TMFN: a text-based multimodal fusion network with multi-scale feature extraction and unsupervised contrastive learning for multimodal sentiment analysis by Junsong Fu, Youjia Fu, Huixia Xue, Zihao Xu

“…Firstly, we propose an innovative pyramid-structured multi-scale feature extraction method, which captures the multi-scale features of modal data through convolution kernels of different sizes and strengthens key features through channel attention mechanism. …”
Get full text

Enhancing Speaker Recognition with CRET Model: a fusion of CONV2D, RESNET and ECAPA-TDNN by Pinyan Li, Lap Man Hoi, Yapeng Wang, Xu Yang, Sio Kei Im

“…In this study, two CRET models are proposed, and these two models are compared with the baseline models Multi-Scale Backbone Architecture (Res2Net) and ECAPA-TDNN in different channels and different datasets. The experimental findings indicate that our proposed models exhibit strong performance across various experiments conducted on both training and test sets, even when the network layer is deep. …”
Get full text

Deep vision-based real-time hand gesture recognition: a review by Cui Cui, Mohd Shahrizal Sunar, Goh Eg Su

“…The choice of evaluation metrics and dataset is critical since different tasks require different evaluation parameters, and the model learns more patterns and features from diverse data. …”
Get full text

Computer-Aided Brain Tumor Diagnosis: Performance Evaluation of Deep Learner CNN Using Augmented Brain MRI by Asma Naseer, Tahreem Yasir, Arifah Azhar, Tanzeela Shakeel, Kashif Zafar

“…The performance and sustainability of the model is evaluated on six different datasets, i.e., BMI-I, BTI, BMI-II, BTS, BMI-III, and BD-BT. …”
Get full text

Adaptive Conditional Reasoning for Remote Sensing Visual Question Answering by Yiqun Gao, Zongwen Bai, Meili Zhou, Bolin Jia, Peiqi Gao, Rui Zhu

“…In order to enhance the multimodal fusion process of different types of questions, the ACR model further integrates visual and textual features by leveraging type-guided cross-attention. …”
Get full text

Digital processing of images with defects due to double beam attenuation in indirect X-ray fluorescence mapping by Luisa Dutra Silva, Lucas da Costa Souza, Davi Ferreira Oliveira, Marcelino José Anjos, Elicardo Alves de Souza Gonçalves

“…This algorithm showed the characteristics of the convolution matrix K needed to solve the problem. The results show the real possibility of using the equipment for this adapted measurement and a methodology that can be expanded to different situations.…”
Get full text

Detection of Pathogenic Microorganisms by Fusion of Recursive Feature Pyramid by HUANGZhitian, XIEYining, ZHAOJing, HEYongjun

“…Aiming at the problems of less research on the detection of pathogenic microorganisms , large differences in target size and complex background , a multi-scale detection method of pathogenic microorganisms fused with recursive feature pyramid was proposed. …”
Get full text

YOLO Network-Based Extraction of Target Geometry From Time-Frequency Representation by Jingyuan Han, Kunyi Guo, Xinqing Sheng

“…The robustness of the network is verified through comparison experiments and ablation experiments for different types of targets. Experimental results, including metric functions and data on reconstructed geometric structures, demonstrate good consistency between the extracted and actual geometric parameters, and the trained network model has a good generalization ability for more complicated structural targets. …”
Get full text

Comparative Study of the Performance of Two Treatment Planning Systems Using Tests from the MPPG 5b Guidelines, TECDOC 1583 and Venselaar's Confidence Limits by Carlos Vega D'Espaux, Federico Lorenzo, Franco La Paz Mastandrea, Nicolás Larragueta

“… This work presents a comprehensive comparative study of the performance of two Treatment Planning Systems (TPS) in radiotherapy: the Eclipse™ TPS by Varian Medical Systems, which utilizes the Analytical Anisotropic Algorithm (AAA), and the MIRS TPS by Nuclemed, which uses the Convolution and Superposition (CS) Algorithm. The evaluation of both systems was conducted following different methods, including point measurements, dose profiles, and measurements on phantoms with heterogeneities. …”
Get full text

