Related papers: Representations of Text and Images Align From Laye…

Generic text embeddings are successfully used in a variety of tasks. However, they are often learnt by capturing the co-occurrence structure from pure text corpora, resulting in limitations of their ability to generalize. In this paper, we…

Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Existing methods often rely on complex 3D reconstruction…

Generating an image from a provided descriptive text is quite a challenging task because of the difficulty in incorporating perceptual information (object shapes, colors, and their interactions) along with providing high relevancy related…

Text-to-image synthesis is the task of generating images from text descriptions. Image generation, by itself, is a challenging task. When we combine image generation and text, we bring complexity to a new level: we need to combine data from…

The goal of this paper is to embed controllable factors, i.e., natural language descriptions, into image-to-image translation with generative adversarial networks, which allows text descriptions to determine the visual attributes of…

We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and…

As pre-trained text-to-image diffusion models have become a useful tool for image synthesis, people want to specify the results in various ways. This paper tackles training-free appearance transfer, which produces an image with the…

Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple source images without user specified masks…

An intuitive way to search for images is to use queries composed of an example image and a complementary text. While the first provides rich and implicit context for the search, the latter explicitly calls for new traits, or specifies how…

Text-to-image synthesis refers to computational methods which translate human written textual descriptions, in the form of keywords or sentences, into images with similar semantic meaning to the text. In earlier research, image synthesis…

Two modalities are often used to convey information in a complementary and beneficial manner, e.g., in online news, videos, educational resources, or scientific publications. The automatic understanding of semantic correlations between text…

Generative models for 3D object synthesis have seen significant advancements with the incorporation of prior knowledge distilled from 2D diffusion models. Nevertheless, challenges persist in the form of multi-view geometric inconsistencies…

With the rapid advancement of text-to-image (T2I) generation models, assessing the semantic alignment between generated images and text descriptions has become a significant research challenge. Current methods, including those based on…

Text-to-image diffusion models sometimes depict blended concepts in the generated images. One promising use case of this effect would be the nonword-to-image generation task which attempts to generate images intuitively imaginable from a…

Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of…

Image and sentence matching has made great progress recently, but it remains challenging due to the large visual-semantic discrepancy. This mainly arises from that the representation of pixel-level image usually lacks of high-level semantic…

While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to…

We present a model of visually-grounded language learning based on stacked gated recurrent neural networks which learns to predict visual features given an image description in the form of a sequence of phonemes. The learning task resembles…

We present an approach to infer a layer-structured 3D representation of a scene from a single input image. This allows us to infer not only the depth of the visible pixels, but also to capture the texture and depth for content in the scene…

Latent representations learned by neural networks often exhibit semantic structure, where concept similarity is reflected by geometric proximity in embedding space. However, comparing such spaces across models remains difficult: changes in…