Artificial Intelligence Medical Compendium

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

Showing 251 to 260 of 212,780 articles

MuViSeg: Multi-View Segment Correspondences from Dense Geometry Priors

arXiv Jul 20, 2026
Classical image correspondence is solved at the level of sparse keypoints or dense pixels, but the systems that consume these matches - object-level mapping, topological navigation, scene-graph maintenance - reason about whole objects. Recent work na... read more 
Computer Vision and Pattern Recognition

Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement

arXiv Jul 20, 2026
Monocular geometry estimation has recently achieved impressive performance across diverse scenes. However, state-of-the-art models still face notable distortion in local 3D structure, especially in fine details, like thin structures and small objects... read more 
Computer Vision and Pattern Recognition

MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement

arXiv Jul 20, 2026
Monocular geometry estimation has recently achieved impressive performance across diverse scenes. However, state-of-the-art models still face notable distortion in local 3D structure, especially in fine details, like thin structures and small objects... read more 
Computer Vision and Pattern Recognition

Keyframe-Anchored Identity Preservation for Sequential-Action Video Generation

arXiv Jul 20, 2026
Identity-preserving text-to-video generation aims to synthesize a video that accurately follows a textual description while maintaining the recognizability of a user-specified subject throughout. The IPVG26 challenge extends this framework from a sin... read more 
Computer Vision and Pattern Recognition cs.MM

Remote Awareness of Seafloor Images Collected by AUVs over Low-Bandwidth Communication Links

arXiv Jul 20, 2026
This paper introduces a method for real-time processing and transmission of autonomous underwater vehicle (AUV) imagery over low-bandwidth communication links. It leverages artificial intelligence (AI) techniques to identify a set of images that best... read more 
Information Retrieval cs.LG cs.RO eess.IV

SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokens

arXiv Jul 20, 2026
Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These adaptations, however, are largely general-purpose models that treat MRI... read more 
Computer Vision and Pattern Recognition

Benchmarking NACTI Species Recognition in Long-Tailed Regimes

arXiv Jul 20, 2026
As with most ``in the wild'' collections of the natural world, the North America Camera Trap Images (NACTI) dataset exhibits long-tailed class imbalance, with the largest class covering over 50% of its 3.7M images. Building on the PyTorch Wildlife mo... read more 
Computer Vision and Pattern Recognition

When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry

arXiv Jul 20, 2026
Existing image manipulation localization (IML) methods rely heavily on 2D forensic cues, such as low-level artifacts, noise traces, and semantic inconsistencies in the manipulated image. While effective in many cases, these cues become much less disc... read more 
Computer Vision and Pattern Recognition

Anticipate Before Acting: Future-State-Conditioned Vision-Language Navigation

arXiv Jul 20, 2026
End-to-end vision-language navigation (VLN) with causal vision-language models can map instructions and egocentric observations directly to actions, but standard behavior cloning supervises only the next action and does not explicitly train the polic... read more 
Computer Vision and Pattern Recognition cs.AI

SEE: Structure-aware Exploring \& Exploiting for Long-horizon GUI Agent Trajectory Synthesis

arXiv Jul 20, 2026
Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack of high-coverage, long-horizon interaction trajectories collected from element-rich ... read more 
Machine Learning
Popular Topics
Recent Journals