💻 Category

cs

2786 papers

💻 computer science

3D Surface Reconstruction from Point Clouds via Explicitly Geometrically Weighted RBF Neural Interpolation

This paper proposes a novel 3D surface reconstruction framework that enhances Radial Basis Function (RBF) neural interpolation by explicitly embedding geometric altitude weights into the activation matrix and utilizing K-means clustering with compactly supported kernels to achieve high-accuracy, computationally efficient reconstruction of large-scale unstructured point clouds.

Mohamed Cherkaoui Eddeqaqi2026-08-28
💻 computer science

An analysis of university ranking systems using an unsupervised machine learning-based ranking framework

This study proposes an unsupervised machine learning framework utilizing Principal Component Analysis and Factor Analysis to validate and improve the transparency and stability of university rankings by deriving latent factors and applying balanced weights, ultimately demonstrating that while individual ranks fluctuate, the overall distributional patterns of top Australian universities remain consistent with established systems like THE and QS.

Yipeng Zhu, Yuanxi Peng, Mengtong Li, Rohitash Chandra2026-08-28
💻 computer science

Where Abstention Lives: A Pre-Registered Four-Way Comparison of Abstention Interfaces in a Small Language Model with Versioned Memory

This pre-registered study demonstrates that in a small language model with versioned memory, implementing abstention via a separate binary head significantly outperforms vocabulary tokens and memory slots by decoupling the decision from the generation softmax, thereby making the ability to say "I don't know" learnable even with limited accuracy margins.

Maximiliano Rodrigo Speranza2026-08-28
💻 computer science

A Lightweight Context-Aware Detector for Small and Occluded Targets in Aerial Power-Line Inspection

The paper proposes LiteFocus-DEIM, a lightweight context-aware detector that integrates a Gated Attention Block, Adaptive Feature Fusion, and a Focused Scale Flow Network to effectively detect small and occluded safety gear in aerial power-line inspections, achieving high accuracy and efficiency on both a custom HAD dataset and the VisDrone2019 benchmark.

Dahua Li, Junru Shi, Xuan Li, Xueying Hu, Qiang Gao, Dong Li2026-08-28
💻 computer science

Human action recognition based on cascade graph convolutional network

This paper proposes a Cascade Graph Convolutional Network (CGCN) that utilizes a Motion-Aware Hierarchical Adjacency Matrix to dynamically model joint correlations and a stepwise cascaded architecture to progressively classify actions with increasing complexity, thereby achieving a superior balance between recognition accuracy and computational efficiency across multiple datasets.

Mengai Yan, Jianying Xiong, Ben Huang, Jiabin Chen, Leiyue Yao2026-08-28
💻 computer science

2D Rotary Position Embedding for Scene Text Recognition with Transformers

This paper introduces \method{}, a parameter-free adaptation of 2D Rotary Position Embedding for Scene Text Recognition that addresses the limitations of existing methods by allocating dimensions anisotropically to match text aspect ratios and extending rotary coupling to encoder-decoder cross-attention, thereby significantly improving accuracy on curved, rotated, and perspective-distorted text layouts.

Zobeir Raisi2026-08-27
💻 computer science

A PRISMA-Guided Critical Review of CNN, Transformer, and Hybrid Object Detection Architectures for Autonomous Driving

This PRISMA-guided critical review of 142 studies on CNN, Transformer, and hybrid object detection architectures for autonomous driving identifies significant gaps in real-world deployment evidence and introduces the AVOD-DRF framework to enable reproducible, evidence-based selection of detectors based on operational readiness rather than benchmark performance alone.

Girija G. Chiddarwar, Madhav J. Salunkhe, Yogesh G. Joshi, Rahul G. Deshmukh, Swapnil Yashavant Gadgune, Suraj Rajaram N (…)2026-08-27