Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285771359> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4285771359 abstract "Semantic segmentation task aims to create a dense classification by labeling pixelwise each object present in images. Convolutional neural network (CNN) approaches have been proved useful by exhibiting the best results in this task. However, some challenges remain, such as the low-resolution of feature maps and the loss of spatial precision, both produced in the last convolution layer of the CNNs. In this work, we propose an hourglass model based on the multi-task approach. Consequently, we combine the tasks of edge detection, semantic segmentation, and distance transform. The refinement of the tasks (getting specific information of each task) is obtained in the last layers of the decodification stage. All the tasks share the rest of the information, that is, shared weights. Thus our model is efficient with respect to the number of tasks and memory used. We obtained encouraging preliminary results still in images using Cityspace and Kitti datasets." @default.
- W4285771359 created "2022-07-19" @default.
- W4285771359 creator A5090851317 @default.
- W4285771359 date "2019-12-08" @default.
- W4285771359 modified "2023-10-03" @default.
- W4285771359 title "Semantic Segmentation on Image Using Multi-task Hourglass Networks" @default.
- W4285771359 doi "https://doi.org/10.52591/lxai201912085" @default.
- W4285771359 hasPublicationYear "2019" @default.
- W4285771359 type Work @default.
- W4285771359 citedByCount "0" @default.
- W4285771359 crossrefType "proceedings-article" @default.
- W4285771359 hasAuthorship W4285771359A5090851317 @default.
- W4285771359 hasBestOaLocation W42857713591 @default.
- W4285771359 hasConcept C124504099 @default.
- W4285771359 hasConcept C127532173 @default.
- W4285771359 hasConcept C138885662 @default.
- W4285771359 hasConcept C153180895 @default.
- W4285771359 hasConcept C154945302 @default.
- W4285771359 hasConcept C162307627 @default.
- W4285771359 hasConcept C162324750 @default.
- W4285771359 hasConcept C166957645 @default.
- W4285771359 hasConcept C178790620 @default.
- W4285771359 hasConcept C185592680 @default.
- W4285771359 hasConcept C187736073 @default.
- W4285771359 hasConcept C2776401178 @default.
- W4285771359 hasConcept C2779227376 @default.
- W4285771359 hasConcept C2780451532 @default.
- W4285771359 hasConcept C2781238097 @default.
- W4285771359 hasConcept C31972630 @default.
- W4285771359 hasConcept C41008148 @default.
- W4285771359 hasConcept C41895202 @default.
- W4285771359 hasConcept C45347329 @default.
- W4285771359 hasConcept C50644808 @default.
- W4285771359 hasConcept C52622490 @default.
- W4285771359 hasConcept C81363708 @default.
- W4285771359 hasConcept C89600930 @default.
- W4285771359 hasConcept C95457728 @default.
- W4285771359 hasConceptScore W4285771359C124504099 @default.
- W4285771359 hasConceptScore W4285771359C127532173 @default.
- W4285771359 hasConceptScore W4285771359C138885662 @default.
- W4285771359 hasConceptScore W4285771359C153180895 @default.
- W4285771359 hasConceptScore W4285771359C154945302 @default.
- W4285771359 hasConceptScore W4285771359C162307627 @default.
- W4285771359 hasConceptScore W4285771359C162324750 @default.
- W4285771359 hasConceptScore W4285771359C166957645 @default.
- W4285771359 hasConceptScore W4285771359C178790620 @default.
- W4285771359 hasConceptScore W4285771359C185592680 @default.
- W4285771359 hasConceptScore W4285771359C187736073 @default.
- W4285771359 hasConceptScore W4285771359C2776401178 @default.
- W4285771359 hasConceptScore W4285771359C2779227376 @default.
- W4285771359 hasConceptScore W4285771359C2780451532 @default.
- W4285771359 hasConceptScore W4285771359C2781238097 @default.
- W4285771359 hasConceptScore W4285771359C31972630 @default.
- W4285771359 hasConceptScore W4285771359C41008148 @default.
- W4285771359 hasConceptScore W4285771359C41895202 @default.
- W4285771359 hasConceptScore W4285771359C45347329 @default.
- W4285771359 hasConceptScore W4285771359C50644808 @default.
- W4285771359 hasConceptScore W4285771359C52622490 @default.
- W4285771359 hasConceptScore W4285771359C81363708 @default.
- W4285771359 hasConceptScore W4285771359C89600930 @default.
- W4285771359 hasConceptScore W4285771359C95457728 @default.
- W4285771359 hasLocation W42857713591 @default.
- W4285771359 hasOpenAccess W4285771359 @default.
- W4285771359 hasPrimaryLocation W42857713591 @default.
- W4285771359 hasRelatedWork W1669643531 @default.
- W4285771359 hasRelatedWork W1963494852 @default.
- W4285771359 hasRelatedWork W2004370856 @default.
- W4285771359 hasRelatedWork W2019566805 @default.
- W4285771359 hasRelatedWork W2026019026 @default.
- W4285771359 hasRelatedWork W2059299633 @default.
- W4285771359 hasRelatedWork W2101128524 @default.
- W4285771359 hasRelatedWork W2122581818 @default.
- W4285771359 hasRelatedWork W2383464976 @default.
- W4285771359 hasRelatedWork W1967061043 @default.
- W4285771359 isParatext "false" @default.
- W4285771359 isRetracted "false" @default.
- W4285771359 workType "article" @default.