A5101704265- Anomaly Detection Techniques and Applications
- Adversarial Robustness in Machine Learning
- Parallel Computing and Optimization Techniques
- Advanced biosensing and bioanalysis techniques
- Machine Learning and ELM
- Interconnection Networks and Systems
- Machine Learning and Data Classification
- Explainable Artificial Intelligence (XAI)
- Cloud Computing and Resource Management
- Advanced Neural Network Applications
- Embedded Systems Design Techniques
- Biosensors and Analytical Detection
- Tactile and Sensory Interactions
- Real-Time Systems Scheduling
- Augmented Reality Applications
- Participatory Visual Research Methods
- Machine Learning in Bioinformatics
- Mobile Agent-Based Network Management
- Fire Detection and Safety Systems
- Spatial Cognition and Navigation
- Misinformation and Its Impacts
- bioluminescence and chemiluminescence research
- Cyberloafing and Workplace Behavior
- Face and Expression Recognition
- Hate Speech and Cyberbullying Detection
Guangzhou University
2024
Guangzhou Xinhua University
2024
University of Chinese Academy of Social Sciences
2023-2024
Chinese Academy of Social Sciences
2023-2024
Nanjing University of Finance and Economics
2023-2024
Communication University of China
2020-2024
Renmin University of China
2024
Central South University
2022
National University of Singapore
2021-2022
Fourth People's Hospital of Shenzhen
2011
3D deep learning has been increasingly more popular for a variety of tasks including many safety-critical applications. However, recently several works raise the security issues models. Although most them consider adversarial attacks, we identify that backdoor attack is indeed serious threat to systems but remains unexplored. We present attacks in point cloud with unified framework exploits unique properties data and networks. In particular, design two approaches on cloud: poison-label...
Abstract Tangible cultural heritage is rich in historical, artistic and scientific value, but due to its own characteristics the constraints of museum displays, key issue facing us today how utilize activate enhance experience learning interest audience. Focusing on Chinese treasure, chimes, this article innovatively proposes an interaction system based digital augmented projection somatosensory technology empower aesthetic expression knowledge dissemination chimes. On basis, a series...
Neural Code Intelligence -- leveraging deep learning to understand, generate, and optimize code holds immense potential for transformative impacts on the whole society. Bridging gap between Natural Language Programming Language, this domain has drawn significant attention from researchers in both research communities over past few years. This survey presents a systematic chronological review of advancements intelligence, encompassing 50 representative models their variants, more than 20...
Abstract Research has shown that spatial perception is not only one of the essential abilities for success in science, technology, engineering, and mathematics (STEM), but also closely related to quality human existence. However, a variety reasons, many students' skills are less than ideal. In recent years, various video games showing great potential as low‐cost effective training tools improve educational level cognitive skills. This paper presented novel serious strategy game named Magic...
User-facing applications running in modern datacenters exhibit irregular request patterns and are implemented using a multitude of services with tight latency requirements (30–250$\mu$s). These characteristics render existing energy-conserving techniques ineffective when processors idle due to the long transition time (order 100$\mu$s) from deep CPU core power state (C-state). While prior works propose management mitigate this inefficiency, we tackle it at its root AgileWatts (AW): new...
Zen is a treasure of the world's intangible cultural heritage (ICH), but nowadays it facing difficulties in dissemination. This paper presents an immersive experience space Flowing with by integrating HCI technology and mixed reality (MR). Audiences can explore interact four scenarios, as well meditate, philosophy. The pilot study shows that MR not only evokes users' interest participation also deepens their empathy or reflections. innovative way combining MR, ICH, enhances accessibility...
Abstract In the context of social media becoming users' primary access to information, such as news, incidental news exposure under influence algorithmic recommendation and its democratic consequences are worth studying. While studies on relationship between users’ online political participation have been widely explored, we know little about current mechanisms variable association in recommendations. This study examines mediating role awareness moderating effect intolerance uncertainty...
AbstractThis study investigated the relationship between childhood emotional abuse and gamebullying among youths, roles of mindfulness Machiavellianism in that relationship. The sample comprised 504 Chinese youths (female = 51.2%) who completed Childhood Emotional Abuse Scale, Gamebullying Mindful Attention Awareness Scale. Path analysis results indicated a history to predict gamebullying. Mindfulness mediated with be lower. higher. In our sample, demographic variables, including gender...
Abstract As the last node of data journalism creation, visual design plays a crucial role in transmission information. Exploring routes to improve quality at language and interaction design, this paper analyzes works won awards produced by well-known media from 2012 2019, discusses misunderstandings shortcomings current visualization practice. This presents improvement mapping, symbolic expression, level, interactive narration.
Abstract Training accurate and explainable models in limited time has been a longstanding challenge for classification problems. One of the most popular techniques to cope with this is support vector machine (SVM). Compared SVM, least squares (LSSVM) smooth more robust. However, LSSVM suffers from poor predictive performance high complexity when training large-scale high-dimensional datasets. In paper, we introduce sparse accelerated memory Broyden–Fletcher–Goldfarb–Shanno (SAL-BFGS)...
Trustworthy machine learning is of primary importance to the practical deployment deep models. While state-of-the-art models achieve astonishingly good performance in terms accuracy, recent literature reveals that their predictive confidence scores unfortunately cannot be trusted: e.g., they are often overconfident when wrong predictions made, or so even for obvious outliers. In this paper, we introduce a new approach self-supervised probing, which enables us check and mitigate...
Radio Frequency Identification (RFID) is generic term for technology employing radio waves detecting objects. RFID has wide application in payment systems, access control, asset tracking and other areas as many companies are using developing the technology's potential. As develops, it imports some new elements, one of which Java technology. now can be seen any links from tags to database centre. But performance still a main concern us. This paper shows good solution deal with efficiency...
Java is one of the most popular programming architectures because its platform-independence. A processor called "JOP" accelerates speed applications by executing bytecode instructions directly instead software emulation. However, in executable file need to be resolved before executed. JOP finishes this resolving procedure application compiling stage and generates a memory image run-time environment from class files. As result that, Java's outstanding features — platform-independence lost....
The scalability problem caused by the difficulty in annotating Person Re-identification(Re-ID) datasets has become a crucial bottleneck development of Re-ID.To address this problem, many unsupervised Re-ID methods have recently been proposed.Nevertheless, most these models require transfer from another auxiliary fully supervised dataset, which is still expensive to obtain.In work, we propose model based on Weakly Supervised Tracklets(WST) data various camera views, can be inexpensively...