SN360: Semantic and Surface Normal Cascaded Multi-Task 360 Monocular Depth Estimation by Payal Mohadikar, Ye Duan

“…Specifically, our approach utilizes an initial depth estimation to simulate RGBD input to enhance the performance of semantic segmentation and surface normal estimation, which is, in turn, leveraged to explicitly guide the final depth prediction. …”
Get full text

Harnessing Semantic and Trajectory Analysis for Real-Time Pedestrian Panic Detection in Crowded Micro-Road Networks by Rongyong Zhao, Lingchen Han, Yuxin Cai, Bingyu Wei, Arifur Rahman, Cuiling Li, Yunlong Ma

“…Current detection models often rely on single-modality features, which limits their effectiveness in complex and dynamic crowd scenarios. …”
Get full text

A Multi-Task Learning Framework with Enhanced Cross-Level Semantic Consistency for Multi-Level Land Cover Classification by Shilin Tao, Haoyu Fu, Ruiqi Yang, Leiguang Wang

“…A hierarchical loss function is also embedded that explicitly models the semantic dependencies between levels, enhancing semantic consistency across levels. …”
Get full text

FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change Detection by Fenglei Chen, Haijun Liu, Zhihong Zeng, Xiaoheng Tan

“…We attempt to employ frequency-domain information to explicitly interact bitemporal low-frequency semantic information during the encoding process, subsequently preserving and enhancing the high-frequency information of each temporal feature. …”
Get full text

LLM-DSK: A Domain-Specific Semantic Knowledge-Guided Ocean Environment Prediction Method Based on Large Language Models by Ning Song, Caichao Lv, Jie Nie, Min Ye, Enyuan Zhao, Jun Ma, Xiong Liu, Zhiqiang Wei

“…LLM-DSK comprises three core modules: 1) a spatiotemporal feature extraction module that utilizes geographic data (e.g., latitude, longitude, wind fields, and land–sea boundaries) to extract key domain-relevant spatiotemporal features; 2) a semantic encoding module that employs an attention mechanism to align these features with the vocabulary of LLMs, enabling cross-modal alignment between oceanic and natural language domains to enrich semantic representations; and 3) an LLM-based prediction module driven by domain-specific prompts that integrate geographic information and statistical indicators. …”
Get full text

GeoMM-SSL: Integrating Geospatial Object Relations in Multimodal Self-Supervised Learning for Semantic Segmentation of Remote Sensing Images by Yang Liu, Tong Zhang, Yanru Huang

“…In this article, we propose a multimodal pretrained SSL (GeoMM-SSL) framework that explicitly integrates geospatial object relations. The proposed framework includes a teacher-student framework with residual gated guidable attention units as the backbone, a multihead graph attention network that encodes prior knowledge of geospatial object relations, a multimodal representation fusion module that facilitates mutual learning between visual features of remote sensing images and topological features of geospatial object relations, and a multilevel loss function that performs multiple levels of evaluation, enabling the model to learn the data representation at the pixel, object, and global levels. …”
Get full text

Semantic Segmentation of Rice Fields in Sub-Meter Satellite Imagery Using an HRNet-CA-Enhanced DeepLabV3+ Framework by Yifan Shao, Pan Pan, Hongxin Zhao, Jiale Li, Guoping Yu, Guomin Zhou, Jianhua Zhang

Get full text

Morphological-Priors-Guided Network With Semantic Booster and Scalable Bins Module for Height Estimation From Single-View Remote Sensing Images by Tao Zhang, Furong Shi, Yuanping Zhu

“…First, considering the semantic morphological priors, we propose to explicitly enhance the 3-D visual cues (e.g., co-occurrence relationship between shadow buildings and shadow trees) and simultaneously design a semantic booster composed of a two-stream network with a multilevel cross-stream attention fusion mechanism to facilitate the 3-D feature learning for monocular height estimation. …”
Get full text

Temporal Features-Fused Vision Retentive Network for Echocardiography Image Segmentation by Zhicheng Lin, Rongpu Cui, Limiao Ning, Jian Peng

“…The Vision RetNet encoder introduces explicit spatial priors by constructing a spatial decay matrix using the Manhattan distance. …”
Get full text

