AV-FOS: Transformer-Based Audio-Visual Multimodal Interaction Style Recognition for Children with Autism Using the Revised Family Observation Schedule 3rd Edition (FOS-R-III)

Information Science, Computer Science, Artificial Intelligence, Medicine, Pediatrics, Psychiatry, Clinical Psychology, Medical Imaging,
autism spectrum disorder   challenging behaviors   multimodal learning   self-supervised learning   video understanding   interaction style recognition   clinical observation  

1. Background: Clinical Challenges and Technological Prospects in Behavior Monitoring of Children with Autism Autism Spectrum Disorder (ASD, autism) is a lifelong neurodevelopmental disorder. In recent years, the prevalence of autism in the United States has risen rapidly, with current epidemiological data indicating that one in every 36 children i...

Curriculum-Guided Self-Supervised Representation Learning of Dynamic Heterogeneous Networks

Information Science, Computer Science, Artificial Intelligence,
network embedding   transformer   dynamic heterogeneous network embedding   curriculum learning   self-supervised learning  

Academic Background In the real world, network data (such as social networks, citation networks, etc.) often contain multiple types of nodes and edges, and these network structures evolve dynamically over time. To better analyze these complex networks, researchers have proposed network embedding techniques, which aim to represent nodes and edges in...

Continual Learning of Conjugated Visual Representations through Higher-Order Motion Flows

Information Science, Computer Science, Artificial Intelligence,
continual learning   motion flows   self-supervised learning   feature extraction   higher-order motion   visual representations   online learning  

Continual Learning of Conjugated Visual Representations through Higher-Order Motion Flows: A Study on the CMOSFET Model Academic Background In the fields of artificial intelligence and computer vision, continual learning from continuous visual data streams has long been a challenge. Traditional machine learning methods typically rely on the assumpt...

Self-Supervised Feature Detection and 3D Reconstruction for Real-Time Neuroendoscopic Guidance

Self-Supervised Feature Detection and 3D Reconstruction for Real-Time Neuroendoscopic Guidance

Information Science, Artificial Intelligence, Medicine, Neurosurgery, Medical Imaging, Life Sciences, Bioengineering,
neuroendoscopy   3D reconstruction   self-supervised learning   feature detection   real-time navigation  

Research on Real-Time 3D Reconstruction and Navigation in Neuroendoscopy Based on Self-Supervised Learning Academic Background Neuroendoscopic surgery, as a minimally invasive surgical technique, is widely used in the treatment of deep brain lesions, such as endoscopic third ventriculostomy (ETV), choroid plexus cauterization, and cyst fenestration...

Self-Supervised Shutter Unrolling with Events

Engineering, Electrical Engineering, Information Science, Electronic Information, Computer Science, Artificial Intelligence,
rolling shutter correction   event camera   self-supervised learning   continuous-time global shutter   video recovery  

Event Camera-Based Self-Supervised Shutter Unrolling Method Research Background and Problem Statement In the field of computer vision, recovering undistorted global shutter (GS) videos from rolling shutter (RS) images has been a highly challenging problem. RS cameras, due to their row-by-row exposure mechanism, are prone to spatial distortions (e.g...