Adaptive Gaussian Incremental Expectation Stadium Parameter Estimation Algorithm for Sports Video Analysis by Lizhi Geng

“…The features with more discriminative power are selected from the set of positive and negative templates using a feature selection mechanism, and a sparse discriminative model is constructed by combining a confidence value metric strategy. The sparse generative model is constructed by combining L1 regularization and subspace representation, which retains sufficient representational power while dealing with outliers. …”
Get full text

GenAI synthesis of histopathological images from Raman imaging for intraoperative tongue squamous cell carcinoma assessment by Bing Yan, Zhining Wen, Lili Xue, Tianyi Wang, Zhichao Liu, Wulin Long, Yi Li, Runyu Jing

“…In this study, we integrate Raman imaging technology with an artificial intelligence (AI) generative model, proposing an innovative approach for intraoperative margin status diagnosis. …”
Get full text

The Mirror, the Self(ie) and the New Sacred. Bodies, Objects, and Figures of the Contemporary "Cult of the Self" by Simona Stano

“…Thus it problematises the bodies, as well as the sacred objects, and more generally the figures, of today's cult of the Self, with specific reference to the "generative model" suggested by Just Believe, as well as to the understanding of the sacred in the "postsecular" era.…”
Get full text

Anomaly Detection in Moving Crowds through Spatiotemporal Autoencoding and Additional Attention by Biao Yang, Jinmeng Cao, Rongrong Ni, Ling Zou

“…We propose an anomaly detection approach by learning a generative model using deep neural network. A weighted convolutional autoencoder- (AE-) long short-term memory (LSTM) network is proposed to reconstruct raw data and perform anomaly detection based on reconstruction errors to resolve the existing challenges of anomaly detection in complicated definitions and background influence. …”
Get full text

TAGAN: an academic paper adversarial recommendation algorithm incorporating fine-grained semantic features by Jinyang SUN, Baisong LIU, Hao REN, Jiangbo QIAN

“…Academic paper recommendation aims to provide users with personalized paper resources.Collaborative filtering methods face the problems of highly sparse data and lack of negative samples.Considering the above challenges, an academic paper recommendation algorithm TAGAN（title and abstract GAN）which incorporated fine-grained semantic features was presented.Firstly, based on titles and abstracts provide abundant semantic features, convolutional neural networks (CNN) was used to extract the global features of the titles, a two-layer long and short-term memory network (LSTM) was built to model abstract words separately.At the same time, the attention mechanism was proposed to associate the title and the abstract semantically.Then, the semantic features of the paper were integrated into the recommendation framework based on generative adversarial network (GAN).The generative model will fit the user’s interest preferences and can effectively replace the negative sampling process.Finally,through the experimental comparison on the public dataset, TAGAN is better than the baseline models in all indicators, which verifies the effectiveness of TAGAN.…”
Get full text

3D data augmentation and dual-branch model for robust face forgery detection by Changshuang Zhou, Frederick W.B. Li, Chao Song, Dong Zheng, Bailin Yang

“…Additionally, a 3D generative model augments training data. Extensive experiments demonstrate our method achieves state-of-the-art performance on benchmarks, and ablation studies validate its effectiveness in generalizing to unseen data under various manipulations and compression.…”
Get full text

Deep learning for multi-modal data fusion in IoT applications by Anila Saghir, Anum Akbar, Asma Zafar, Asif Hassan

“…This research proposes a robust solution by fusing the multimodal data and employing a deep learning-based hybrid architecture that incorporates a generative model with a deep convolutional network. The unified model fuses RGB, thermal and depth images for semantic segmentation to improve the accuracy and reliability. …”
Get full text

Penerapan Deep Convolutional Generative Adversarial Network Untuk Menciptakan Data Sintesis Perilaku Pengemudi Dalam Berkendara by Michael Stephen Lui, Fitra Abdurrachman Bachtiar, Novanto Yudistira

“…One way to increase deep learning method performance is by using additional synthesis data made by generative model. Deep Convolutional Generative Adversarial Network (DCGAN) is a generative model that uses convolution layer. …”
Get full text

Structured Dynamics in the Algorithmic Agent by Giulio Ruffini, Francesca Castaldo, Jakub Vohryzek

“…We first formalize the notion of a <i>generative model</i> using the language of symmetry from group theory, specifically employing Lie pseudogroups to describe the continuous transformations that characterize invariance in natural data. …”
Get full text

Detecting memberships in multiplex networks via nonnegative matrix factorization and tensor decomposition by Fengqin Tang, Xiaozong Wang, Xuejing Zhao, Chunning Wang

“…We propose a general and flexible generative model-the mixed membership multilayer stochastic block model, in which layers with meaningful similarities are grouped together. …”
Get full text

A Unified Bayesian Model for Generalized Community Detection in Attribute Networks by Qiang Tian, Wenjun Wang, Yingjie Xie, Huaming Wu, Pengfei Jiao, Lin Pan

