Latest AI and machine learning research in smoking & tobacco for healthcare professionals.
Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most app...
Medical images are essential for diagnosis, treatment planning, and research, but their quality is o...
Medical image segmentation remains challenging due to limited annotations for training, ambiguous an...
Whole slide images, with their gigapixel-scale panoramas of tissue samples, are pivotal for precise ...
Vision Transformers rely on positional embeddings and class tokens that encode fixed spatial priors....
Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generati...
Image Copy Detection (ICD) aims to identify manipulated content between image pairs through robust f...
Black-box adversarial attacks on Large Vision-Language Models (LVLMs) are challenging due to missing...
Generating diagnostic text from histopathology whole slide images (WSIs) is challenging due to the g...
Street-view image attribute classification is a vital downstream task of image classification, enabl...
Whole-slide images (WSIs) from cancer patients contain rich information that can be used for medical...
The study of histopathological subtypes is valuable for the personalisation of effective treatment s...
Pathology foundation models (PFMs) have enabled robust generalization in computational pathology thr...
We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual toke...
Spatial transcriptomics (ST) provides spatially resolved measurements of gene expression, enabling c...
Pre-trained diffusion models excel at generating high-quality images but remain inherently limited b...
Background: Liver cancer primarily develops in patients with chronic liver disease (CLD), yet most c...
Digital histopathology whole slide images (WSIs) provide gigapixel-scale high-resolution images that...
While multimodal large language models (MLLMs) have made substantial progress in single-image spatia...
While multimodal large language models (MLLMs) have made substantial progress in single-image spatia...
Rapid building damage assessment is critical for post-disaster response. Damage classification model...