Regional-to-Local Point-Voxel Transformer for Large-Scale Indoor 3D Point Cloud Semantic Segmentation by Shuai Li, Hongjun Li

“…The window-based point-voxel branch concentrates on local feature learning while integrating voxel-level information within each window. …”
Get full text

Graph neural network recommendation algorithm based on improved dual tower model by Qiang He, Xinkai Li, Biao Cai

“…Additionally, this method utilizes graph convolutional networks for higher-order feature learning, pooling the node embeddings of the twin towers to obtain enhanced end-user and item representations. …”
Get full text

Feature Refine Network for Salient Object Detection by Jiejun Yang, Liejun Wang, Yongming Li

“…Different feature learning strategies have enhanced performance in recent deep neural network-based salient object detection. …”
Get full text

Semi-Supervised Machine Condition Monitoring by Learning Deep Discriminative Audio Features by Iordanis Thoidis, Marios Giouvanakis, George Papanikolaou

“…We propose a comprehensive feature learning approach that operates on raw audio, by supervising the formation of salient audio embeddings in latent states of a deep temporal convolutional neural network. …”
Get full text

An Improved Informer Model for Short-Term Load Forecasting by Considering Periodic Property of Load Profiles by Fu Liu, Tian Dong, Tian Dong, Yun Liu

“…In recent times, an attention-based model, Informer, has been proposed for efficient feature learning of lone sequences. To solve the quadratic complexity of traditional method, this model designs what is called ProbSparse self-attention mechanism. …”
Get full text

Learning representations for human re-identification by Varior, Rahul Rama

“…The goal of this thesis is to present various feature learning architectures in different perspectives to tackle the aforementioned challenges in human re-identification. …”
Get full text

Combining wav2vec 2.0 Fine-Tuning and ConLearnNet for Speech Emotion Recognition by Chenjing Sun, Yi Zhou, Xin Huang, Jichen Yang, Xianhua Hou

“…ConLearnNet comprises three steps: feature learning, contrastive learning, and classification. …”
Get full text

Network Embedding Algorithm Taking in Variational Graph AutoEncoder by Dongming Chen, Mingshuo Nie, Hupo Zhang, Zhen Wang, Dongqi Wang

“…This algorithm first pre-processes the attribute features, i.e., the attribute feature learning of the network nodes. Then, the feature learning matrix and the adjacency matrix of the network are fed into the variational graph autoencoder algorithm to obtain the Gaussian distribution of the potential vectors, which more easily generate high-quality node embedding representation vectors. …”
Get full text

EXAM: A Framework of Learning Extreme and Moderate Embeddings for Person Re-ID by Guanqiu Qi, Gang Hu, Xiaofei Wang, Neal Mazur, Zhiqin Zhu, Matthew Haner

“…This is done using discriminative feature learning, requiring attention-based guidance during training. …”
Get full text

Sentiment Interaction Distillation Network for Image Sentiment Analysis by Lifang Wu, Sinuo Deng, Heng Zhang, Ge Shi

“…In addition, we propose a knowledge distillation framework to utilize interaction information guiding global context feature learning, which can avoid noisy features introduced by error propagation and a varying number of objects. …”
Get full text

A dual-branch multi-feature deep fusion network framework for hyperspectral image classification by Linfeng Liu, Chengcai Zhang, Weiran Luo

“…For the second part, a series spectral-spatial feature learning modules and augmentation modules for spatial feature learning are being developed to learn these features in a continuous manner while also effectively fusing features from various depth layers. …”
Get full text

Text3D: 3D Convolutional Neural Networks for Text Classification by Jinrui Wang, Jie Li, Yirui Zhang

“…This paper proposes a simple, yet effective, approach for hierarchy feature learning using 3D CNN in text classification tasks, named Text3D. …”
Get full text

Multi-view learning-based heterogeneous network representation learning by Lei Chen, Yuan Li, Xingye Deng

“…Firstly, to simplify the difficulty of feature learning, a novel view generation strategy is designed to divide the heterogeneous network into multiple sub-views that contain only one semantic feature and its related structural features. …”
Get full text

Integrating Enhanced Sparse Autoencoder-Based Artificial Neural Network Technique and Softmax Regression for Medical Diagnosis by Sarah A. Ebiaredoh-Mienye, Ebenezer Esenogho, Theo G. Swart

“…Hence, the proposed approach has the advantage of effective feature learning and robust classification performance. …”
Get full text

Predicting Adverse Drug Reactions from Social Media Posts: Data Balance, Feature Selection and Deep Learning by Jhih-Yuan Huang, Wei-Po Lee, King-Der Lee

“…In contrast to the traditional machine learning methods, our feature learning approach can automatically achieve the required task to save the manual effort for the large number of experiments.…”
Get full text

Deep Error-Correcting Output Codes by Li-Na Wang, Hongxu Wei, Yuchen Zheng, Junyu Dong, Guoqiang Zhong

“…We have conducted extensive experiments to compare DeepECOCs with traditional ECOC, feature learning and deep learning algorithms. The results demonstrate that DeepECOCs perform, not only better than existing ECOC and feature learning algorithms, but also related to deep learning ones in most cases.…”
Get full text

Lightweight Semantic-Guided Neural Networks Based on Single Head Attention for Action Recognition by Seon-Bin Kim, Chanhyuk Jung, Byeong-Il Kim, Byoung Chul Ko

“…However, because an SGN focuses on global feature learning rather than local feature learning owing to the structural characteristics, there is a limit to an action recognition in which the dependency between neighbouring nodes is important. …”
Get full text

Improved Heart Disease Prediction Using Particle Swarm Optimization Based Stacked Sparse Autoencoder by Ibomoiye Domor Mienye, Yanxia Sun

“…The optimization by the PSO improves the feature learning and classification performance of the SSAE. …”
Get full text

Object detection utilizing modified auto encoder and convolutional neural networks by Khiarak, Jalil Nourmohammadi, Mazaheri, Samaneh, Tayebi, Rohollah Moosavi, Noorbakhsh-Devlagh, Hamid

“…The proposed method has two main advantages over other unsupervised feature learning techniques. Firstly, as it will be shown, features are detected with a much higher precision. …”
Get full text

Exploring Channel Properties to Improve Singing Voice Detection with Convolutional Neural Networks by Wenming Gui, Yukun Li, Xian Zang, Jinglan Zhang

“…Because of the poor adaptability and complexity of feature engineering, there is a recent trend towards feature learning in which deep neural networks play the roles of feature extraction and classification. …”
Get full text