Crack Detection Method of Sleeper Based on Cascade Convolutional Neural Network by Liming Li, Shubin Zheng, Chenxi Wang, Shuguang Zhao, Xiaodong Chai, Lele Peng, Qianqian Tong, Ji Wang

“…During object detection, the proposed method is compared with YOLOv3 in terms of directly locating sleeper cracks. …”
Get full text

River floating object detection with transformer model in real time by Chong Zhang, Jie Yue, Jianglong Fu, Shouluan Wu

“…The RT-DETR, a member of the DETR family, has notably addressed the speed limitations of its predecessors by utilizing a high-performance hybrid encoder that optimizes query selection. Building upon this foundation, we introduce the LR-DETR, a lightweight evolution of RT-DETR for river floating object detection. …”
Get full text

High-Quality Text-to-Speech Implementation via Active Shallow Diffusion Mechanism by Junlin Deng, Ruihan Hou, Yan Deng, Yongqiu Long, Ning Wu

“…In the following stage of processing, a post-net is used to optimize the mel-spectrogram reconstruction performance. …”
Get full text

An Empirical Comparison of Machine Learning and Deep Learning Models for Automated Fake News Detection by Yexin Tian, Shuo Xu, Yuchen Cao, Zhongyan Wang, Zijing Wei

“…Despite advances in NLP, systematic empirical benchmarks that directly compare both classical and deep models—across varying input richness and with careful attention to interpretability and computational tradeoffs—remain underexplored. …”
Get full text

Hybrid deep learning framework based on EfficientViT for classification of gastrointestinal diseases by Vishesh Tanwar, Bhisham Sharma, Dhirendra Prasad Yadav, Abolfazl Mehbodniya

“…Furthermore, we designed a dual-block in which input is divided into two parts (q1, q2) to better optimize the model q1 processed through an EfficientNet for local details and a q2 through encoder block for capturing the global dependencies, which enables EfficientViT to pay attention to multiple image regions simultaneously. …”
Get full text

Real-time dental caries segmentation with an efficient Deformable U-Net (DU-Net) for teledentistry system by Zendi Iklima, Trie Maya Kadarina, Ketty Siti Salamah, Arrival Dwi Sentosa

“…The result highlights the DU-Net capability to optimize both computational efficiency and segmentation accuracy, offering a promising solution for real-world applications where speed and resource management are critical, particularly in the medical imaging field.…”
Get full text

Human Activity Recognition Based on Point Clouds from Millimeter-Wave Radar by Seungchan Lim, Chaewoon Park, Seongjoo Lee, Yunho Jung

“…This network achieved 94.79% accuracy with 4 bit quantization, which reduced memory usage to 12.5% compared to existing 32 bit format networks. In addition, we implemented a lightweight HAR system optimized for low-power design on a heterogeneous computing platform, a Zynq UltraScale+ ZCU104 device, through hardware–software implementation. …”
Get full text

Advancing Rice Grain Impurity Segmentation with an Enhanced SegFormer and Multi-Scale Feature Integration by Xiulin Qiu, Hongzhi Yao, Qinghua Liu, Hongrui Liu, Haozhi Zhang, Mengdi Zhao

“…First, the Feature Pyramid Network (FPN) was introduced to optimize the structure, selectively fusing the high-level semantic features and low-level texture features generated by the encoder. …”
Get full text

What Helps to Detect What? Explainable AI and Multisensor Fusion for Semantic Segmentation of Simultaneous Crop and Land Cover Land Use Delineation by Saman Ebrahimi, Saurav Kumar

“…Our approach integrates pixel-level multisensor fusion, combining dual-month moderate-resolution optical imagery (July and December 2023), synthetic aperture radar (SAR), and digital elevation model (DEM) data, processed using a Multi-Attention Network with a modified Mix Vision Transformer encoder to process multiple spectral inputs. Results indicate a uniform improvement in class-specific Intersection over Union by approximately 1% with multisensor integration compared to optical imagery alone. …”
Get full text

MFA-SCDNet: A Semantic Change Detection Network for Visible and Infrared Image Pairs by Xingyu Li, Jiulu Gong, Jianxiong Wen, Zepeng Wang

