Abstract Contrastive Language-Image Pre-training (CLIP) has significantly boosted the
performance of various vision-language tasks by scaling up the dataset with image-text pairs …

In this work, by re-examining the" matching" nature of Anomaly Detection (AD), we propose
a new AD framework that simultaneously enjoys new records of AD accuracy and …

Zero-shot image retrieval involves retrieving images of unseen classes using a query image
of the same class. To determine whether a given image is of the same class as the query …

The goal of multimodal alignment is to learn a single latent space that is shared between
multimodal inputs. The most powerful models in this space have been trained using massive …

Adversarial attacks can cause misclassification in machine learning pipelines, posing a
significant safety risk in critical applications such as autonomous systems or medical …

Current image-text retrieval methods have demonstrated impressive performance in recent
years. However, they still face two problems: the inter-modal matching missing problem and …

Unsupervised cross-modal hashing (UCMH) has been commonly explored to support large-
scale cross-modal retrieval of unlabeled data. Despite promising progress, most existing …

We present an approach for multimodal pathology image search, using dynamic time
warping (DTW) on Variational Autoencoder (VAE) latent space that is fed into a ranked …

The objective of content-based image retrieval (CBIR) is to locate samples from a database
that are akin to a query, relying on the content embedded within the images. A contemporary …

Supervised learning-based adversarial attack detection methods rely on a large number of
labeled data and suffer significant performance degradation when applying the trained …