Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385488512> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4385488512 abstract "Automatic object recoloring or swatch generation aims to change color of an object or the entire scene without altering the structural consistency. The challenges exacerbate while dealing with retail items, such as clothing, shoes and accessories due to the presence of complex patterns, folds and shadows, deformation caused by the human model, and small components such as frills, buttons, belts, etc. The challenge associated with this application increases further for multi-colored item and multi-apparel setup. In this work, we aim to address these problems with our novel architecture SwatchNet based on generative adversarial network (GAN). It stems from the proposed apparel components aware feature extraction module to create rich feature embedding, which guides the proposed dual attention u-net to synthesize recolored product image. For seamless information flow, we have also proposed a dual attention module at the bottleneck of encoder and decoder. Finally, we unify a diverse set of recoloring applications using a fixed training and inference pipeline. The experimental results of fashion item recoloring for several test setups using four large-scale datasets demonstrate the effectiveness of our proposed approach." @default.
- W4385488512 created "2023-08-03" @default.
- W4385488512 creator A5013146462 @default.
- W4385488512 creator A5015757476 @default.
- W4385488512 creator A5017932558 @default.
- W4385488512 creator A5051876605 @default.
- W4385488512 creator A5066546706 @default.
- W4385488512 creator A5072563444 @default.
- W4385488512 creator A5077902462 @default.
- W4385488512 creator A5091021144 @default.
- W4385488512 date "2023-06-18" @default.
- W4385488512 modified "2023-10-16" @default.
- W4385488512 title "SwatchNet: Small Components Aware Attention for Fashion Product Recoloring" @default.
- W4385488512 cites W1987971958 @default.
- W4385488512 cites W2093848332 @default.
- W4385488512 cites W2097117768 @default.
- W4385488512 cites W2194775991 @default.
- W4385488512 cites W2471768434 @default.
- W4385488512 cites W2531409750 @default.
- W4385488512 cites W2549139847 @default.
- W4385488512 cites W2591510999 @default.
- W4385488512 cites W2750259860 @default.
- W4385488512 cites W2752782242 @default.
- W4385488512 cites W2802650881 @default.
- W4385488512 cites W2884585870 @default.
- W4385488512 cites W2962770929 @default.
- W4385488512 cites W2962793481 @default.
- W4385488512 cites W2963073614 @default.
- W4385488512 cites W2989855043 @default.
- W4385488512 cites W3035149916 @default.
- W4385488512 cites W3174868683 @default.
- W4385488512 cites W3204676534 @default.
- W4385488512 cites W4289830204 @default.
- W4385488512 doi "https://doi.org/10.1109/ijcnn54540.2023.10191677" @default.
- W4385488512 hasPublicationYear "2023" @default.
- W4385488512 type Work @default.
- W4385488512 citedByCount "0" @default.
- W4385488512 crossrefType "proceedings-article" @default.
- W4385488512 hasAuthorship W4385488512A5013146462 @default.
- W4385488512 hasAuthorship W4385488512A5015757476 @default.
- W4385488512 hasAuthorship W4385488512A5017932558 @default.
- W4385488512 hasAuthorship W4385488512A5051876605 @default.
- W4385488512 hasAuthorship W4385488512A5066546706 @default.
- W4385488512 hasAuthorship W4385488512A5072563444 @default.
- W4385488512 hasAuthorship W4385488512A5077902462 @default.
- W4385488512 hasAuthorship W4385488512A5091021144 @default.
- W4385488512 hasConcept C149635348 @default.
- W4385488512 hasConcept C154945302 @default.
- W4385488512 hasConcept C199360897 @default.
- W4385488512 hasConcept C2776214188 @default.
- W4385488512 hasConcept C2780513914 @default.
- W4385488512 hasConcept C31972630 @default.
- W4385488512 hasConcept C41008148 @default.
- W4385488512 hasConcept C41608201 @default.
- W4385488512 hasConcept C43521106 @default.
- W4385488512 hasConcept C52622490 @default.
- W4385488512 hasConceptScore W4385488512C149635348 @default.
- W4385488512 hasConceptScore W4385488512C154945302 @default.
- W4385488512 hasConceptScore W4385488512C199360897 @default.
- W4385488512 hasConceptScore W4385488512C2776214188 @default.
- W4385488512 hasConceptScore W4385488512C2780513914 @default.
- W4385488512 hasConceptScore W4385488512C31972630 @default.
- W4385488512 hasConceptScore W4385488512C41008148 @default.
- W4385488512 hasConceptScore W4385488512C41608201 @default.
- W4385488512 hasConceptScore W4385488512C43521106 @default.
- W4385488512 hasConceptScore W4385488512C52622490 @default.
- W4385488512 hasLocation W43854885121 @default.
- W4385488512 hasOpenAccess W4385488512 @default.
- W4385488512 hasPrimaryLocation W43854885121 @default.
- W4385488512 hasRelatedWork W2023603361 @default.
- W4385488512 hasRelatedWork W2078130820 @default.
- W4385488512 hasRelatedWork W2099597042 @default.
- W4385488512 hasRelatedWork W2154461499 @default.
- W4385488512 hasRelatedWork W2354251581 @default.
- W4385488512 hasRelatedWork W2357461155 @default.
- W4385488512 hasRelatedWork W2384129116 @default.
- W4385488512 hasRelatedWork W2623483207 @default.
- W4385488512 hasRelatedWork W2766721049 @default.
- W4385488512 hasRelatedWork W2899307613 @default.
- W4385488512 isParatext "false" @default.
- W4385488512 isRetracted "false" @default.
- W4385488512 workType "article" @default.