Graph convolutional network (GCN)-based methods have shown strong performance in 3D human pose estimation by leveraging the natural graph structure of the human skeleton. However, their local receptive field limits their ability to capture long-range dependencies essential for handling occlusions and depth ambiguities. They also exhibit spectral bias, which prioritizes low-frequency components while struggling to model high-frequency details. In this paper, we introduce PoseKAN, an adaptive graph Kolmogorov-Arnold Network (KAN), framework that extends KANs to graph-based learning for 2D-to-3D pose lifting from a single image. Unlike GCNs that use fixed activation functions, KANs employ learnable functions on graph edges, allowing data-driven, adaptive feature transformations. This enhances the model's adaptability and expressiveness, making it more expressive in learning complex pose variations. Our model employs multi-hop feature aggregation, ensuring the body joints can leverage information from both local and distant neighbors, leading to improved spatial awareness. It also incorporates residual PoseKAN blocks for deeper feature refinement, and a global response normalization for improved feature selectivity and contrast. Extensive experiments on benchmark datasets demonstrate the competitive performance of our model against state-of-the-art methods.
YOLO with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection with trustworthy multimodal AI in computer vision perception
University of Bath（巴斯大学）；Zhejiang University（浙江大学）
LAKAN: Landmark-assisted Adaptive Kolmogorov-Arnold Network for Face Forgery Detection
School of Cyber Science and Technology, University of Science and Technology of China（计算机科学与技术学院，中国科学技术大学）；Anhui Province Key Laboratory of Digital Security（安徽省数字安全重点实验室）
KANO: Kolmogorov-Arnold Neural Operator for Image Super-Resolution
Southeast University（东南大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空信息研究所）；College of Resources and Environment, University of Chinese Academy of Sciences（中国科学院大学资源与环境学院）；Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK（格勒诺布尔阿尔卑斯大学、法国国家科研机构（Inria）、法国国家科学研究中心（CNRS）、格勒诺布尔INP、LJK）
PostHoc FREE Calibrating on Kolmogorov Arnold Networks
Institute for Clarity in Documentation（文献研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗康校区）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）
KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements
the University of New Orleans（新奥尔良大学）；Naval Research Laboratory（美国海军研究实验室）；US Army Corps of Engineers, Engineer Research and Development Center（美国陆军工程兵团工程研究与发展中心）
QuKAN: A Quantum Circuit Born Machine approach to Quantum Kolmogorov Arnold Networks
Department of Computer Science and Research Initiative QC-AI, RPTU Kaiserslautern-Landau（计算机科学系和QC-AI研究计划，鲁尔-帕绍大学（RPTU）凯斯贝赫-劳恩道分校）；Embedded Intelligence, German Research Center for Artificial Intelligence (DFKI)（嵌入式智能，德国人工智能研究中心（DFKI））；Department of Physics, RPTU Kaiserslautern-Landau（物理系，鲁尔-帕绍大学（RPTU）凯斯贝赫-劳恩道分校）
本研究利用量子电路 Born 机（QCBM）在混合与全量子形式下实现了 KAN 架构，通过预训练残差函数发挥参数化量子电路的表示能力，验证了 QuKAN 架构的可行性、可解释性与性能。
