Multi-granularity feature intersection learning for visible-infrared person re-identification by Sixian Chan, Jie Wang, Jiaao Cui, Jie Hu, Zhuorong Li, Jiafa Mao

“…Next, HPC spreads the identity loss across all layers to reduce the distance for gradient backpropagation and further optimize fine-grained features in shallow layers. …”
Get full text

A Novel Sentence-Level Visual Speech Recognition System for Vietnamese Language Using ResNet3D and Zipformer by Phat Nguyen Huu, Thach Ho Sy

“…It incorporates a stateless decoder that considers two preceding tokens and is optimized with a pruned-RNNT loss function. Experimental results show that our system achieves a word error rate (WER) of 27.14% and a character error rate (CER) of 20.45% on single-speaker tasks, demonstrating significant progress in VSR for Vietnamese.…”
Get full text

Exploring the Role of β-Sitosterol, Genistein, and Emodin in Periodontal Regeneration by Prabhu M. Natarajan, Mohamed A. Jaber, Vidhyarekha Umapathy, Bhuminathan Swamikannu, Manickam S Nandhini, Vijay B. Desai, Mohammad K. S. Khot

“…If not treated in time, it can lead to alveolar bone resorption and defect, periodontal attachment loss, teeth loosening, and complete tooth loss. Bone grafting is to repair periodontal defects by transplanting materials to restore the anatomical morphology of the alveolar bone and the function of periodontal tissue. …”
Get full text

VRU-YOLO: A Small Object Detection Algorithm for Vulnerable Road Users in Complex Scenes by Yunxiang Liu, Yuqing Shi

“…Finally, to alleviate the deficiencies of traditional loss functions in shape matching and computational efficiency, we propose the Wise-Powerful Intersection over Union (WPIoU) loss function, which further optimizes the regression of target bounding boxes. …”
Get full text

A recommender algorithm based on SVD ++model under trust network by Peiwu CHEN, Fangxing SHU

“…Recommender algorithms are usually modeled based on user behavior data.However, the sparseness of explicit behavior data may cause the cold start problem of recommender algorithms.In order to solve the impact of data sparseness and cold-start problems on the effect of recommender algorithms, implicit trust relationship based on user similarity was introduced based on the existing revealed trust relationship, and a new recommender algorithm was designed through the SVD++ implicit semantic model.In order to improve the effect of the algorithm, the neighborhood model was integrated further, and the algorithm score prediction formula and loss function were derived.In the Epinions open source data set, RMSE and MAE were used as test indicators, and comparative experiments were conducted on the entire user set and the cold start user set.The experimental results show that the recommender algorithm can optimize the cold start problem of the original recommender algorithm to a certain extent, and achieve a better rating prediction accuracy.…”
Get full text

Berries and Their Active Compounds in Prevention of Age-Related Macular Degeneration by Xiang Li, Lingda Zhao, Bowei Zhang, Shuo Wang

“…Age-related macular degeneration (AMD) is a leading cause of vision loss in the elderly, significantly diminishing quality of life. …”
Get full text

A Deep Reinforcement Learning–Based Urban Traffic Control Model for Vehicle-to-Everything Ecosystem by Lingyu Zheng, Han Chen, Yajie Zou

“…The framework incorporates a joint-state representation integrating traffic data from both I2I and vehicle-to-infrastructure (V2I) communications, while considering communication range effects. The reward function is designed to optimize both local intersection conditions and global network performance, facilitating adaptive signal coordination. …”
Get full text

A Resilience Enhancement Model for Complex Distribution Network Coupling with Human Resources and Traffic Network by Biyun Chen, Yumo Shi, Yanni Chen

“…Secondly, according to the function of human resources in shortening the repair time and improving system resilience, an optimization model of emergency repair strategy is proposed. …”
Get full text

Enhancing Secure Energy Efficiency of SWIPT IoT Network Considering IRS and Artificial-Noise: A Deep Learning Approach by Kimchheang Chhea, Jung-Ryun Lee

“…To solve this problem, we propose a deep neural network (DNN) algorithm that utilizes a loss function derived from Lagrange duality function. …”
Get full text

Small Object Detection Algorithm Based on Partial Convolution and Attention Fusion Detection Head by Peng Sheng, Zhu Fenghua, Zhou Jin, Zhu Gaofeng, Wang Yingxu, Chen Yuehui

