Fashion Domain
Research in the fashion domain focuses on leveraging artificial intelligence to enhance various aspects of the industry, from design and manufacturing to retail and customer experience. Current efforts concentrate on developing multimodal models, particularly those integrating vision and language, using architectures like transformers and diffusion models, to achieve tasks such as fashion item retrieval, generation of new designs from text or sketches, and personalized outfit recommendations. These advancements aim to improve efficiency, personalization, and overall customer satisfaction within the fashion industry, while also providing valuable datasets and benchmarks for the broader computer vision and AI research communities.
Papers
MADiff: Text-Guided Fashion Image Editing with Mask Prediction and Attention-Enhanced Diffusion
Zechao Zhan, Dehong Gao, Jinxia Zhang, Jiale Huang, Yang Hu, Xin Wang
FashionFAE: Fine-grained Attributes Enhanced Fashion Vision-Language Pre-training
Jiale Huang, Dehong Gao, Jinxia Zhang, Zechao Zhan, Yang Hu, Xin Wang