3D SOC-Net: Deep 3D reconstruction network based on self-organizing clustering mapping

Article Computer Science, Artificial Intelligence

Synchronization of Delayed Complex Networks on Time Scales via Aperiodically Intermittent Control Using Matrix-Based Convex Combination Method

Peng Wan et al.

Summary: This article reconsidered the synchronization problem of linear complex networks with time-varying delay on time scales and proposed aperiodically intermittent control schemes for different types of time scales. By using a common Lyapunov function and a special Lyapunov function with time-varying coefficients, synchronization of linear delayed complex networks onto an isolated node was successfully achieved on special and general time scales.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

A high-quality voxel 3D reconstruction system for large scenes based on the branch and bound method

Junyi Hou et al.

Summary: This paper proposes a high-quality voxel 3D reconstruction system for large scenes based on the branch and bound method, which obtains high-precision 3D models by optimizing camera pose and utilizing the truncated signed distance function.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Enhancing single-view 3D mesh reconstruction with the aid of implicit surface learning

George Fahim et al.

Summary: The study proposes a mesh-based single-view object reconstruction model enhanced with additional implicit surface learning, leading to lower surface-to-surface error compared to using an explicit branch alone. The hybrid method outperforms state-of-the-art mesh reconstruction methods and compares favorably to prior work incorporating a hybrid approach. Despite being trained with synthetic images, it generalizes well to real-world images.

IMAGE AND VISION COMPUTING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Multiple Kernel k-Means Clustering by Selecting Representative Kernels

Yaqiang Yao et al.

Summary: This article proposes a method to optimize multiple kernel k-means clustering through subset selection, using an alternating minimization algorithm to optimize the combination coefficients of the selected kernels. It improves clustering performance and efficiency by effectively selecting representative kernels and reducing redundancy.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Active contour model driven by Self Organizing Maps for image segmentation

Bin Dong et al.

Summary: An unsupervised active contour model with Self Organizing Maps (SOM) is proposed in this paper, which effectively segments images with intensity inhomogeneity.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Adaptive Graph Convolution for Point Cloud Analysis

Haoran Zhou et al.

Summary: The proposed Adaptive Graph Convolution (AdaptConv) generates adaptive kernels for points based on dynamically learned features, improving the flexibility of point cloud convolutions and effectively capturing diverse relations between points from different semantic parts. Extensive qualitative and quantitative evaluations demonstrate that the method outperforms state-of-the-art approaches in point cloud classification and segmentation.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Article Computer Science, Artificial Intelligence