相关论文: Evaluating Attribute Confusion in Fashion Text-to-…

Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. Prior works directly evaluate the answering models by simply calculating the accuracy of predicted answers. However,…

Vector quantization (VQ) is a key technique in high-resolution and high-fidelity image synthesis, which aims to learn a codebook to encode an image with a sequence of discrete codes and then generate an image in an auto-regression manner.…

Text-to-Image (T2I) generation models have been widely adopted across various industries, yet are criticized for frequently exhibiting societal stereotypes. While a growing body of research has emerged to evaluate and mitigate these biases,…

Text-based Visual Question Answering~(TextVQA) aims to produce correct answers for given questions about the images with multiple scene texts. In most cases, the texts naturally attach to the surface of the objects. Therefore, spatial…

Evidence shows that text-to-image (T2I) models disproportionately reflect Western cultural norms, amplifying misrepresentation and harms to minority groups. However, evaluating cultural sensitivity is inherently complex due to its fluid and…

Rapid advances in text-to-image (T2I) generation have raised higher requirements for evaluation methodologies. Existing benchmarks center on objective capabilities and dimensions, but lack an application-scenario perspective, limiting…

Recent advances in text-driven image editing have been significant, yet the task of accurately evaluating these edited images continues to pose a considerable challenge. Different from the assessment of text-driven image generation,…

Accurately assessing image complexity (IC) is critical for computer vision, yet most existing methods rely solely on visual features and often neglect high-level semantic information, limiting their accuracy and generalization. We introduce…

Large Vision-Language Models (LVLMs) show promise for scientific applications, yet open-source models still struggle with Scientific Visual Question Answering (SVQA), namely answering questions about figures from scientific papers. A key…

A layout to image (L2I) generation model aims to generate a complicated image containing multiple objects (things) against natural background (stuff), conditioned on a given layout. Built upon the recent advances in generative adversarial…

This work addresses the challenge of quantifying originality in text-to-image (T2I) generative diffusion models, with a focus on copyright originality. We begin by evaluating T2I models' ability to innovate and generalize through controlled…

Existing efforts in text-based video question answering (TextVideoQA) are criticized for their opaque decisionmaking and heavy reliance on scene-text recognition. In this paper, we propose to study Grounded TextVideoQA by forcing models to…

Personalized diffusion models have shown remarkable success in Text-to-Image (T2I) generation by enabling the injection of user-defined concepts into diverse contexts. However, balancing concept fidelity with contextual alignment remains a…

Understanding images and text together is an important aspect of cognition and building advanced Artificial Intelligence (AI) systems. As a community, we have achieved good benchmarks over language and vision domains separately, however…

Vector quantization (VQ) transforms continuous image features into discrete representations, providing compressed, tokenized inputs for generative models. However, VQ-based frameworks suffer from several issues, such as non-smooth latent…

Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-faceted nature encompassing visual quality, semantic…

We study the visual quality judgments of human subjects on digital human avatars (sometimes referred to as "holograms" in the parlance of virtual reality [VR] and augmented reality [AR] systems) that have been subjected to distortions. We…

Since its appearance, Visual Question Answering (VQA, i.e. answering a question posed over an image), has always been treated as a classification problem over a set of predefined answers. Despite its convenience, this classification…

Learning to answer visual questions is a challenging task since the multi-modal inputs are within two feature spaces. Moreover, reasoning in visual question answering requires the model to understand both image and question, and align them…

The rapid advancement of text-to-image (T2I) models has increased the need for reliable human preference modeling, a demand further amplified by recent progress in reinforcement learning for preference alignment. However, existing…