Object-Specific Multiview Classification Through View-Compatible Feature Fusion by Javier Perez Soler, Jose-Luis Guardiola, Nicolás García Sastre, Pau Garrigues Carbó, Miguel Sanchis Hernández, Juan-Carlos Perez-Cortes

“…It does not merely use pose as auxiliary data but employs it to align and selectively fuse features from different views. This mathematically explicit fusion of rotations, based on relative poses, allows VCFF to effectively combine multi-view information, enhancing classification accuracy. …”
Get full text

The Problem of Detecting Incitement in Extremist Content (Using Examples from the Internet) by T. V. Berdnikova

“…Targeting is closely related to the types of incitement: direct/indirect, explicit/implicit. To identify the linguistic features of the “incitement” meaning it is necessary to conduct a multidimensional analysis considering the general communicative situation, the category of targeting and its implementation in the statement.…”
Get full text

MULTIMODAL SYNTACTIC CONSTRUCTIONS: A STRIKING FEATURE OF DIGITAL COMMUNICATION IN MODERN ENGLISH by Larysa L. Makaruk

“…The social semiotic approach was aimed at identifying the implicit and explicit load to identify the true meanings. The comparative method was useful for distinguishing types of multimodal syntactic constructions based on common features. …”
Get full text

Enhancing Text Classification Through Grammar-Based Feature Engineering and Learning Models by Alaa Mohasseb, Andreas Kanavos, Eslam Amer

“…Grammatical and domain-specific features are explicitly extracted and leveraged to improve multi-class classification. …”
Get full text

Neighborhood Information Aggregation and Multi-View Feature Extraction-Based Contrastive Graph Clustering by Liulong Yao, Jinrong Cui, Yazi Xie, Chengli Sun

“…In addition, existing methods mainly rely on the original graph topology information and fail to fully utilize the neighborhood information hidden in the node attribute features. To address the above problems, we proposes a Neighborhood Information Aggregation and Multi-View Feature Extraction-Based Contrastive Graph Clustering (NIA-MVFE-CGC) framework, which improves the existing methods from the perspectives of network architecture, feature redundancy and neighborhood information. …”
Get full text

Dependency-Aware Entity–Attribute Relationship Learning for Text-Based Person Search by Wei Xia, Wenguang Gan, Xinpan Yuan

Get full text

Identity Hides in Darkness: Learning Feature Discovery Transformer for Nighttime Person Re-Identification by Xin Yuan, Ying He, Guozhu Hao

“…To this end, we propose a novel nighttime person Re-ID method, termed Feature Discovery Transformer (FDT), explicitly capturing the pedestrian identity information hidden in darkness at night. …”
Get full text

Specificity of Cognate Nouns and Adjectives Functioning by L. V. Noskina

“…These predicates also differ in the forms of their arguments.Conclusion. The revealed features of cognate nouns and adjectives functioning show the significant influence of the form of linguistic unit on syntactic behavior and indicate that formation of syntactic structures is not only determined by semantics.…”
Get full text

TableBorderNet: A Table Border Extraction Network Considering Topological Regularity by Jing Yang, Shengqiang Zhou, Xialing Li, Yuchun Huang, Honglin Jiang

“…The framework captures structural context by guiding convolutional feature extraction along explicit row and column directions, enabling more accurate delineation of table borders. …”
Get full text

GIRH-Unet: Improved Residual Tobacco Segmentation Algorithm Based on GhostNetV3-Unet by Jianhua Ye, Yunda Zhang, Pan Li, Ze Guo

“…In this study, we propose an enhanced lightweight segmentation model, GhostNetV3-Unet, designed explicitly for residual tobacco segmentation. Our approach utilizes an improved GhostNetV3 to bolster feature extraction capabilities. …”
Get full text

AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features by Ruochen Zhang, Hyeung-Sik Choi, Dongwook Jung, Phan Huy Nam Anh, Sang-Ki Jeong, Zihao Zhu

“…Monocular 3D object detection is a challenging task in autonomous systems due to the lack of explicit depth information in single-view images. Existing methods often depend on external depth estimators or expensive sensors, which increase computational complexity and complicate integration into existing systems. …”
Get full text