Latest AI and machine learning research in smoking & tobacco for healthcare professionals.
Hepatic vessels in computed tomography scans often suffer from image fragmentation and noise inter...
It is vital to recover 3D geometry from multi-view RGB images in many 3D computer vision tasks. Th...
Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potenti...
Gigapixel image analysis, particularly for whole slide images (WSIs), often relies on multiple ins...
The visual understanding are often approached from 3 granular levels: image, patch and pixel. Visu...
Although facial landmark detection (FLD) has gained significant progress, existing FLD methods sti...
The generation of medical images presents significant challenges due to their high-resolution and ...
Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal sam...
This article presents a novel approach to improving the accuracy of 360-degree perceptual image qu...
The emergence of large multimodal models (LMMs) has brought significant advancements to pathology....
Classifying large images with small or tiny regions of interest (ROI) is challenging due to comput...
This paper presents a comprehensive exploration of the phenomenon of data redundancy in video unde...
Recently, cross-spectral image patch matching based on feature relation learning has attracted ext...
Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically uses Class Activa...
We tackle the problem of localizing traffic cameras within a 3D reference map and propose a novel ...
Segmentation of ultra-high resolution (UHR) images is a critical task with numerous applications, ...
Document classification is considered a critical element in automated document processing systems....
Physical adversarial attacks in driving scenarios can expose critical vulnerabilities in visual pe...
Autonomous vehicles (AVs) increasingly use DNN-based object detection models in vision-based perce...
We focus on tertiary lymphoid structure (TLS) semantic segmentation in whole slide image (WSI). Un...
Finetuning-free personalized image generation can synthesize customized images without test-time f...