“…Finally, the bounding box loss function is optimized as Inner-ShapeIoU, focusing on shape and scale of the bounding box to improve the accuracy for bounding box regression calculation while utilizing auxiliary bounding boxes to expedite convergence speed. …”
Get full text

Accelerating Euclidean Distance Transforms: A Fast and Flexible Approach With Multi-Vendor GPU, Multi-Threading, and Multi-Language Support by Dale Black, Wenbo Li, Qiyu Zhang, Sabee Molloi

“…Benchmarks demonstrate substantial performance improvements, achieving speedups by a factor of 250 for 2D and a factor of 400 for 3D transforms compared to optimized CPU implementations. We showcase the impact of our approach through two real-world applications: accelerating the Hausdorff distance loss function for medical image segmentation, achieving a 7.4-fold improvement in processing speed with enhanced accuracy, and enhancing a GPU-optimized distance transform-based skeletonization algorithm with performance gains up to a factor of 88. …”
Get full text

Multi-class segmentation of knee MRI based on hybrid attention by Yuhang Xiang, Xinglin Zhang, Tao Meng, Tao Meng, Tao Chen, Tao Chen

“…Secondly, we introduce the Atrous Squeeze Attention (ASA) module, which enables the model to focus on multi-scale features and capture long-range dependencies, thereby improving the segmentation accuracy of complex multi-class structures. Lastly, the loss function is optimized to address the challenges of class imbalance and limited data. …”
Get full text

Flexi-YOLO: A lightweight method for road crack detection in complex environments. by Jiexiang Yang, Renjie Tian, Zexing Zhou, Xingyue Tan, Pingyang He

“…We designed Wise-IoU as the model's loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”
Get full text

Application of Improved YOLOv8 Image Model in Urban Manhole Cover Defect Management and Detection: Case Study by Yanqiong Ding, Baojiang Han, Hua Jiang, Hao Hu, Lei Xue, Jiasen Weng, Zhili Tang, Yuzhang Liu

“…This structure utilizes bidirectional feature transfer and automatic structure search, significantly enhancing the expressiveness of multi-scale features. A combined loss function design using GIoU loss, dynamically weighted BCE loss, and Distribution Focal Loss (DFL) is adopted to address the issues of sample imbalance and inter-class differences. …”
Get full text

Lightweight wavelet-CNN tea leaf disease detection. by Jing Yang, GaoJian Xu, MengDao Yang, ZhengPei Lin

“…A focal loss function also replaces traditional cross-entropy loss to mitigate sample category imbalance, improving recognition accuracy across varying distributions. …”
Get full text

YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7 by Xiaoming Wang, Xiaoming Wang, Zhenlong Wu, Guannan Xiao, Guannan Xiao, Chongyang Han, Cheng Fang

“…Secondly, a new loss function WiseIoU is proposed for the loss function in YOLOv7, which improves the accuracy of the model. …”
Get full text

RTL-Net: real-time lightweight Urban traffic object detection algorithm by Zhiqing Cui, Jiahao Yuan, Haibin Xu, Yamei Wei, Zhenglong Ding

“…To enhance real-time performance beyond the benchmark, we implemented lightweight designs for the loss function, backbone, neck, and head components. …”
Get full text

2×2 Microfluidic Optical Switch with Ferromagnetic Fluid Drive by SHI Zheng, WAN Jing, YU Tingjie, ZHOU Rui, CHEN Jiansong

“…It utilizes microfluidic driving technology based on magnetic fluids, along with trace amounts of liquid and air, to achieve optical path selection and switching functions for the optical switch. The transmission characteristics of optical switch are studied and discussed, and the structure of optical switch is optimized.…”
Get full text

Semi-supervised emotion-driven music generation model based on category-dispersed Gaussian Mixture Variational Autoencoders. by Zihao Ning, Xiao Han, Jie Pan

“…Finally, the objective loss function is optimized to enhance the separation of distinct emotional clusters. …”
Get full text

Projectile Explosion Weak Firelight Image Recognition Method Using Multi-Scale Adaptive Enhancement Network by Xuebin Liu, Hanshan Li, Shaopeng Liang

“…The Focal-Dice Loss is used as the joint supervision loss function of the network model, which can effectively solve the problem of sample imbalance and improve the recognition accuracy of the network. …”
Get full text