A5101579269- Artificial Intelligence in Games
- Video Analysis and Summarization
- Face and Expression Recognition
- Sports Analytics and Performance
- Face recognition and analysis
- Advanced Malware Detection Techniques
- Anomaly Detection Techniques and Applications
- Digital Games and Media
- Recommender Systems and Techniques
- Explainable Artificial Intelligence (XAI)
- Generative Adversarial Networks and Image Synthesis
- Advanced Image and Video Retrieval Techniques
- Biometric Identification and Security
- Consumer Market Behavior and Pricing
- Customer churn and segmentation
- Gambling Behavior and Treatments
- Data Stream Mining Techniques
- Network Security and Intrusion Detection
- Advanced Steganography and Watermarking Techniques
- Multimedia Communication and Technology
- Adversarial Robustness in Machine Learning
- Mobile Crowdsensing and Crowdsourcing
- Advanced Neural Network Applications
- Image Processing Techniques and Applications
- Antioxidants, Aging, Portulaca oleracea
Shanghai Architectural Design & Research Institute
2025
NetEase (China)
2020-2024
Nanjing University of the Arts
2024
South China University of Technology
2024
China Academy of Railway Sciences
2024
Beijing Academy of Agricultural and Forestry Sciences
2024
Shandong University of Science and Technology
2024
North China Electric Power University
2023
State Key Laboratory of Medicinal Chemical Biology
2021-2023
Nankai University
2021-2023
Density-based and classification-based methods have ruled unsupervised anomaly detection in recent years, while reconstruction-based are rarely mentioned for the poor reconstruction ability low performance. However, latter requires no costly extra training samples that is more practical, so this paper focuses on improving kind of method proposes a novel Omni-frequency Channel-selection Reconstruction (OCR-GAN) network to handle task perspective frequency. Concretely, we propose Frequency...
Prefabricated buildings have a series of advantages such as high efficiency, energy savings, and environmental protection, are being strongly promoted by the Chinese government. However, due to late start prefabricated in China, installation process components is relatively complex, leading difficulties quality safety control. A novel evaluation methodology integrating technique for order preference similarity ideal solution (TOPSIS) with prospect theory interval-valued Pythagorean fuzzy...
Online gaming is a multibillion dollar industry that entertains large, global population. Empowering online games with AI has made great success, however, ignores the explainability of black-box model makes less responsible and hinders its further development. In this article, we introduce discuss audience concept XAI (eXplainable AI) in games. We propose GXAI workflow, which combines strong expressiveness multiview data sources clear transparency models. present four specific classifiers...
Type 2 diabetes (T2D) is a chronic, burdensome disease that characterized by disordered insulin sensitivity and disturbed glucose/lipid homeostasis. Berberine (BBR) has multiple therapeutic actions on T2D, including regulation of glucose lipid metabolism, improvement energy expenditure. Recently, the function BBR fibroblast growth factor 21 (FGF21) been identified. However, if ameliorates T2D through FGF21, underlying mechanisms remain unknown. Herein, we used wild type (WT) FGF21 global...
Ochratoxin A (OTA) is a common environmental pollutant found in variety of foods and grains, excessive OTA consumption causes serious global health effects on animals humans. Astaxanthin (AST) natural carotenoid that has anti‐inflammatory, antiapoptotic, immunomodulatory, antitumor, antidiabetes, other biological activities. The present study aimed at investigating the AST OTA‐induced cecum injury its mechanism action. Eighty C57 mice were randomly divided into four groups, including control...
Recently Transformer models is new direction in the computer vision field, which based on self multihead attention mechanism. Compared with convolutional neural network, this uses self-attention mechanism to capture global contextual information and extract more strong features by learning association relationship between different features, has achieved good results many tasks. In face-based age estimation, some facial patches that contain rich age-specific are critical estimation task. The...
Abstract Cell totipotency and pluripotency are the cellular basis for root regeneration in Platycladus orientalis cuttings, of adventitious roots is a key determinant improving stem-cutting. However, physiological regulation formation still ambiguous. In this research, primordia initiation organogenesis were histologically observed, dynamic alterations soluble proteins monitored, Tandem Mass Tag protein profiling during development was carried out. It explicitly shown that primordium...
Online gaming is one of the most successful applications having a large number players interacting in an online persistent virtual world through Internet. However, some cheating gain improper advantages over normal by using illegal automated plugins which has brought huge harm to game health and player enjoyment. Game industries have been devoting much efforts on detection with multiview data sources achieved great accuracy improvements applying artificial intelligence (AI) techniques....
