A semi-supervised feature-level attribute manipulation method for fashion images that matches manipulated feature distributions to real features to support both instance retrieval and attribute editing.
Combination of multiple global descriptors for image retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semi-supervised Feature-Level Attribute Manipulation for Fashion Image Retrieval
A semi-supervised feature-level attribute manipulation method for fashion images that matches manipulated feature distributions to real features to support both instance retrieval and attribute editing.