Incomplete Multi-View Clustering (IMVC) is a promising topic in multimedia as it breaks the data completeness assumption. Most existing methods solve IMVC from the perspective of graph learning. In contrast, self-representation learning enjoys a superior ...

In contemporary times, artificial intelligence is extensively applied across domains, concurrently raising concerns about privacy breaches. In response, federated learning has emerged as a promising solution that allows multiple parties to ...

• Propose a fuzzy clustering-based FL framework for the under utilization of data.
• Propose a recursive bi-partitioning clustering algorithm for client partitioning.
• Design a model fusion strategy to enhance the performance of ...

Partial Label Learning (PLL) is a typical weakly supervised learning task, which assumes each training instance is annotated with a set of candidate labels containing the ground-truth label. Recent PLL methods adopt identification-based disambiguation to ...

Multiple-instance learning (MIL) is a significant weakly supervised learning problem, where the training data consists of bags containing multiple instances and bag-level labels. Most previous MIL research required fully labeled bags. However, collecting ...

Contrastive learning improves the performance of sequential recommendation models by mining self-supervised information and mitigating the impact of data sparsity and noise interference. Existing contrastive sequential recommendation models pull ...

Sequential Recommendation (SR) models with auxiliary tasks of contrastive learning have achieved remarkable progress in recent years, which can effectively mine the self-supervised signals to mitigate the data sparsity problem. However, current ...

Digital platforms have become central in job search. Job-seekers’ experiences with these platforms, however, is a relatively new research area. This paper presents findings from 27 interviews with US low-income job-seekers. Job-seekers encountered many ...

Node attack plays a vital role in evaluating the reliability of large scale infrastructure networks, which has attracted intensive research interests. Unfortunately, most of them focus on single node attack. Multi-node attack based on MBA (Module ...

Log-based anomaly detections have shown huge commercial potential in system maintenance. However, existing methods encounter two practical challenges. Firstly, they struggle to maintain consistent performance when dealing with evolving logs over ...

• An optimized algorithm is designed for log templates generation and compression.
• A Wide & Deep model is designed for log-based anomaly detection.
• Our method achieves higher peformance and robustness compared with existing methods.

• FishTrack, a transformer-based, joint multi-fish tracking method is proposed.
• An Encoder is designed to fuse the historical position information iteratively.
• Appearance and motion models are decoded in a decoupled manner.
• A ...

Tracking the fish is a key step in analyzing fish behavior, evaluating their health levels, and warning of abnormal water quality, so it is of significant importance for intelligent monitoring in fish farming. However, multi-object tracking for ...

Small Unmanned Aerial Vehicles (UAVs) are becoming potential threats to security-sensitive areas and personal privacy. A UAV can shoot photos at height, but how to detect such an uninvited intruder is an open problem. This article presents mmHawkeye, a ...

Cancellable biometrics is essential for preserving sensitive biometric information from potential exposure. Existing studies usually convert real-valued biometric vectors into protected templates by randomly generated transformation keys. However, this ...

Recent studies have demonstrated that malicious adversaries are capable of fingerprinting Internet of Things (IoT) devices in a smart home and further causing privacy breaches. However, many existing anti-fingerprinting schemes, either by traffic padding ...

This article investigates how and why the traditional on-demand service (i.e., taxies) and ridesharing platforms (e.g., Uber) perform in contexts of urban uncertainty. We consider different types of unexpected urban anomalies and collect large-scale trip ...

Urban anomalies bring uncertainties to society, urban transportation systems, and businesses. Some urban anomalies, such as no-notice and/or unpredictable terrorist attacks or other urban strikes, if not handled in timely ways may result in loss of life ...

Partial-Label Learning (PLL) is an important weakly supervised learning task that assumes each training instance is annotated with a set of candidate labels. In recent years, self-training PLL models, which learn label confidence vectors and train ...

The evolving unknown cyberattacks have rapidly expanded the cyber threat landscape. Identifying unknown cyberattacks, therefore, remains a challenging issue, compounded by the widespread implementation of emerging technologies, such as 5G, ...

• The artificial immunity based intrusion detection effectively detects unknown attacks.
• Possible unknown attacks are created by evolution algorithm for generating detectors.
• The filtering mechanism designed for evolved antigens ...

Recent years have witnessed an increased attack surface of the Industrial Internet of Things (IIoT), as the deep convergence of the Internet of Things (IoT) and other information and communications technologies (ICTs). However, the massive ...

• Presenting a novel artificial immunity based distributed and fast anomaly detection system for IIoT.
• Designing a new negative selection based hyper-dimensional anomaly detector generation model.
• Crafting a point-hyperspace tree ...

Emerging as a promising distributed learning paradigm, federated learning (FL) has been widely adopted in many fields. Nonetheless, a big challenge for FL in real-world implementation is Byzantine attacks, where compromised clients can mislead or ...

• Design a new federated learning architecture supporting various deep learning models.
• Craft a ‘phishing’ method to detect Byzantine attacks in federated learning.
• Present a Bayesian inference-based mechanism to evaluate the ...

Existing micro-video recommendation models exploit the interactions between users and micro-videos and/or multi-modal information of micro-videos to predict the next micro-video a user will watch, ignoring the information related to vloggers, i.e.,...