相关论文: Customizable ROI-Based Deep Image Compression
The sheer volume and size of histopathological images (e.g.,10^6 MPixel) underscores the need for faster and more accurate Regions-of-interest (ROI) detection algorithms. In this paper, we propose such an algorithm, which has four main…
The proliferation of AI-powered cameras in Intelligent Transportation Systems (ITS) creates a severe conflict between the need for rich visual data and the right to privacy. Existing privacy-preserving methods, such as blurring or…
Image customization, a crucial technique for industrial media production, aims to generate content that is consistent with reference images. However, current approaches conventionally separate image customization into position-aware and…
Telemedicine applications have recently received substantial potential and interest, especially after the COVID-19 pandemic. Remote experience will help people get their complex surgery done or transfer knowledge to local surgeons, without…
With the metaverse slowly becoming a reality and given the rapid pace of developments toward the creation of digital humans, the need for a principled style editing pipeline for human faces is bound to increase manifold. We cater to this…
Learning-based image compression was shown to achieve a competitive performance with state-of-the-art transform-based codecs. This motivated the development of new learning-based visual compression standards such as JPEG-AI. Of particular…
Low-rank Adaptation (LoRA) models have revolutionized the personalization of pre-trained diffusion models by enabling fine-tuning through low-rank, factorized weight matrices specifically optimized for attention layers. These models…
Recently, large language models (LLMs) have advanced recommendation systems (RSs), and recent works have begun to explore how to integrate LLMs into industrial RSs. While most approaches deploy LLMs offline to generate and pre-cache…
Manual prescription of the field of view (FOV) by MRI technologists is variable and prolongs the scanning process. Often, the FOV is too large or crops critical anatomy. We propose a deep-learning framework, trained by radiologists'…
Low-Rank Adaptation (LoRA) has emerged as a widely adopted technique in text-to-image models, enabling precise rendering of multiple distinct elements, such as characters and styles, in multi-concept image generation. However, current…
Compositional Customized Image Generation aims to customize multiple target concepts within generation content, which has gained attention for its wild application. Existing approaches mainly concentrate on the target entity's appearance…
In this paper, we aim to tackle the task of semi-supervised video object segmentation across a sequence of frames where only the ground-truth segmentation of the first frame is provided. The challenges lie in how to online update the…
Memory-efficient personalization is critical for adapting text-to-image diffusion models while preserving user privacy and operating within the limited computational resources of edge devices. To this end, we propose a selective…
Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…
Cryo-electron tomography (cryo-ET) enables high resolution, three-dimensional reconstruction of biological structures, including membranes and membrane proteins. Identification of regions of interest (ROIs) is central to scientific imaging,…
High-dimensional tissue imaging generates highly complex 3D data containing multiple biomarkers, making it challenging to identify biologically relevant regions without an expert user specifying manual labels for regions of interest. We…
Vision-Language Models (VLMs) facilitate medical visual question answering (MedVQA) by jointly interpreting images and text. However, existing models typically depend on large architectures and closed-set answers, which limits their…
Besides a 3D mesh, Human Mesh Recovery (HMR) methods usually need to estimate a camera for computing 2D reprojection loss. Previous approaches may encounter the following problem: both the mesh and camera are not correct but the combination…
Inter-subject registration of cortical areas is necessary in functional imaging (fMRI) studies for making inferences about equivalent brain function across a population. However, many high-level visual brain areas are defined as peaks of…
The deployment of Machine Learning models intraoperatively for tissue characterisation can assist decision making and guide safe tumour resections. For image classification models, pixel attribution methods are popular to infer…