Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385801091> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4385801091 abstract "Clothing segmentation and fine-grained attribute recognition are challenging tasks at the crossing of computer vision and fashion, which segment the entire ensemble clothing instances as well as recognize detailed attributes of the clothing products from any input human images. Many new models have been developed for the tasks in recent years, nevertheless the segmentation accuracy is less than satisfactory in case of layered clothing or fashion products in different scales. In this paper, a new DEtection TRansformer (DETR) based method is proposed to segment and recognize fine-grained attributes of ensemble clothing instances with high accuracy. In this model, we propose a multi-layered attention module by aggregating features of different scales, determining the various scale components of a single instance, and merging them together. We train our model on the Fashionpedia dataset and demonstrate our method surpasses SOTA models in tasks of layered clothing segmentation and fine-grained attribute recognition." @default.
- W4385801091 created "2023-08-15" @default.
- W4385801091 creator A5004249628 @default.
- W4385801091 creator A5030824965 @default.
- W4385801091 creator A5084573823 @default.
- W4385801091 date "2023-06-01" @default.
- W4385801091 modified "2023-10-16" @default.
- W4385801091 title "DETR-based Layered Clothing Segmentation and Fine-Grained Attribute Recognition" @default.
- W4385801091 cites W2471768434 @default.
- W4385801091 cites W2811481004 @default.
- W4385801091 cites W2962914239 @default.
- W4385801091 cites W2963351448 @default.
- W4385801091 cites W2967819436 @default.
- W4385801091 cites W3175016299 @default.
- W4385801091 cites W3176659256 @default.
- W4385801091 cites W4312422436 @default.
- W4385801091 cites W4312844845 @default.
- W4385801091 doi "https://doi.org/10.1109/cvprw59228.2023.00360" @default.
- W4385801091 hasPublicationYear "2023" @default.
- W4385801091 type Work @default.
- W4385801091 citedByCount "0" @default.
- W4385801091 crossrefType "proceedings-article" @default.
- W4385801091 hasAuthorship W4385801091A5004249628 @default.
- W4385801091 hasAuthorship W4385801091A5030824965 @default.
- W4385801091 hasAuthorship W4385801091A5084573823 @default.
- W4385801091 hasBestOaLocation W43858010912 @default.
- W4385801091 hasConcept C124504099 @default.
- W4385801091 hasConcept C153180895 @default.
- W4385801091 hasConcept C154945302 @default.
- W4385801091 hasConcept C166957645 @default.
- W4385801091 hasConcept C31972630 @default.
- W4385801091 hasConcept C41008148 @default.
- W4385801091 hasConcept C530175646 @default.
- W4385801091 hasConcept C89600930 @default.
- W4385801091 hasConcept C95457728 @default.
- W4385801091 hasConceptScore W4385801091C124504099 @default.
- W4385801091 hasConceptScore W4385801091C153180895 @default.
- W4385801091 hasConceptScore W4385801091C154945302 @default.
- W4385801091 hasConceptScore W4385801091C166957645 @default.
- W4385801091 hasConceptScore W4385801091C31972630 @default.
- W4385801091 hasConceptScore W4385801091C41008148 @default.
- W4385801091 hasConceptScore W4385801091C530175646 @default.
- W4385801091 hasConceptScore W4385801091C89600930 @default.
- W4385801091 hasConceptScore W4385801091C95457728 @default.
- W4385801091 hasFunder F4320321920 @default.
- W4385801091 hasLocation W43858010911 @default.
- W4385801091 hasLocation W43858010912 @default.
- W4385801091 hasOpenAccess W4385801091 @default.
- W4385801091 hasPrimaryLocation W43858010911 @default.
- W4385801091 hasRelatedWork W1669643531 @default.
- W4385801091 hasRelatedWork W1982826852 @default.
- W4385801091 hasRelatedWork W2005437358 @default.
- W4385801091 hasRelatedWork W2008656436 @default.
- W4385801091 hasRelatedWork W2023558673 @default.
- W4385801091 hasRelatedWork W2110230079 @default.
- W4385801091 hasRelatedWork W2134924024 @default.
- W4385801091 hasRelatedWork W2517104666 @default.
- W4385801091 hasRelatedWork W2613186388 @default.
- W4385801091 hasRelatedWork W1967061043 @default.
- W4385801091 isParatext "false" @default.
- W4385801091 isRetracted "false" @default.
- W4385801091 workType "article" @default.