Related papers: Language Guided Local Infiltration for Interactive…
The advent of Large Language Models (LLMs) heralds a pivotal shift in online user interactions with information. Traditional Information Retrieval (IR) systems primarily relied on query-document matching, whereas LLMs excel in comprehending…
Detecting spliced images is one of the emerging challenges in computer vision. Unlike prior methods that focus on detecting low-level artifacts generated during the manipulation process, we use an image retrieval approach to tackle this…
Multimodal Large Language Models (MLLMs) excel in vision-language tasks such as image captioning but remain prone to object hallucinations, where they describe objects that do not appear in the image. To mitigate this, we propose LISA, a…
Image restoration, which aims to retrieve and enhance degraded images, is fundamental across a wide range of applications. While conventional deep learning approaches have notably improved the image quality across various tasks, they still…
Interactive garment retrieval (IGR) aims to retrieve a target garment image based on a reference garment image along with user feedback on what to change on the reference garment. Two IGR tasks have been studied extensively: text-guided…
In this paper, we introduce LDGen, a novel method for integrating large language models (LLMs) into existing text-to-image diffusion models while minimizing computational demands. Traditional text encoders, such as CLIP and T5, exhibit…
Large-scale text-to-image diffusion models have been a ground-breaking development in generating convincing images following an input text prompt. The goal of image editing research is to give users control over the generated images by…
With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the development of large…
Large language models ($\textbf{LLMs}$) have emerged as a powerful method for discovery. Instead of utilizing numerical data, LLMs utilize associated variable $\textit{semantic metadata}$ to predict variable relationships. Simultaneously,…
Real-world image restoration (IR) is inherently complex and often requires combining multiple specialized models to address diverse degradations. Inspired by human problem-solving, we propose AgenticIR, an agentic system that mimics the…
Instruction-guided image editing offers an intuitive way for users to edit images with natural language. However, diffusion-based editing models often struggle to accurately interpret complex user instructions, especially those involving…
Large vision-language models (LVLMs) often hallucinate when language priors dominate weak or ambiguous visual evidence. Existing contrastive decoding methods mitigate this problem by comparing predictions from the original image with those…
Diffusion models have shown impressive performance in many domains. However, the model's capability to follow natural language instructions (e.g., spatial relationships between objects, generating complex scenes) is still unsatisfactory. In…
Both masked image modeling (MIM) and natural language supervision have facilitated the progress of transferable visual pre-training. In this work, we seek the synergy between two paradigms and study the emerging properties when MIM meets…
Effective incident response (IR) is critical for mitigating cyber threats, yet security teams are overwhelmed by alert fatigue, high false-positive rates, and the vast volume of unstructured Cyber Threat Intelligence (CTI) documents. While…
Image Manipulation Localization (IML) aims to identify edited regions in an image. However, with the increasing use of modern image editing and generative models, many manipulations no longer exhibit obvious low-level artifacts. Instead,…
Human thinking requires the brain to understand the meaning of language expression and to properly organize the thoughts flow using the language. However, current natural language processing models are primarily limited in the word…
Text-to-image person re-identification (ReID) retrieves pedestrian images according to textual descriptions. Manually annotating textual descriptions is time-consuming, restricting the scale of existing datasets and therefore the…
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adopt the late-fusion strategy to combine visual and language…
An image classifier may depend on incidental features stemming from a strong correlation between the feature and the classification target in the training dataset. Recently, Last Layer Retraining (LLR) with group-balanced datasets is shown…