相关论文: FIDAVL: Fake Image Detection and Attribution using…

Image forgery localization aims to precisely identify tampered regions within images, but it commonly depends on costly pixel-level annotations. To alleviate this annotation burden, weakly supervised image forgery localization (WSIFL) has…

In computer vision, an entity such as an image or video is often represented as a set of instance vectors, which can be SIFT, motion, or deep learning feature vectors extracted from different parts of that entity. Thus, it is essential to…

In this paper, we introduce RAVID, the first framework for AI-generated image detection that leverages visual retrieval-augmented generation (RAG). While RAG methods have shown promise in mitigating factual inaccuracies in foundation…

In the fashion domain, there exists a variety of vision-and-language (V+L) tasks, including cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image captioning. They differ drastically in each individual…

Visual understanding is inherently contextual -- what we focus on in an image depends on the task at hand. For instance, given an image of a person holding a bouquet of flowers, we may focus on either the person such as their clothing, or…

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

A significant amount of redundancy exists between consecutive frames of a video. Object detectors typically produce detections for one image at a time, without any capabilities for taking advantage of this redundancy. Meanwhile, many…

Recently, fake audio detection has gained significant attention, as advancements in speech synthesis and voice conversion have increased the vulnerability of automatic speaker verification (ASV) systems to spoofing attacks. A key challenge…

Vision-language models (VLMs) are impactful in part because they can be applied to a variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We study $\textit{generative VLMs}$ that are trained for next-word…

Well-formed context aware image captions and tags in enterprise content such as marketing material are critical to ensure their brand presence and content recall. Manual creation and updates to ensure the same is non trivial given the scale…

In the rapidly evolving area of image synthesis, a serious challenge is the presence of complex artifacts that compromise perceptual realism of synthetic images. To alleviate artifacts and improve quality of synthetic images, we fine-tune…

The rapid iteration and widespread dissemination of deepfake technology have posed severe challenges to information security, making robust and generalizable detection of AI-generated forged images increasingly important. In this paper, we…

In machine learning, research has traditionally focused on model development, with relatively less attention paid to training data. As model architectures have matured and marginal gains from further refinements diminish, data quality has…

Large-scale contrastive vision-language pre-trained models provide the zero-shot model achieving competitive performance across a range of image classification tasks without requiring training on downstream data. Recent works have confirmed…

We propose Filtering Inversion (FINV), a learning framework and optimization process that predicts a renderable 3D object representation from one or few partial views. FINV addresses the challenge of synthesizing novel views of objects from…

Image scoring is a crucial task in numerous real-world applications. To trust a model's judgment, understanding its rationale is essential. This paper proposes a novel training method for Vision Language Models (VLMs) to generate not only…

Creating fake images and videos such as "Deepfake" has become much easier these days due to the advancement in Generative Adversarial Networks (GANs). Moreover, recent research such as the few-shot learning can create highly realistic…

This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images. Most existing similarity learning methods exacerbate the unexplainability by mapping each…

We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by curating a new…

Deepfake generation has witnessed remarkable progress, contributing to highly realistic generated images, videos, and audio. While technically intriguing, such progress has raised serious concerns related to the misuse of manipulated media.…