Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316127349> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4316127349 endingPage "36" @default.
- W4316127349 startingPage "24" @default.
- W4316127349 abstract "Person image generation is a challenging task aimed to transfer the person of the source image from a source pose to a target pose while preserving its style. In this paper, we proposed a Generative Adversarial Network based on Decoupled Semantic Attention Transfer (DSAT-GAN), focusing on that local semantic representations of different image styles and contents cannot be accurately decoupled and transferred. This architecture employs a novel Multi-scale Semantic Mapping Generation Network (Ms-SMGN), driven by two network modules with different semantic attention mechanism, aiming to accurately align and transfer the representations of local semantics at different spatial scales. Then, a channel-separated convolution is applied in the encoding networks instead of the traditional channel fully-connected operation, which reduces computational complexity while realizing channel semantic decoupling. Moreover, a Gram matrix-based global style loss is introduced to further enhance the consistency of high-level semantic between generated and target images. Experiments on Market-1501 and DeepFashion datasets show that DSAT-GAN has superior performance compared with other recent baselines. Additionally, this architecture can be extended to the data enhancement scenes to significantly improve the accuracy of person Re-identification." @default.
- W4316127349 created "2023-01-14" @default.
- W4316127349 creator A5003554902 @default.
- W4316127349 creator A5036726873 @default.
- W4316127349 creator A5042101060 @default.
- W4316127349 date "2023-04-01" @default.
- W4316127349 modified "2023-10-18" @default.
- W4316127349 title "A novel Multi-scale architecture driven by decoupled semantic attention transfer for person image generation" @default.
- W4316127349 cites W1915485278 @default.
- W4316127349 cites W2117539524 @default.
- W4316127349 cites W2133665775 @default.
- W4316127349 cites W2183341477 @default.
- W4316127349 cites W2194775991 @default.
- W4316127349 cites W2204750386 @default.
- W4316127349 cites W2471768434 @default.
- W4316127349 cites W2475287302 @default.
- W4316127349 cites W2559085405 @default.
- W4316127349 cites W2565639579 @default.
- W4316127349 cites W2603777577 @default.
- W4316127349 cites W2798714868 @default.
- W4316127349 cites W2802832784 @default.
- W4316127349 cites W2883938080 @default.
- W4316127349 cites W2886799640 @default.
- W4316127349 cites W2912301747 @default.
- W4316127349 cites W2913029471 @default.
- W4316127349 cites W2921547827 @default.
- W4316127349 cites W2962785568 @default.
- W4316127349 cites W2962963674 @default.
- W4316127349 cites W2962982136 @default.
- W4316127349 cites W2963073614 @default.
- W4316127349 cites W2963266880 @default.
- W4316127349 cites W2963734522 @default.
- W4316127349 cites W2964002510 @default.
- W4316127349 cites W2964050021 @default.
- W4316127349 cites W2980755761 @default.
- W4316127349 cites W2984529706 @default.
- W4316127349 cites W2984983779 @default.
- W4316127349 cites W2991530302 @default.
- W4316127349 cites W2997142416 @default.
- W4316127349 cites W3013135579 @default.
- W4316127349 cites W3032180949 @default.
- W4316127349 cites W3034950620 @default.
- W4316127349 cites W3035515747 @default.
- W4316127349 cites W3092643288 @default.
- W4316127349 cites W3166096919 @default.
- W4316127349 cites W3176412779 @default.
- W4316127349 cites W4205848079 @default.
- W4316127349 cites W4312896571 @default.
- W4316127349 doi "https://doi.org/10.1016/j.cag.2023.01.003" @default.
- W4316127349 hasPublicationYear "2023" @default.
- W4316127349 type Work @default.
- W4316127349 citedByCount "2" @default.
- W4316127349 countsByYear W43161273492023 @default.
- W4316127349 crossrefType "journal-article" @default.
- W4316127349 hasAuthorship W4316127349A5003554902 @default.
- W4316127349 hasAuthorship W4316127349A5036726873 @default.
- W4316127349 hasAuthorship W4316127349A5042101060 @default.
- W4316127349 hasConcept C153180895 @default.
- W4316127349 hasConcept C154945302 @default.
- W4316127349 hasConcept C184337299 @default.
- W4316127349 hasConcept C199360897 @default.
- W4316127349 hasConcept C41008148 @default.
- W4316127349 hasConceptScore W4316127349C153180895 @default.
- W4316127349 hasConceptScore W4316127349C154945302 @default.
- W4316127349 hasConceptScore W4316127349C184337299 @default.
- W4316127349 hasConceptScore W4316127349C199360897 @default.
- W4316127349 hasConceptScore W4316127349C41008148 @default.
- W4316127349 hasFunder F4320321001 @default.
- W4316127349 hasFunder F4320324302 @default.
- W4316127349 hasLocation W43161273491 @default.
- W4316127349 hasOpenAccess W4316127349 @default.
- W4316127349 hasPrimaryLocation W43161273491 @default.
- W4316127349 hasRelatedWork W2033914206 @default.
- W4316127349 hasRelatedWork W2042327336 @default.
- W4316127349 hasRelatedWork W2046077695 @default.
- W4316127349 hasRelatedWork W2146076056 @default.
- W4316127349 hasRelatedWork W2163831990 @default.
- W4316127349 hasRelatedWork W2378160586 @default.
- W4316127349 hasRelatedWork W2380389143 @default.
- W4316127349 hasRelatedWork W2996038082 @default.
- W4316127349 hasRelatedWork W3003836766 @default.
- W4316127349 hasRelatedWork W3047965787 @default.
- W4316127349 hasVolume "111" @default.
- W4316127349 isParatext "false" @default.
- W4316127349 isRetracted "false" @default.
- W4316127349 workType "article" @default.