A5100453383- Mobile and Web Applications
- Face recognition and analysis
- Advanced Steganography and Watermarking Techniques
- Video Analysis and Summarization
- Biometric Identification and Security
- Advanced Image and Video Retrieval Techniques
- Service-Oriented Architecture and Web Services
- Recommender Systems and Techniques
- Digital Media Forensic Detection
- Privacy-Preserving Technologies in Data
- User Authentication and Security Systems
- Image Retrieval and Classification Techniques
- Web Data Mining and Analysis
- Generative Adversarial Networks and Image Synthesis
- Blockchain Technology Applications and Security
- Anomaly Detection Techniques and Applications
- Software System Performance and Reliability
- Cloud Computing and Resource Management
- Music and Audio Processing
- Advanced Malware Detection Techniques
- Expert finding and Q&A systems
- Caching and Content Delivery
- Advanced Software Engineering Methodologies
- Network Security and Intrusion Detection
- Assisted Reproductive Technology and Twin Pregnancy
Nanjing University of Aeronautics and Astronautics
2023-2025
Yunnan Population and Family Planning Research Institute
2025
First People's Hospital of Yunnan Province
2024-2025
Ministry of Education of the People's Republic of China
2024
Jilin Province Science and Technology Department
2024
Shandong Normal University
2023-2024
China Southern Power Grid (China)
2024
Xinjiang University
2024
Jiangxi University of Finance and Economics
2024
Jilin University
2023-2024
In this paper, we propose Auracle, a wearable earpiece that can automatically recognize eating behavior. More specifically, in free-living conditions, when and for how long person is eating. Using an off-the-shelf contact microphone placed behind the ear, Auracle captures sound of chewing as it passes through bone tissue head. This audio data then processed by custom analog/digital circuit board. To ensure reliable (yet comfortable) between skin, all hardware components are incorporated into...
The tremendous progress in deep learning has enabled to extract soft-biometric attributes from faces, which raises privacy concerns over images collected for face recognition. Advances toward attribute have been able conceal multiple while preserving identity information but suffer limitations: they 1) only consider a few and 2) fail support reversibility preservation. To break these limitations, we design reversible privacy-preserving scheme various attributes, called preservation (RAPP)....
Offchain networks emerge as a promising solution to address the scalability challenge of blockchain. Participants make payments through offchain instead committing transactions on-chain. Routing is critical performance networks. Existing solutions use either static routing with poor or dynamic high overhead obtain channel balance information. In this paper, we propose Flash, new that leverages unique characteristics in strike better tradeoff between path optimality and probing overhead. By...
The effect of pre-pregnancy intrauterine device (IUD) use on subsequent preterm birth (PTB) remains unclear. We aim to investigate the association between IUD before pregnancy and PTB. A total 240,437 women who participated in National Free Preconception Health Examination Project (NFPHEP) Yunnan from 2013 2019 were included study. All study participants classified into three groups according their contraceptive methods: non-method users, other method users. used a multivariable Poisson...
Massive face images collected in smart surveillance and social networks are vulnerable to malicious access, thus compromising individual privacy. Existing schemes have been able protect privacy while preserving a certain level of identifiability, but different limitations, e.g., the lack strong transferability or inability retain irrelevant attributes. This letter proposes novel protection scheme via virtual identity transformation, which guarantees high identifiability. We first solve...
Steganography has received massive attention from the information-hiding community due to its excellent security for covert communication systems. Existing work focuses on improving single-modal media while cross-modal is less explored. However, interaction become a prevalent social manner current networks, which arises potential behavioral issues of steganography. In this letter, we propose novel text steganography explore practicability The proposed scheme composed with image encoder,...
In recent years, research in social recommendation has shown that modeling implicit relations effectively alleviates data sparsity and cold-start problems. However, related often overlooks the influence of user item rating biases when constructing relations. The divergence systems evaluation standards results ratings displaying starkly contrasting extremes, making it difficult to identify among users (or items) fulfill requirements personalized recommendations. To this end, we propose a...
The advent of artificial intelligence-generated content (AIGC) represents a pivotal moment in the evolution information technology. With AIGC, it can be effortless to generate high-quality data that is challenging for public distinguish. Nevertheless, proliferation generative across cyberspace brings security and privacy issues, including leakages individuals media forgery fraudulent purposes. Consequently, both academia industry begin emphasize trustworthiness data, successively providing...
Soccer highlight detection is an active research topic in recent years. One of the difficult problems how to effectively fuse multi-modality cues, i.e. audio, visual and textual information, improve performance. This paper proposes a novel two-dependence Bayesian network (2d-BN) based fusion approach soccer detection. 2d-BN particular which assumes that each variable depends on two other variables at most. Through this assumption, can not only characterize relationships among features but...
To solve the problems of low matching degree, long tracking time, and accuracy multi-target in process athlete motion trajectory using deep learning technology, a new model was proposed this study. The study first optimized current object detection algorithm basketball, utilized hybrid attention mechanism to extract features, improved non-maximum suppression strategy. Then, branch network introduced improve residual identity recognition proposed. Finally, designed by combining model....
Vision is the most important sense for people, and it also one of main ways cognition. As a result, people tend to utilize visual content capture share their life experiences, which greatly facilitates transfer information. Meanwhile, increases risk privacy violations, e.g., an image or video can reveal different kinds privacy-sensitive Researchers have been working continuously develop targeted protection solutions, there are several surveys summarize them from certain perspectives....
The fast performance decay with potentials is an immense obstacle to achieving efficient electrocatalytic N2 reduction reaction (eNRR), which attributed the competition from hydrogen evolution. However, potential-dependent competitive behavior and mechanism are still under debate. Herein, by means of constant-potential/hybrid-solvent framework, we revisited potential-dependence adsorption between H on FeN4 RuN4 catalysts, for first time defined adsorption, mediation, H2 evolution as three...
The requirement of integrating a large number heterogeneous cyber and physical entities in cyber-physical systems (CPSs) motivates the use service-oriented architecture (SOA), which can support composition two or more available functionalities to form complex service. This paper presents context-sensitive service framework CPS with dependability requirements. Firstly, an ontology model is proposed for specification capabilities entities. Then we propose spanning tree (SST) based hierarchical...