cs papers | Gist.Science

Carbon Footprint and Carbon-Aware Selection of Document-Oriented, Relational, and Hybrid Object-Relational Storage for Image-Based Time-Series Workloads in Green IoT

This paper benchmarks the carbon footprint of MongoDB, PostgreSQL/TimescaleDB, and a PostgreSQL+MinIO hybrid for image-based time-series workloads in green IoT, revealing a resolution-dependent emission crossover where MongoDB is most sustainable for lower resolutions (up to 1440p) while the hybrid approach excels at higher resolutions (4K and above) due to decoupled storage, ultimately providing a carbon-aware decision framework for selecting storage architectures in sustainable building monitoring.

Alfa Ryano Yohannis, Alexander Waworuntu2026-09-04

💻 computer science

Synthetic personas as support for UX research

This paper proposes a Design Science Research-based procedure for integrating synthetic personas and AI-generated journeys into UX research to accelerate early-stage analysis and hypothesis formulation, while emphasizing the critical necessity of human oversight to mitigate bias and ensure empirical validity.

Ana Medrado, Carlos Eduardo Barbosa2026-09-04

💻 computer science

Multi-View Aggregation Transformer with Contrastive Learning for 3D Shape Retrieval

This paper proposes the Multi-View Aggregation Transformer (MVAT), a geometry-aligned framework that integrates hierarchical multi-view attention, specialized channel modulation modules, and an absolute cosine similarity metric to achieve state-of-the-art performance in 3D shape retrieval across multiple benchmarks.

Ze Zhang, Xiaojun Wu, Chenxi Wu, Guoyuan Liang2026-09-04

💻 computer science

DDAN: A Dense Dual-Attention Network with Physics-Informed Loss for Robust Multi-Type Optical Image Denoising

This paper introduces the Dense Dual-Attention Network (DDAN), a physics-informed deep learning framework that achieves state-of-the-art performance in robustly removing additive, multiplicative, and hybrid optical noise by integrating residual dense blocks with dual attention mechanisms and a specialized composite loss function.

Slim Rouabah, Rabah Abdelkader, Meziane Kaci, Salem Merabti, Hassane Ezziane, Youcef Naas2026-09-04

💻 computer science

Attention-Enhanced Temporal Convolutional Network for Continuous Word-Level Indian Sign Language Recognition

This paper proposes an attention-enhanced Temporal Convolutional Network (TCN) framework for continuous word-level Indian Sign Language recognition that leverages Mediapipe for landmark extraction and dilated convolutions to effectively capture spatiotemporal features, demonstrating superior performance compared to BiGRU, BiLSTM, and hybrid models on a specialized dataset.

Aswani Sivan¹, E. Chandra Eswaran¹2026-09-04

💻 computer science

CP-GOF: A Center-Object-Faithful and Age-Aware Training-Time Pruning Method for Gaussian Opacity Fields

The paper proposes CP-GOF, a training-time pruning method for Gaussian Opacity Fields that utilizes an age-aware, zero-cost exponential moving average importance measure and a center-protected mechanism to eliminate redundant Gaussians while preserving geometric fidelity and reducing storage overhead.

Yudai Wang, Dekang Yao, Liyan Qin, Yingao Liu, Fanggui Cai, Zhiying Cui, Zan Wang2026-09-04

💻 computer science

A Study on the Intelligent Recommendation of Interdisciplinary Student Innovation and Entrepreneurship Projects Integrating Knowledge Graphs and Graph Neural Networks

This paper proposes the KG-GNN-IPR model, which integrates knowledge graphs and graph neural networks to enhance the accuracy, robustness, and explainability of interdisciplinary student innovation and entrepreneurship project recommendations by effectively leveraging heterogeneous educational data and multi-hop skill complementarity.

Yanhong Wu¹, Lina Guo¹, Qi Li¹, Chengyu Sun2026-09-04

💻 computer science

Zero-Harm Feature Calibration and Adaptive Boundary Query for Tiny Object Detection

This paper proposes a joint optimization framework for tiny object detection that combines Zero-Harm Feature Calibration (ZFC) to prevent representation collapse and a Statistical Boundary Allocator (SBA) for adaptive query assignment, achieving state-of-the-art performance on AI-TOD-V2 and VisDrone-DET2019 while significantly reducing computational costs.

Yingying Zhai, Chang He, Zhi Wang, Zezheng Feng, Bin Wang, Xiaochun Yang2026-09-04

💻 computer science

ESLA: Empirical and Semantic Label Alignment for Multi-Source NER Transfer in Unlabeled Target Domains

The paper introduces ESLA, a framework that combines empirical prediction consistency and semantic representations to align heterogeneous Named Entity Recognition labels across multiple source domains, enabling effective cross-domain transfer to unlabeled target domains without requiring target-side training supervision.

Xiaobo Zhang, Congqing He, Ying He, Jian Peng, Dajie Fu, Tien-Ping Tan2026-09-04

💻 computer science

Multi-Scale Attention-Enhanced EfficientNet for Automated Gleason Grading of Prostate Cancer

This study introduces the Multi-Scale Efficient Attention Convolutional Network (MSEACN), a deep learning model based on EfficientNetB7 and dual attention mechanisms that achieves state-of-the-art performance with 97.69% accuracy and a 0.98 Cohen's Kappa score for the automated Gleason grading of prostate cancer using the PANDA dataset.

Olushola Olawuyi, Serestina Viriri, Samson Akinpelu2026-09-04

← Previous Next →