“…The proposed architecture operates through three principal technical components: An infrared feature enhancement module that transforms infrared inputs into three-channel representations through spectral domain adaptation, enhancing the network’s perception of both high-frequency and low-frequency information in images; an encoder–decoder structure that simultaneously extracts modality-specific features and common features through adversarial learning; and a synergistic information fusion mechanism that integrates semantic recognition with change detection through multi-task optimization. …”
Get full text

Fast Adaptive CU Partition Decision Algorithm for VVC Intra Coding by Lina Si, Wendi Zhu, Qiuwen Zhang

“…The latest video standard - Versatile Video Coding Standard (VVC/H.266) has been standardized and officially entered into force. Compared with the High Efficiency Video Coding (HEVC/H.265), owing to the introduction of the Quad-tree with Nested Multi-type Tree (QTMT) division mode, the encoder can choose a more detailed division type when dividing the Coding unit (CU), thereby improving the coding performance. …”
Get full text

Leveraging Multilingual Transformer for Multiclass Sentiment Analysis in Code-Mixed Data of Low-Resource Languages by Muhammad Kashif Nazir, Cm Nadeem Faisal, Muhammad Asif Habib, Haseeb Ahmad

“…Subsequently, the Multilingual Bidirectional Encoder Representations from Transformers (mBERT) model was optimized and trained for multiclass sentiment analysis on the code-mixed data. …”
Get full text

Visual Automatic Localization Method Based on Multi-level Video Transformer by Qiping ZOU, Botao LI, Saian CHEN, Xi GUO, Taohong ZHANG

“…The proposed models display superior performance when these variants are compared to mainstream video transformers of comparable parameter sizes. …”
Get full text

CAEB7-UNet: An Attention-Based Deep Learning Framework for Automated Segmentation of C-Spine Vertebrae in CT Images by Abhishek Kumar Pandey, Kedarnath Senapati, G. P. Pateel

“…Further, the model is optimized by incorporating hyperparameter optimization, specifically, hybrid learning rate scheduler strategies, along with the AdamW optimizer and custom data augmentation. …”
Get full text

Integrating Multimodality and Partial Observability Solutions Into Decentralized Multiagent Reinforcement Learning Adaptive Traffic Signal Control by Kareem Othman, Xiaoyu Wang, Amer Shalaby, Baher Abdulhai

“…Additionally, ATSC systems are commonly optimized to improve the performance of the general traffic, ignoring the impact on transit. …”
Get full text

AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net by Ming Zhao, Yimin Yang, Bingxue Zhou, Quan Wang, Fu Li

“…In addition, to further improve the performance of the network under different resolution features, we designed a Double-Stage Channel Optimization Module (DSCOM) in the first two layers of the model. …”
Get full text

Spatiotemporal Deformation Prediction Model for Retaining Structures Integrating ConvGRU and Cross-Attention Mechanism by Yanyong Gao, Zhaoyun Xiao, Zhiqun Gong, Shanjing Huang, Haojie Zhu

“…The root mean square error (RMSE) remains below 0.44 mm, while the mean absolute error (MAE) is less than 0.36 mm. Comparative experiments confirm the effectiveness of the proposed model architecture and the optimization strategy. …”
Get full text

Self-Supervised Social Recommendation Algorithm Fusing Residual Networks by WANG Yujie, YANG Zhe

“…Experimental results show that the algorithm has good recommendation performance compared with the benchmark model.…”
Get full text

MAPM:PolSAR Image Classification with Masked Autoencoder Based on Position Prediction and Memory Tokens by Jianlong Wang, Yingying Li, Dou Quan, Beibei Hou, Zhensong Wang, Haifeng Sima, Junding Sun

“…Specifically, MAPM achieves performance gains of about 1% in classification accuracy compared with existing methods.…”
Get full text

Automated Semantic Segmentation of Arctic Surface Water Features with Very-High Resolution Satellite X-Band Radar Imagery and U-Net Deep Learning: Segmentation sémantique automatis... by Michael Allan Merchant, Masoud Mahdianpari, Laura Bourgeau-Chavez, Ben DeVries, Aaron Berg

“…Our study proposes a modified U-Net encoder-decoder model for this task, optimized using the Nadam algorithm. …”
Get full text