Edge-Guided Cross-Domain Learning with Shape Regression for Sketch-Based Image Retrieval
Sketch-based image retrieval (SBIR) is a challenging task due to the cross-domain gap between sketch queries and natural images. In this paper, we propose a novel edge-guided cross-domain learning network to reduce the domain gap. In particular, edge maps extracted from natural images are introduced...
Wedi'i Gadw mewn:
| Prif Awduron: | , , , , , |
|---|---|
| Fformat: | Artigo |
| Iaith: | Inglês |
| Cyhoeddwyd: |
IEEE
2019-01-01
|
| Cyfres: | IEEE Access |
| Pynciau: | |
| Mynediad Ar-lein: | https://ieeexplore.ieee.org/document/8664177/ |
| Tagiau: |
Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!
|