English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The focus of this paper is on the problem of image retrieval with attributemanipulation. Our proposed work is able to manipulate the desired attributes ofthe query image while maintaining its other attributes. For example, the collarattribute of the query image can be changed from round to v-neck to retrievesimilar images from a large dataset. A key challenge in e-commerce is thatimages have multiple attributes where users would like to manipulate and it isimportant to estimate discriminative feature representations for each of theseattributes. The proposed FashionSearchNet-v2 architecture is able to learnattribute specific representations by leveraging on its weakly-supervisedlocalization module, which ignores the unrelated features of attributes in thefeature space, thus improving the similarity learning. The network is jointlytrained with the combination of attribute classification and triplet rankingloss to estimate local representations. These local representations are thenmerged into a single global representation based on the instructed attributemanipulation where desired images can be retrieved with a distance metric. Theproposed method also provides explainability for its retrieval process to helpprovide additional information on the attention of the network. Experimentsperformed on several datasets that are rich in terms of the number ofattributes show that FashionSearchNet-v2 outperforms the other state-of-the-artattribute manipulation techniques. Different than our earlier work(FashionSearchNet), we propose several improvements in the learning procedureand show that the proposed FashionSearchNet-v2 can be generalized to differentdomains other than fashion.

FashionSearchNet-v2: Learning Attribute Representations with Localization for Image Retrieval with Attribute Manipulation