Artificial Intelligence Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 38,811 to 38,820 of 223,469 articles

HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images

arXiv
Recovering high-fidelity 3D hand geometry from images is a critical task in computer vision, holding significant value for domains such as robotics, animation and VR/AR. Crucially, scalable applications demand both accuracy and deployment flexibility... read more 

HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images

arXiv
Recovering high-fidelity 3D hand geometry from images is a critical task in computer vision, holding significant value for domains such as robotics, animation and VR/AR. Crucially, scalable applications demand both accuracy and deployment flexibility... read more 

UW-VOS: A Large-Scale Dataset for Underwater Video Object Segmentation

arXiv
Underwater Video Object Segmentation (VOS) is essential for marine exploration, yet open-air methods suffer significant degradation due to color distortion, low contrast, and prevalent camouflage. A primary hurdle is the lack of high-quality training... read more 

SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision

arXiv
3D Gaussian Splatting (3DGS) enables real-time, photorealistic novel view synthesis, making it a highly attractive representation for model-based video tracking. However, leveraging the differentiability of the 3DGS renderer "in the wild" remains not... read more 

A^3: Towards Advertising Aesthetic Assessment

arXiv
Advertising images significantly impact commercial conversion rates and brand equity, yet current evaluation methods rely on subjective judgments, lacking scalability, standardized criteria, and interpretability. To address these challenges, we prese... read more 

Minimal Sufficient Representations for Self-interpretable Deep Neural Networks

arXiv
Deep neural networks (DNNs) achieve remarkable predictive performance but remain difficult to interpret, largely due to overparameterization that obscures the minimal structure required for interpretation. Here we introduce DeepIn, a self-interpretab... read more 

HAM: A Training-Free Style Transfer Approach via Heterogeneous Attention Modulation for Diffusion Models

arXiv
Diffusion models have demonstrated remarkable performance in image generation, particularly within the domain of style transfer. Prevailing style transfer approaches typically leverage pre-trained diffusion models' robust feature extraction capabilit... read more 

LGEST: Dynamic Spatial-Spectral Expert Routing for Hyperspectral Image Classification

arXiv
Deep learning methods, including Convolutional Neural Networks, Transformers and Mamba, have achieved remarkable success in hyperspectral image (HSI) classification. Nevertheless, existing methods exhibit inflexible integration of local-global repres... read more 

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

arXiv
Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in high-stakes scenarios such as autonomous driving and medical image analys... read more 

AD-Reasoning: Multimodal Guideline-Guided Reasoning for Alzheimer's Disease Diagnosis

arXiv
Alzheimer's disease (AD) diagnosis requires integrating neuroimaging with heterogeneous clinical evidence and reasoning under established criteria, yet most multimodal models remain opaque and weakly guideline-aligned. We present AD-Reasoning, a mult... read more