With the exponential surge in diverse multimodal data, traditional unimodal retrieval
methods struggle to meet the needs of users seeking access to data across various …

Cross-modal alignment aims to build a bridge connecting vision and language. It is an
important multi-modal task that efficiently learns the semantic similarities between images …

Pre-trained vision-language models (VLM) such as CLIP, have demonstrated impressive
zero-shot performance on various vision tasks. Trained on millions or even billions of image …

As a pivotal link between visual and linguistic relationships, image-text cross-modal retrieval
has received widespread attention. However, existing studies primarily focus on intricate …

Machine Learning (ML) is continuously permeating a growing amount of application
domains. Generative AI such as Large Language Models (LLMs) also sees broad adoption …

Image-text retrieval is a fundamental cross-modal task that aims to align the representation
spaces between the image and text modalities. Existing cross-modal image-text retrieval …

Due to the inconsistency in feature representations between different modalities, namely
“Heterogeneous gap”, it remains a persistent challenge to correlate images and texts …

Cross-modal medical image-report retrieval task plays a significant role in clinical diagnosis
and various medical generative tasks. Eliminating heterogeneity between different …

In the swiftly advancing realm of information retrieval, unsupervised cross-modal hashing
has emerged as a focal point of research, taking advantage of the inherent advantages of …

The essence of improving the effect of cross-modal image–text retrieval (CIR) lies in the finer-
grained modeling of homogeneous features between modalities. However, in remote …