Quantum Integral Inequalities with Respect to Raina’s Function via Coordinated Generalized Ψ-Convex Functions with Applications by Saima Rashid, Saad Ihsan Butt, Shazia Kanwal, Hijaz Ahmad, Miao-Kun Wang

“…This novel framework is the convolution of quantum calculus, convexity, and special functions. …”
Get full text

Research on graph-based heterogeneous data integration method by HUANG Yuezhen, YANG Fen, TIAN Feng, ZHANG Chengye, LI Yuchan

“…The table names and field names were regarded as different types of entities in the graph. Then, input the constructed graph into the graph neural network, and the vector representation of each node in the graph was obtained through graph convolution. …”
Get full text

Comparative evaluation of deep learning and machine learning techniques for sentiment analysis of electronic product review data by Nagelli Archana, Saleena B., Prakash B.

“…The Naïve Bayes, support vector machine, decision tree, convolution neural network, long short term memory, recursive neural networks, and recurrent neural networks were used on the dataset after applying different data preprocessing. …”
Get full text

STMSF: Swin Transformer with Multi-Scale Fusion for Remote Sensing Scene Classification by Yingtao Duan, Chao Song, Yifan Zhang, Puyu Cheng, Shaohui Mei

“…Specifically, a multi-scale feature fusion module is proposed, so that features of ground objects at different scales in the RS scene can be well considered by merging multi-scale features. …”
Get full text

Research on YOLOv3 model compression strategy for UAV deployment by Fei Xu, Litao Huang, Xiaoyang Gao, Tingting Yu, Leyi Zhang

“…In this paper, we tend to compress YOLOv3 model in different aspects to achieve load availability at the edge. …”
Get full text

A multimodal deep learning model with differential evolution-based optimized features for classification of power quality disturbances by Md Nurul Islam

“…Detection and classification of the different power quality disturbances has become one of the current priority research topics for last few years. …”
Get full text

Research on delay upper bound analysis based on network calculus for LEO satellite network by WANG Huizi, SUN Lei, WANG Jianquan, LIN Shangjing, WANG Zhuoqun, SUN Kewen

“…Next, a traffic model was formulated based on leaky bucket model, considering the worst-case impact of interference from different priorities, and then the service curve for a satellite node was established. …”
Get full text

Salient object detection with non-local feature enhancement and edge reconstruction by Tao Xu, Jingyao Jiang, Lei Cai, Haojie Chai, Hanjun Ma

“…It aggregates various image details from different branches to better capture and enhance edge information, thereby generating saliency maps with more exact edges. …”
Get full text

A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction. by Yuping Yin, Haodong Zhu, Lin Wei

“…Hyperspectral Image (HSI) classification tasks are usually impacted by Convolutional Neural Networks (CNN). Specifically, the majority of models using traditional convolutions for HSI classification tasks extract redundant information due to the convolution layer, which makes the subsequent network structure produce a large number of parameters and complex computations, so as to limit their classification effectiveness, particularly in situations with constraints on computational power and storage capacity. …”
Get full text

Urban Traffic Flow Forecasting Based on Graph Structure Learning by Guangyu Huo, Yong Zhang, Yimei Lv, Hao Ren, Baocai Yin

“…In our model, the graph structure learning module dynamically captures the correlation and causation between the different time series and infers a potentially fully connected graph. …”
Get full text

Research on graph-based heterogeneous data integration method by HUANG Yuezhen, YANG Fen, TIAN Feng, ZHANG Chengye, LI Yuchan

“…The table names and field names were regarded as different types of entities in the graph. Then, input the constructed graph into the graph neural network, and the vector representation of each node in the graph was obtained through graph convolution. …”
Get full text