Related papers: Selectively Informative Description can Reduce Und…
Text-to-Image (T2I) generation is enabling new applications that support creators, designers, and general end users of productivity software by generating illustrative content with high photorealism starting from a given descriptive text as…
Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across…
Artificial neural networks typically struggle in generalizing to out-of-context examples. One reason for this limitation is caused by having datasets that incorporate only partial information regarding the potential correlational structure…
In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…
Text-to-image generation and image captioning are recently emerged as a new experimental paradigm to assess machine intelligence. They predict continuous quantity accompanied by their sampling techniques in the generation, making evaluation…
The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of…
Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under…
In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet…
Text-to-image diffusion models have achieved remarkable progress in generating diverse and realistic images from textual descriptions. However, they still struggle with personalization, which requires adapting a pretrained model to depict…
Sequence-based recommendations models are driving the state-of-the-art for industrial ad-recommendation systems. Such systems typically deal with user histories or sequence lengths ranging in the order of O(10^3) to O(10^4) events. While…
Person re-identification (reID) aims to match person images to retrieve the ones with the same identity. This is a challenging task, as the images to be matched are generally semantically misaligned due to the diversity of human poses and…
In this paper we deal with the task of Disturbing Image Detection (DID), exploiting knowledge encoded in Large Multimodal Models (LMMs). Specifically, we propose to exploit LMM knowledge in a two-fold manner: first by extracting generic…
We propose a text-to-image generation algorithm based on deep neural networks when text captions for images are unavailable during training. In this work, instead of simply generating pseudo-ground-truth sentences of training images using…
This paper examines the limitations of advanced text-to-image models in accurately rendering unconventional concepts which are scarcely represented or absent in their training datasets. We identify how these limitations not only confine the…
In linear inverse problems, the goal is to recover a target signal from undersampled, incomplete or noisy linear measurements. Typically, the recovery relies on complex numerical optimization methods; recent approaches perform an unfolding…
Image quality evaluation accurately is vital in developing image stitching algorithms as it directly reflects the algorithms progress. However, commonly used objective indicators always produce inconsistent and even conflicting results with…
In the context of temporal image forensics, it is not evident that a neural network, trained on images from different time-slots (classes), exploits solely image age related features. Usually, images taken in close temporal proximity (e.g.,…
Performance of trimap-free image matting methods is limited when trying to decouple the deterministic and undetermined regions, especially in the scenes where foregrounds are semantically ambiguous, chromaless, or high transmittance. In…
The advent of accessible Generative AI tools enables anyone to create and spread synthetic images on social media, often with the intention to mislead, thus posing a significant threat to online information integrity. Most existing…
Pose variation is one of the key factors which prevents the network from learning a robust person re-identification (Re-ID) model. To address this issue, we propose a novel person pose-guided image generation method, which is called the…