“…In this paper, we propose a novel unified Bayesian generative model to detect generalized communities and provide semantic descriptions simultaneously by combining network topology and node attributes. …”
Get full text

CodeContrast: A Contrastive Learning Approach for Generating Coherent Programming Exercises by Nicolás Torres

“…We present CodeContrast, a novel generative model that uses contrastive learning to map programming problems, test cases, and solutions into a shared feature space. …”
Get full text

Disentangled Contrastive Learning From Synthetic Matching Pairs for Targeted Chest X-Ray Generation by Euyoung Kim, Soochahn Lee, Kyoung Mu Lee

“…However, traditional generative models often struggle to independently disentangle these attributes while maintaining the ability to generate entirely new, fully randomized, and diverse synthetic data. …”
Get full text

Survey on the research progress of generative adversarial networks for 6G by Chanyuan MENG, Ke XIONG, Bo GAO, Yu ZHANG, Pingyi FAN

“…The deep integration of artificial intelligence (AI) and communication technology is the typical feature of the 6G network.On the one hand, AI injects new vitality into the development of the 6G network, which can effectively use the data generated by the historical operation of the network.It enables the network to be self-maintained and selfoptimized, and accelerates the process of network intelligence.On the other hand, the rich scenarios and IoT devices of the 6G network provide a large number of application fields and massive data for AI.These can enable the better deployment of AI, fully demonstrate the performance advantages of AI, and provide high-quality services for users.However, in practice, it is difficult to give full play to the performance advantages of AI due to the difficulty of sample collection, high cost of the collection, and lack of universality which caused by the complexity of the environment.Therefore, academia and industry introduce generative adversarial network (GAN) into the design of wireless networks.The powerful feature learning and feature expression ability of GAN can generate a large number of generated samples, which realizes the expansion of the wireless database.The introduction of GAN can effectively improve the generalization ability of AI models for wireless networks.Owing to the excellent performance of GAN, the generative model represented by GAN has attracted increased attention in the field of wireless networks, and rapidly became the new research hotspot of 6G networks.Firstly, the principle of GAN and its different versions of improved derived models were summarized.Then, the framework, advantages and disadvantages of each model were analyzed.Secondly, the research and application status of these models in wireless networks were reviewed.Finally, the research trends of GAN were proposed for the 6G network requirements, which provided some valuable exploration for future research.…”
Get full text

Network representations of drum sequences for classification and generation by Daniel Gómez-Marín, Daniel Gómez-Marín, Sergi Jordà, Perfecto Herrera

“…Second, we present a generative model based on Markov chains operating on the network structure, which is able to produce new drum patterns that retain the essential features of the training data. …”
Get full text

Synthesis‐Style Auto‐Correlation‐Based Transformer: A Learner on Ionospheric TEC Series Forecasting by Yuhuan Yuan, Guozhen Xia, Xinmiao Zhang, Chen Zhou

“…We proposed a two‐step framework: (a) a time series generative model to produce realistic synthetic TEC data for training, and (b) an auto‐correlation‐based transformer model designed to capture long‐range dependencies in the TEC sequence. …”
Get full text

MED-AGNeT: An attention-guided network of customized augmentation of samples based on conditional diffusion for textile defect detection by Jun Liu, Haolin Li, Hao Liu, Jiuzhen Liang

“…During the training process, a conditional term (M) that represents the shape of the defect is added, and through supervised learning, the generative model learns the correlation between the background and defects. …”
Get full text

Deep learning models reveal the link between dynamic brain connectivity patterns and states of consciousness by Chloé Gomez, Lynn Uhrig, Vincent Frouin, Edouard Duchesnay, Béchir Jarraya, Antoine Grigis

“…Here, we investigated the complexity of selecting such a generative model to study brain dynamics, and extended the available methods for latent space characterization and modeling. …”
Get full text

11 Key Strategies in Using AI Chat GPT to Develop HOTS-Based Entrepreneurship Questionnaires by Almaida Vebibina, Rusijono Rusijono, Andi Mariono, Ahsan Muafa, Dydik Kurniawan, Ragil Sugeng Dewantoro, Dian Noer Asyari, Sussi Widiastuti, Jarot Suseno

“…This finding can be utilized by teachers as the latest generative model to increase the bank of diverse multiple-choice questions without replacing human expertise. …”
Get full text

Multi-Class Guided GAN for Remote-Sensing Image Synthesis Based on Semantic Labels by Zhenye Niu, Yuxia Li, Yushu Gong, Bowei Zhang, Yuan He, Jinglin Zhang, Mengyu Tian, Lei He

“…In the scenario of limited labeled remote-sensing datasets, the model’s performance is constrained by the insufficient availability of data. Generative model-based data augmentation has emerged as a promising solution to this limitation. …”
Get full text