Online games make up the largest segment of booming global game market in terms revenue as well players. Unlike that sell at one time for profit, online money from in-game purchases by a large number engaged Therefore, Customer Lifetime Value (CLTV) is particularly vital companies to improve marketing decisions and increase revenues. Nowadays, virtual worlds are becoming increasingly innovative, complex, diverse, CLTV massive players highly personalized. That is, different may have very...
The reduction of insulin resistance or improvement sensitivity is the most effective treatment for type 2 diabetes (T2D). We previously reported that Nogo-B receptor (NGBR), encoded by NUS1 gene, required attenuating hepatic lipogenesis blocking nuclear translocation liver X alpha, suggesting its important role in regulating lipid metabolism. Herein, we demonstrate NGBR expression was decreased obesity-associated T2D patients and db/db mice. knockout mouse hepatocytes resulted increased...
Matchmaking is a core task in e-sports and online games, as it contributes to player engagement further influences the game's lifecycle. Previous methods focus on creating fair games at all times. They divide players into different tiers based skill levels only select from same tier for each game. Though this strategy can ensure matchmaking, not always good engagement. In paper, we propose novel Engagement-oriented (EnMatch) framework simultaneously enhance Two main issues need be addressed....
Massive multiplayer online role-playing games (MMORPG) have been becoming one of the most popular and exciting games. In recent years, a cheating phenomenon called real money trading (RMT) has arisen damaged fantasy world in many ways. RMT is sale in-game items, currency, or even characters to earn money, breaking balance game economy ecosystem damaging experience. Therefore, some studies emerged address problem detection. However, they cannot well handle label uncertainty practice, where...
Accurately predicting the binding affinities between Human Leukocyte Antigen (HLA) molecules and peptides is a crucial step in understanding adaptive immune response. This knowledge can have important implications for development of effective vaccines design targeted immunotherapies. Existing sequence-based methods are insufficient to capture structure information. Besides, current lack model interpretability, which hinder revealing key amino acids two molecules. To address these...
Calculation methods have a critical role in the precise sorting of medical images. Particle swarm optimization (PSO) is widely used approach clinical centers and for other applications as it can disentangle errors attached spaces. In this work, new model image segmentation proposed through an improved algorithm.A novel multi-objective algorithm was configured, named "multi-objective mathematical programming" (MOMP), based on normalized normal constraint method (NNCM). model, applied to...
This paper studies the task of detecting bots for online mobile games. Considering fact lacking labeled cheating samples and restricted available data in real detection systems, we aim to study finger operations captured by screen sensors infer potential an unsupervised way. In detail, introduce a Transformer-style model, namely FingFormer. It format graph structure order capture spatial temporal relatedness between two hands' operations. To optimize model way, contrastive learning...
Face-based age estimation strongly depends on deep residual networks (ResNets), used as the backbone in relevant research. However, ResNet-based methods ignore importance of some large-scale facial information and other attributes. Inspired by attention mechanism, a multi-task learning framework for face-based called multi-scale is proposed. First, authors embed alternative strategy structure dilated convolution into ResNet34 to construct module (MSA) improve network's receptive field, which...
Faced with saturated market and fierce competition of online games, it is great value to analyze the causes player churn for improving game product, maintaining retention. A large number research efforts on analysis have been made into prediction, which can achieve a sound accuracy benefiting from booming AI technologies. However, publishers are usually unable apply high-accuracy prediction methods in practice preventing or relieving due lack specific decision support (e.g., why they leave...
A novel skin detection method in JPEG compressed domain has been proposed this paper. Color and texture features of the image blocks are extracted from entropy decoded DCT coefficients firstly. Then, data mining method, i.e. decision tree, is applied to establish color model describe relationship between results, afterwards, initial regions detected based on model. The finally, segmented through region growing method. Experimental results show that, compared with SPM (skin probability map)...
Most pornographic image recognition researches focus on detection accuracy. However, as the highly increasing of web data, speed becomes a new consideration. In this paper, issue is discussed from following two aspects: 1) feature extraction in compressed domain and 2) classifier design, then simple, novel yet effective method proposed, which based multi-cost sensitive decision tree. More specifically, some features, including: features skin color region, results retrieval, face regions...
With the emerging of smartphones, mobile games have attracted billions players and occupied most share for game companies. On other hand, cheating, aiming to gain improper advantages by using programs that simulate players' inputs, severely damages game's fairness harms user experience. Therefore, detecting cheating is great importance Many PC game-oriented detection methods been proposed in past decades, however, they can not be directly adopted due concern privacy, power, memory...