cs papers | Gist.Science

Hierarchical Progressive Stereo Extrinsic Self-Calibration with Stereo Super-Resolution and Multi-Level Correspondence Filtering

This paper proposes a Hierarchical Progressive Self-Calibration (HPSC) framework that jointly addresses resolution degradation, depth-dependent uncertainty, and dynamic object interference in autonomous driving stereo cameras through a unified three-stage pipeline integrating stereo super-resolution, depth-stratified correspondence pruning, and hierarchical dynamic suppression.

Xin Ding, Ting Sun2026-08-11

💻 computer science

MR-STGCN: A Multi-weather Robust Spatial–Temporal Graph Convolutional Network for Skeleton-based Gesture Recognition

This paper introduces MR-STGCN, a multi-weather robust spatial-temporal graph convolutional network that leverages dynamic regional routing attention and multi-scale dilated convolutions to achieve high-accuracy, low-latency recognition of traffic police command gestures under adverse weather conditions.

Zhipeng Liu, Zhizhou Wu, Chi Zhang, Bin Pan2026-08-10

💻 computer science

Liability in Motion: A retrieval-augmented LLM application in road traffic liability apportionment

This study presents a retrieval-augmented language model that predicts proportional road traffic liability distributions in German law by integrating taxonomic legal metadata and relevance-ordered demonstrations, thereby facilitating out-of-court settlements through rationalized, justice-aligned algorithmic predictions.

Felix Riechmann2026-08-10

💻 computer science

SRM-UNet: A Lightweight Structure-Region Guided Network with Multi-Receptive-Field Learning for Dermoscopic Skin Lesion Segmentation

This paper introduces SRM-UNet, a lightweight network that employs an explicit structure-region prior collaboration mechanism and multi-receptive-field learning to achieve high-accuracy, resource-efficient skin lesion segmentation on dermoscopic images with blurred boundaries and irregular shapes.

Shikai Zhang, Kaiyan Zhu, Yuhang Mao, Yuanbo Dai, Wenru Zhao2026-08-10

💻 computer science

Intelligent Cross-modal Alignment With Cataphora Dependency Modeling-based Text-to-image Synthesis and Captioning Using Gclan and Gq2phpt

This paper proposes an intelligent cross-modal alignment framework utilizing a GCLAN-based Text-to-Image Synthesis module and a GQ2PHPT-based Image Captioning module to model Cataphora Dependencies, thereby achieving high-accuracy content retrieval and generation with a success rate of 0.9422 and an overall accuracy of 98.9734%.

Yamini Chouhan, Rohit Raja, Shilpa Choudhary, Rohit Miri, Parul Dubey2026-08-10

💻 computer science

EAMF: Evidence-Aware Multimodal Fusion for Conversational Emotion Recognition

This paper proposes EAMF, a decision-oriented framework that enhances multimodal conversational emotion recognition by constructing complementary evidence to specifically resolve ambiguous decisions between closely competing emotion classes, thereby achieving improved performance on challenging minority categories.

Haoran Ma, Liejun Wang, Yinfeng Yu, Xiaoming Tao2026-08-10

💻 computer science

CASCADE: Cross-modal Adaptive Dynamic Gating for Scene Text Recognition

The paper proposes CASCADE, an interpretable adaptive cross-modal fusion module for scene text recognition that utilizes a difficulty estimator and decoupled gating mechanism to dynamically balance visual and linguistic features, achieving state-of-the-art performance on multiple benchmarks while providing transparent decision-making insights.

Wenping Yu, Wei Xu, Jinya Cheng, Yu Zhao, Xuan Wei, Jihan Liu2026-08-10

💻 computer science

Edge Weight Concentration Overcomes Node Degree Blindness in Graph Based Network Intrusion Detection

This paper demonstrates that in graph-based network intrusion detection, edge-weight concentration features outperform traditional node-degree metrics when network address translation (NAT) collapses multiple hosts into few identities, revealing that these two feature families are complementary along the identity-collapse axis and that a compact, leakage-free graph-context feature set can achieve near-baseline performance with significantly reduced training costs.

Md Hasibuzzaman2026-08-10

💻 computer science

Intelligent Multi-Objective Cluster-Head Selection with AoI-Awareness and Anomaly-Informed Suspicion for Tactical WSNs

This paper proposes an intelligent multi-objective cluster-head selection framework for tactical wireless sensor networks that integrates K-Means spatial clustering, temporal anomaly detection, and Q-learning to simultaneously optimize energy efficiency, security, and information freshness (AoI), demonstrating superior performance over existing methods in simulations.

Fayza A. Nada, Fatma S. Abousaleh, Soliman M. Salman, Enas Selem2026-08-10

💻 computer science

Encoder-based 3D GAN inversion: A systematic review

This systematic review of 33 studies reveals that while encoder-based 3D GAN inversion enables real-time reconstruction and editing primarily on high-end hardware using EG3D-based architectures, its widespread adoption is currently limited by challenges in balancing speed with 3D consistency and a lack of robust geometric evaluation beyond frontal face datasets.

Assadig Abakr, Asif Khan, Maruf Hassan, Danyal Aftab, Jane Courtney, Steven Davy2026-08-10

← Previous Next →