Estimation Task
Estimation tasks, broadly defined as the process of inferring unknown parameters or values from available data, are central to numerous scientific and engineering disciplines. Current research emphasizes developing robust and efficient estimation methods across diverse data types and model complexities, focusing on techniques like Bayesian frameworks, deep neural networks (including graph convolutional networks), and simulation-based inference. These advancements are driving improvements in areas ranging from medical diagnosis and robotics to power systems optimization and material science, enabling more accurate predictions and informed decision-making.
Papers
COBRA -- COnfidence score Based on shape Regression Analysis for method-independent quality assessment of object pose estimation from single images
Panagiotis Sapoutzoglou, George Giapitzakis, George Terzakis, Maria Pateraki
Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference
Zhe Zhang, Ryumei Nakada, Linjun Zhang
IFFNeRF: Initialisation Free and Fast 6DoF pose estimation from a single image and a NeRF model
Matteo Bortolon, Theodore Tsesmelis, Stuart James, Fabio Poiesi, Alessio Del Bue
Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimation
Jun Yu, Gongpeng Zhao, Yongqi Wang, Zhihong Wei, Yang Zheng, Zerui Zhang, Zhongpeng Cai, Guochen Xie, Jichao Zhu, Wangyuan Zhu