cs papers | Gist.Science

CBAM-Enhanced MaxViT-Tiny for Gastrointestinal Endoscopy Image Classification: Robustness, Explainability, and External Validation

This study proposes a CBAM-enhanced MaxViT-Tiny model for 8-class gastrointestinal endoscopy image classification that achieves high accuracy and explainability on clean data but demonstrates significant vulnerability to adversarial attacks and poor cross-attack generalization, highlighting the critical need for adversarial training and multi-center validation before clinical deployment.

Sadek Al Prince, Israt Fatema Shorna, Md Mehedi Hasan, Mohammad Ahanaf Akif, Aziz Misher Mishu, Gazi Mehraj Sakib2026-11-09

💻 computer science

Multi-Objective Constrained Deep Q-Networks for Supplier Selection and Order Allocation in Sustainable Supply Chains

This paper introduces ParetoShield-Q, a multi-objective constrained deep Q-learning framework that optimizes sustainable supplier selection and order allocation by integrating preference conditioning, distributional tail-risk management, and feasibility oracles within a Markov decision process, validated through extensive quantitative analysis on public demand and supplier datasets.

Miao Li, Zihan Wang, Xuwen Cao, Yangcui Weng2026-11-09

💻 computer science

Reliability of Urdu–Arabic Abusive Language Detection with Cross- Lingual Transformers and Explainable AI

This study evaluates a bilingual XLM-RoBERTa model for detecting abusive language in Urdu and Arabic, revealing that while joint training yields high accuracy, the system lacks robust cross-lingual transfer and context sensitivity, underscoring the necessity of targeted reliability tests over aggregate metrics alone.

Malik Daler Ali Awan, Farhan Ansari, Sunnia Ikram, Nadia Khan, Amna Ikram, Najah Alsubaie, Hadia Saeed2026-11-09

💻 computer science

Does Graph Attention Improve Weighted-Polling Classification on the Pima Indians Diabetes Dataset? A Nested Cross-Validation Comparison with Standard Models

A nested cross-validation study on the Pima Indians Diabetes Dataset demonstrates that a tuned GATv2 weighted-polling classifier does not outperform standard machine learning models or raw-feature weighted polling, suggesting that graph attention offers no significant accuracy benefit for this specific small clinical tabular dataset.

Farid Morsidi2026-11-09

💻 computer science

MC-SAM: A Stability-Constrained Coupled Adaptation Framework for SAM in Camouflaged Scene Segmentation

MC-SAM introduces a stability-constrained coupled adaptation framework for the Segment Anything Model that utilizes a shared doubly stochastic prior and Sinkhorn normalization to effectively fuse visual and textual cues, thereby significantly improving camouflaged object segmentation performance while preserving weak foreground features.

Zihua Liu, Yonghao Wu, Jiajie Murong, Chang Liu2026-11-09

💻 computer science

AMFD-YOLO: An Adaptive Multi-scale Feature Modulation Network for Small Object Detection in Airport Surface Surveillance

This paper proposes AMFD-YOLO, an enhanced YOLO11-based network incorporating a Multiscale Occlusion-aware Attention Module, a Feature Distribution Modulation activation function, and a P2 detection layer to significantly improve the accuracy of detecting small and occluded airport surface targets under complex environmental conditions.

Tian Luan, Fan Yang, Huanxia Wei, Weijun Pan2026-11-09

💻 computer science

Adaptive Hard Negative Mining for Fine Grained Vision Language Understanding A Negative Result and Analysis

This paper demonstrates that adaptive hard negative mining fails to improve upon fixed hard negative training on the SPEC benchmark due to the dataset's uniformly hard candidate sets, while also revealing that high benchmark accuracy does not necessarily indicate compositional reasoning capabilities.

Silas Ayitey, Kwabena Owusu-Agyemang2026-11-07

💻 computer science

ECL-YOLOv8: An improved YOLOv8-based algorithm for detecting cattle faces and muzzles in complex open pasture environments

This study proposes ECL-YOLOv8, an improved YOLOv8-based model that significantly enhances the robustness and accuracy of simultaneously detecting cattle faces and muzzles in complex open pasture environments compared to the baseline algorithm.

Juan Liu¹, Shuai Zhang¹, Yuhang Li¹, Hao Zhang¹, Zishuai Jia¹, Yuning Ding¹, Runa Liu¹, Jie Hu¹2026-11-06

💻 computer science

Lung Cancer Classification from CT Images: A Comparative Study of SVM, Modified CNN, and EfficientNet–SVM Hybrid Models

This paper presents a comprehensive computer-aided diagnosis framework for lung cancer classification on the IQ-OTH/NCCD CT dataset, demonstrating that a modified CNN architecture enriched with batch normalization outperforms both traditional SVM-based approaches and a hybrid EfficientNet–SVM model by achieving a test accuracy of 99.41%.

Nuran Binte Habib, Shahida Akther, Rabiul Islam2026-11-06

💻 computer science

Investigating Activity-Linked Audio for Conveying Partner Activity Information in Collaborative VR

This study investigates how different types of activity-linked audio (footsteps and noise-based sonification) influence collaborative VR performance and social dynamics, finding that while subjective evaluations and overall task metrics remained consistent across conditions, specific auditory cues significantly increased the Executor's movement when searching for targets behind the Director.

Miki Hasegawa, Yasu Nakamizo, Ikkaku Kawaguchi2026-11-06

← Previous Next →