CODE

Chapter 3: Data-driven Compatibility Modeling

We employ a dual autoencoder network to learn the latent compatibility space, where we jointly model the coherent relationship between visual and contextual modalities and the implicit preference among items via the Bayesian Personalized Ranking. The code can be downloaded here.

Chapter 4: Knowledge-guided Compatibility Modeling

We present a compatibility modeling scheme with attentive knowledge distillation, which is able to learn from both the specific data samples and the general domain knowledge. The code can be downloaded here.

Chapter 5: Prototype-wise Interpretable Compatibility Modeling

We comprehensively tackle all the three essential problems, namely, the compatibility determination between fashion items, discordant component interpretation for incompatible outfits, and alternative item suggestion towards making compatible ones. We focus on devising a versatile attribute-wise interpretable clothing matching scheme, since attributes are the most intuitive semantic cues to characterize fashion items. The code can be downloaded here.

Chapter 6: Personalized Compatibility Modeling

We present a personalized compatibility modeling scheme for clothing matching, which is able to measure the compatibility between fashion items from not only the general aesthetics but also the personal preference perspectives. The code can be downloaded here.

Chapter 7: Personalized Capsule Wardrobe Creation

we propose a combinatorial optimization-based personalized capsule wardrobe creation framework with dual compatibility modeling. The key novelty of the proposed framework lies in the creation of a scoring model that comprehensively evaluates the compatibility of potential outfits from both user-garment and garment-garment perspectives. The code can be downloaded here.

This program is licensed under the GNU General Public License 3.0 (https://www.gnu.org/licenses/gpl-3.0.html). Any derivative work obtained under this license must be licensed under the GNU General Public License as published by the Free Software Foundation, either Version 3 of the License, or (at your option) any later version, if this derivative work is distributed to a third party.

The copyright for the program is owned by Shandong University. For commercial projects that require the ability to distribute the code of this program as part of a program that cannot be distributed under the GNU General Public License, please contact <sxmustc@gmail.com> to purchase a commercial license.