Computational technologies for fashion recommendation: A survey
Fashion recommendation is a key research field in computational fashion research and has
attracted considerable interest in the computer vision, multimedia, and information retrieval …
attracted considerable interest in the computer vision, multimedia, and information retrieval …
A survey on rag meeting llms: Towards retrieval-augmented large language models
As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can
offer reliable and up-to-date external knowledge, providing huge convenience for numerous …
offer reliable and up-to-date external knowledge, providing huge convenience for numerous …
Diffusion models for generative outfit recommendation
Outfit Recommendation (OR) in the fashion domain has evolved through two stages: Pre-
defined Outfit Recommendation and Personalized Outfit Composition. However, both stages …
defined Outfit Recommendation and Personalized Outfit Composition. However, both stages …
Your negative may not be true negative: Boosting image-text matching with false negative elimination
Most existing image-text matching methods adopt triplet loss as the optimization objective,
and choosing a proper negative sample for the triplet of< anchor, positive, negative> is …
and choosing a proper negative sample for the triplet of< anchor, positive, negative> is …
Sgdiff: A style guided diffusion model for fashion synthesis
This paper reports on the development of a novel style guided diffusion model (SGDiff)
which overcomes certain weaknesses inherent in existing models for image synthesis. The …
which overcomes certain weaknesses inherent in existing models for image synthesis. The …
Align and retrieve: Composition and decomposition learning in image retrieval with text feedback
We study the task of image retrieval with text feedback, where a reference image and
modification text are composed to retrieve the desired target image. To accomplish this goal …
modification text are composed to retrieve the desired target image. To accomplish this goal …
Leveraging multimodal features and item-level user feedback for bundle construction
Automatic bundle construction is a crucial prerequisite step in various bundle-aware online
services. Previous approaches are mostly designed to model the bundling strategy of …
services. Previous approaches are mostly designed to model the bundling strategy of …
A Survey on Bundle Recommendation: Methods, Applications, and Challenges
Modeling Multi-Relational Connectivity for Personalized Fashion Matching
Personalized fashion matching task aims to predict the compatible fashion items given
available ones for specific users through the effective modeling of the third-order interaction …
available ones for specific users through the effective modeling of the third-order interaction …