Artificial Intelligence Medical Compendium

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

Showing 24,111 to 24,120 of 217,366 articles

Lost in State Space: Probing Frozen Mamba Representations

arXiv
Mamba's recurrent state h_t is, by construction, a compressed summary of every token seen so far. This raises a tempting hypothesis: if we extract token-level outputs y_t at fixed patch boundaries, we obtain semantic sentence summaries for free, with... read more 

MAEPose: Self-Supervised Spatiotemporal Learning for Human Pose Estimation on mmWave Video

arXiv
Millimetre-wave (mmWave) radar offers a more privacy-preserving alternative to RGB-based human pose estimation. However, existing methods typically rely on pre-extracted intermediate representations such as sparse point clouds or spectrogram images, ... read more 

Adaptive Geodesic Conformal Prediction for Egocentric Camera Pose Estimation

arXiv
Egocentric pose estimation for Augmented Reality (AR) and assistive devices requires not just accurate predictions but guaranteed uncertainty regions. Conformal prediction (CP) provides such guarantees without retraining, but we show that standard CP... read more 

Selfie-Capture Dynamics as an Auxiliary Signal Against Deepfakes and Injection Attacks for Mobile Identity Verification

arXiv
Mobile remote identity verification (RIdV) systems are exposed to attacks that manipulate or replace the facial video stream, including presentation attacks, real-time deepfakes, and video injection. Recent European requirements, including ETSI TS 11... read more 

DPU or GPU for Accelerating Neural Networks Inference -- Why not both? Split CNN Inference

arXiv
Video and image streaming on edge devices requires low latency. To address this, Neural Networks (NNs) are widely used, and prior work mainly focuses on accelerating them with single hardware units such as Graphics Processing Units (GPUs), Field Prog... read more 

Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization

arXiv
Learning meaningful representations from medical time series (MedTS) such as ECG or EEG signals is a critical challenge. These signals are often high-dimensional, variable-length and rife with noise. Existing self-supervised approaches, such as Maske... read more 

GAFSV-Net: A Vision Framework for Online Signature Verification

arXiv
Online signature verification (OSV) requires distinguishing skilled forgeries from genuine samples under high intra-class variability and with very few enrollment samples. Existing deep learning methods operate directly on raw temporal sequences, res... read more 

AIDA-ReID: Adaptive Intermediate Domain Adaptation for Generalizable and Source-Free Person Re-Identification

arXiv
Person re-identification (Re-ID) aims to match images of the same individual across non-overlapping camera views and remains challenging due to domain shifts caused by variations in illumination, background, camera characteristics, and population dis... read more 

Hyperspherical Forward-Forward with Prototypical Representations

arXiv
The Forward-Forward (FF) algorithm presents a compelling, bio-inspired alternative to backpropagation. However, while efficient in training, it has a computationally prohibitive inference process that requires a separate forward pass for every class ... read more 

The Kinematic Chain in Hindustani Classical Singing: An Exploratory Bioacoustic Pilot Study of Seated Posture and Vocal Quality.

Journal of voice : official journal of the Voice Foundation
Seated posture (Asana) is an important part of Hindustani classical vocal pedagogy, yet its biomechanical function remains under-researched. This exploratory pilot study applies "Kinematic Chain" theory-where proximal stability dictates distal mobili... read more