896580719 hasConcept C125411270 @default.
- W2896580719 hasConcept C153180895 @default.
- W2896580719 hasConcept C154945302 @default.
- W2896580719 hasConcept C157899210 @default.
- W2896580719 hasConcept C163258240 @default.
- W2896580719 hasConcept C2780992000 @default.
- W2896580719 hasConcept C39890363 @default.
- W2896580719 hasConcept C41008148 @default.
- W2896580719 hasConcept C48044578 @default.
- W2896580719 hasConcept C57273362 @default.
- W2896580719 hasConcept C62520636 @default.
- W2896580719 hasConcept C77088390 @default.
- W2896580719 hasConcept C81363708 @default.
- W2896580719 hasConceptScore W2896580719C108583219 @default.
- W2896580719 hasConceptScore W2896580719C11413529 @default.
- W2896580719 hasConceptScore W2896580719C115961682 @default.
- W2896580719 hasConceptScore W2896580719C121332964 @default.
- W2896580719 hasConceptScore W2896580719C125411270 @default.
- W2896580719 hasConceptScore W2896580719C153180895 @default.
- W2896580719 hasConceptScore W2896580719C154945302 @default.
- W2896580719 hasConceptScore W2896580719C157899210 @default.
- W2896580719 hasConceptScore W2896580719C163258240 @default.
- W2896580719 hasConceptScore W2896580719C2780992000 @default.
- W2896580719 hasConceptScore W2896580719C39890363 @default.
- W2896580719 hasConceptScore W2896580719C41008148 @default.
- W2896580719 hasConceptScore W2896580719C48044578 @default.
- W2896580719 hasConceptScore W2896580719C57273362 @default.
- W2896580719 hasConceptScore W2896580719C62520636 @default.
- W2896580719 hasConceptScore W2896580719C77088390 @default.
- W2896580719 hasConceptScore W2896580719C81363708 @default.
- W2896580719 hasLocation W28965807191 @default.
- W2896580719 hasOpenAccess W2896580719 @default.
- W2896580719 hasPrimaryLocation W28965807191 @default.
- W2896580719 hasRelatedWork W2731899572 @default.
- W2896580719 hasRelatedWork W2732542196 @default.
- W2896580719 hasRelatedWork W2738221750 @default.
- W2896580719 hasRelatedWork W3116150086 @default.
- W2896580719 hasRelatedWork W3133861977 @default.
- W2896580719 hasRelatedWork W4200173597 @default.
- W2896580719 hasRelatedWork W4214561993 @default.
- W2896580719 hasRelatedWork W4312417841 @default.
- W2896580719 hasRelatedWork W4321369474 @default.
- W2896580719 hasRelatedWork W564581980 @default.
- W2896580719 isParatext "false" @default.
- W2896580719 isRetracted "false" @default.
- W2896580719 magId "2896580719" @default.
- W2896580719 workType "article" @default.