Fashion recommendation is a key research field in computational fashion research and has
attracted considerable interest in the computer vision, multimedia, and information retrieval …

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 …

Fine-grained vision-language models (VLM) have been widely used for inter-modality local
alignment between the predefined fixed patches and textual words. However, in medical …

Abstract Composed Image Retrieval (CIR) presents challenges in expressing search intent
through hybrid-modality queries where users search for a target image using another image …

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 …

Most existing cross-modal retrieval methods employ two-stream encoders with different
architectures for images and texts, eg, CNN for images and RNN/Transformer for texts. Such …

Composed image retrieval (CIR) aims to retrieve the target image based on a multimodal
query, ie, a reference image paired with corresponding modification text. Recent CIR studies …

Multimodal Conditional Image Synthesis (MCIS) aims to generate images according to
different modalities input and their combination, which allows users to describe their …

Going beyond the user–item rating information, recent studies have utilized additional
information to improve the performance of recommender systems. Graph neural network …

Noise-to-image synthesis continues to be challenging, despite the application of the
advanced loss functions in Generative Adversarial Networks (GANs). The main issue lies in …