Cognition-Driven Structural Prior for Instance-Dependent Label Transition Matrix Estimation
The label transition matrix has emerged as a widely accepted method for mitigating label
noise in machine learning. In recent years, numerous studies have centered on leveraging …
noise in machine learning. In recent years, numerous studies have centered on leveraging …
HeadDiff: Exploring Rotation Uncertainty With Diffusion Models for Head Pose Estimation
In this paper, we propose a probabilistic regression diffusion model for head pose
estimation, dubbed HeadDiff, which typically addresses the rotation uncertainty, especially …
estimation, dubbed HeadDiff, which typically addresses the rotation uncertainty, especially …
From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos
Abstract Video-based Human-Object Interaction (HOI) recognition explores the intricate
dynamics between humans and objects, which are essential for a comprehensive …
dynamics between humans and objects, which are essential for a comprehensive …
Knowledge-Driven Framework for Anatomical Landmark Annotation in Laparoscopic Surgery
J Zhang, S Zhou, Y Wang, H Zhao… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Accurate and reliable annotation of anatomical landmarks in laparoscopic surgery remains a
challenge due to varying degrees of landmark visibility and changing shapes of human …
challenge due to varying degrees of landmark visibility and changing shapes of human …
Enhancing Situational Awareness in Surveillance: Leveraging Data Visualization Techniques for Machine Learning-based Video Analytics Outcomes
The pervasive deployment of surveillance cameras produces a massive volume of data,
requiring nuanced interpretation. This study thoroughly examines data representation and …
requiring nuanced interpretation. This study thoroughly examines data representation and …