Abstract In Composed Image Retrieval (CIR), a user combines a query image with text to
describe their intended target. Existing methods rely on supervised learning of CIR models …

We argue that there are many notions of'similarity'and that models, like humans, should be
able to adapt to these dynamically. This contrasts with most representation learning …

Large-scale vision-language models (VLMs) like CLIP successfully find correspondences
between images and text. Through the standard deterministic map** process, an image or …

Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the
inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic …

Contrastively trained encoders have recently been proven to invert the data-generating
process: they encode each input, eg, an image, into the true latent vector that generated the …

In various domains such as surveillance and smart retail pedestrian retrieval centering on
person re-identification (Re-ID) plays a pivotal role. Existing Re-ID methodologies often …

As a promising field, Multi-Query Image Retrieval (MQIR) aims at searching for the
semantically relevant image given multiple region-specific text queries. Existing works …

Perceiving 3D structures from RGB images based on CAD model primitives can enable an
effective, efficient 3D object-based representation of scenes. However, current approaches …

Multimodal learning robust to missing modality has attracted increasing attention due to its
practicality. Existing methods tend to address it by learning a common subspace …

In e-commerce, products and micro-videos serve as two primary carriers. Introducing cross-
domain retrieval between these carriers can establish associations, thereby leading to the …