We study the zero-shot Composed Image Retrieval (ZS-CIR) task which is to retrieve the
target image given a reference image and a description without training on the triplet …

Neural networks embed the geometric structure of a data manifold lying in a high-
dimensional space into latent representations. Ideally, the distribution of the data points in …

Abstract Contrastive Language-Image Pre-training (CLIP) is attracting increasing attention
for its impressive zero-shot recognition performance on different down-stream tasks …

We investigate composed image retrieval with text feedback. Users gradually look for the
target of interest by moving from coarse to fine-grained feedback. However, existing …

While different neural models often exhibit latent spaces that are alike when exposed to
semantically related data, this intrinsic similarity is not always immediately discernible …

Recently, a number of approaches to train speech models by incorporating text into end-to-
end models have been developed, with Maestro advancing state-of-the-art automatic …

Contrastive Language-Image Pre-training (CLIP) has become the standard for learning
cross-modal representations between images and text. Efforts to improve its capabilities …

Aligned text-image encoders such as CLIP have become the de-facto model for vision-
language tasks. Furthermore modality-specific encoders achieve impressive performances …

Prompt tuning in natural language processing (NLP) has become an increasingly popular
method for adapting large language models to specific tasks. However, the transferability of …

It has been observed that representations learned by distinct neural networks conceal
structural similarities when the models are trained under similar inductive biases. From a …