Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220802905> ?p ?o ?g. }
- W4220802905 abstract "Visual analysis of fashion images gain much attention in the fashion industry due to its commercial and social importance. In recent years, deep learning techniques offer overwhelming progress in improving the accuracy of fine-grained apparel segmentation with accurate bounding box prediction. The baseline pixel-based masking techniques show excellent performance in object detection and segmentation but sometimes ignores the boundary of objects, resulting in uneven and complicated segmentation masks. Moreover, it is time taking to generate a multi-scale feature map against each anchor box. To remedy this problem, a more accurate, faster, and suitable deep learning architecture is proposed that accurately detects, classify, and performs fine-grained segmentation of cloth products in a single platform. In this paper, initially, an Object Class Head Detector model is proposed in which the baseline Mask-RCNN model is used as a reference model. Here, we replace the Region Proposal Network with the proposed modified YoloV2 model to locate apparel products with its class prediction. The modified YoloV2 model has more capability to detect tiny objects because of local and high-level feature fusion. The goal of this step is to accurately locate the objects in minimum time intervals. Furthermore, the predicted bounding box is converted to object shape offsets using deep snake architecture that tightly fits onto the apparel shape. It can improve the accuracy of cloth shape segmentation by preserving object contours. The proposed architecture is empirically validated on various existing fashion image datasets. The experimental results illustrate that the proposed architecture performs better on the Deepfashion2 dataset with mAP of 86.86%, as compared to other state-of-the-art deep learning models." @default.
- W4220802905 created "2022-04-03" @default.
- W4220802905 creator A5002855381 @default.
- W4220802905 creator A5022309652 @default.
- W4220802905 creator A5052505171 @default.
- W4220802905 creator A5073915117 @default.
- W4220802905 date "2022-03-14" @default.
- W4220802905 modified "2023-09-25" @default.
- W4220802905 title "A novel approach of boundary preservative apparel detection and classification of fashion images using deep learning" @default.
- W4220802905 cites W1536680647 @default.
- W4220802905 cites W1903029394 @default.
- W4220802905 cites W2037947416 @default.
- W4220802905 cites W2091473544 @default.
- W4220802905 cites W2160977321 @default.
- W4220802905 cites W2405088233 @default.
- W4220802905 cites W2412782625 @default.
- W4220802905 cites W2565639579 @default.
- W4220802905 cites W2570343428 @default.
- W4220802905 cites W2711321710 @default.
- W4220802905 cites W2756291343 @default.
- W4220802905 cites W2760516584 @default.
- W4220802905 cites W2771435365 @default.
- W4220802905 cites W2780202401 @default.
- W4220802905 cites W2789006728 @default.
- W4220802905 cites W2811481004 @default.
- W4220802905 cites W2892166671 @default.
- W4220802905 cites W2902306794 @default.
- W4220802905 cites W2907502322 @default.
- W4220802905 cites W2909971279 @default.
- W4220802905 cites W2932272460 @default.
- W4220802905 cites W2963037989 @default.
- W4220802905 cites W2963150697 @default.
- W4220802905 cites W2967819436 @default.
- W4220802905 cites W2969991587 @default.
- W4220802905 cites W2970127347 @default.
- W4220802905 cites W2978917440 @default.
- W4220802905 cites W2988916019 @default.
- W4220802905 cites W2989604896 @default.
- W4220802905 cites W2993182889 @default.
- W4220802905 cites W2995278328 @default.
- W4220802905 cites W2998860519 @default.
- W4220802905 cites W3013222095 @default.
- W4220802905 cites W3015500262 @default.
- W4220802905 cites W3035709993 @default.
- W4220802905 cites W3043995050 @default.
- W4220802905 cites W3088163045 @default.
- W4220802905 cites W3092663126 @default.
- W4220802905 cites W3105335430 @default.
- W4220802905 cites W3106651317 @default.
- W4220802905 cites W3128670213 @default.
- W4220802905 cites W3155257528 @default.
- W4220802905 cites W3170019900 @default.
- W4220802905 cites W3175016299 @default.
- W4220802905 cites W3213267304 @default.
- W4220802905 cites W639708223 @default.
- W4220802905 cites W91087281 @default.
- W4220802905 doi "https://doi.org/10.1002/mma.8197" @default.
- W4220802905 hasPublicationYear "2022" @default.
- W4220802905 type Work @default.
- W4220802905 citedByCount "2" @default.
- W4220802905 countsByYear W42208029052022 @default.
- W4220802905 countsByYear W42208029052023 @default.
- W4220802905 crossrefType "journal-article" @default.
- W4220802905 hasAuthorship W4220802905A5002855381 @default.
- W4220802905 hasAuthorship W4220802905A5022309652 @default.
- W4220802905 hasAuthorship W4220802905A5052505171 @default.
- W4220802905 hasAuthorship W4220802905A5073915117 @default.
- W4220802905 hasConcept C108583219 @default.
- W4220802905 hasConcept C115961682 @default.
- W4220802905 hasConcept C124504099 @default.
- W4220802905 hasConcept C134306372 @default.
- W4220802905 hasConcept C138885662 @default.
- W4220802905 hasConcept C147037132 @default.
- W4220802905 hasConcept C153180895 @default.
- W4220802905 hasConcept C154945302 @default.
- W4220802905 hasConcept C2776151529 @default.
- W4220802905 hasConcept C2776401178 @default.
- W4220802905 hasConcept C2777212361 @default.
- W4220802905 hasConcept C2781238097 @default.
- W4220802905 hasConcept C31972630 @default.
- W4220802905 hasConcept C33923547 @default.
- W4220802905 hasConcept C41008148 @default.
- W4220802905 hasConcept C41895202 @default.
- W4220802905 hasConcept C62354387 @default.
- W4220802905 hasConcept C63584917 @default.
- W4220802905 hasConcept C89600930 @default.
- W4220802905 hasConceptScore W4220802905C108583219 @default.
- W4220802905 hasConceptScore W4220802905C115961682 @default.
- W4220802905 hasConceptScore W4220802905C124504099 @default.
- W4220802905 hasConceptScore W4220802905C134306372 @default.
- W4220802905 hasConceptScore W4220802905C138885662 @default.
- W4220802905 hasConceptScore W4220802905C147037132 @default.
- W4220802905 hasConceptScore W4220802905C153180895 @default.
- W4220802905 hasConceptScore W4220802905C154945302 @default.
- W4220802905 hasConceptScore W4220802905C2776151529 @default.
- W4220802905 hasConceptScore W4220802905C2776401178 @default.
- W4220802905 hasConceptScore W4220802905C2777212361 @default.
- W4220802905 hasConceptScore W4220802905C2781238097 @default.
- W4220802905 hasConceptScore W4220802905C31972630 @default.
- W4220802905 hasConceptScore W4220802905C33923547 @default.