Audio-Visual Segmentation (AVS) aims to segment sound sources from video frames using synchronized audio cues. This task requires not only localizing the sound sources within frames but also accurately delineating their shapes. Existing AVS methods often rely on assumptions of spatial-temporal consistency between audio-visual content and are typically designed for specific learning paradigms. However, this specialization limits their ability to handle multi-granularity supervision signals and and adapt to diverse task requirements. For this purpose, we propose a Cross-modal Spatial-Temporal Alignment (X-STA) network to alleviate spatial-temporal inconsistency and overcome paradigm-specific constraint. Our X-STA introduces three key components: a novel multi-stage Cross-modal Adapter (xAdapter) that transfers knowledge from a pre-trained SAM through multi-grained representation adaptation, an innovative Cross-modal Prompter (xPrompter) that provides geometry-aware constraints for AVS through dynamic prompting strategies, and a Cross-modal Self-supervised (xSelf) mechanism that refines temporal alignment and enables self-supervised AVS. These components collectively facilitate explicit reasoning about location and geometric shape of the sound source by refining the alignment of cross-modal spatial-temporal cues. Our method achieves competitive performance across several baselines on widely-used AVS datasets, demonstrating its effectiveness in addressing the complexities of AVS.

Explainable Fake News Detection (EFND) is a new challenge that aims to verify news authenticity and provide clear explanations for its decisions. Traditional EFND methods often treat the tasks of classification and explanation as separate, ignoring the fact that explanation content can assist in enhancing fake news detection. To overcome this gap, we present a new solution: the End-to-End Explainable Fake News Detection Network ( EExpFND ). Our model includes an evidence-claim variational causal inference component, which not only utilizes explanation content to improve fake news detection but also employs a variational approach to address the distributional bias between the ground truth explanation in the training set and the prediction explanation in the test set. Additionally, we incorporate a masked attention network to detail the nuanced relationships between evidence and claims. Our comprehensive tests across two public datasets show that EExpFND sets a new benchmark in performance. The code is available at https://anonymous.4open.science/r/EExpFND-F5C6 .

In major public health events such as the outbreak of COVID-19, it is crucial to design effective and efficient quarantine policies to minimize both the epidemic spread as well as the economic loss. Most prior works in the literature either only consider the epidemic control while ignoring the economic loss or just tell the percentage of users to quarantine without explicitly pointing out whom to quarantine. In addition, many assume that we have perfect knowledge of each user's health states at all times, and they are not equipped to handle super-large networks with more than 100 000 users. In this work, we consider those pandemics with incubation periods and assume that we are unable to know the exact health states of all users. We propose a method to estimate each user's probability of being infectious and then propose the basic minimum-loss quarantine (basic-MinLoQ) algorithm to jointly minimize the epidemic spread, the economic loss as well as the number of people in quarantine. For super-large networks with more than 100 000 nodes, we propose the subgraph minimum-loss quarantine (subgraph-MinLoQ) algorithm to reduce the computation complexity. Simulation results show that our basic-MinLoQ algorithm outperforms several prior works, including Netshield, Acquaintance, and GreedyDrop, in terms of epidemic control and reducing economic loss. While our proposed subgraph-MinLoQ algorithm can efficiently identify people to quarantine and control the epidemic spread in super-large networks with more than100 000 users.

Video streaming applications are rapidly proliferating, allowing users to browse, download, and share videos through platforms such as YouTube, Netflix, and Amazon. Media content providers are required to register copyrights on digital platforms. With the existence of blockchain technology, users can manage their data using a smart contract, which allows them to define access and search policies and use an instant payment system without a third party in a decentralized network. We propose a secure and reliable video sharing scheme based on blockchain, using cryptographic primitives to secure the information of streamers and viewers. The use of blockchain ensures reliability and prevents the manipulating or forging of multimedia content. A smart contract system is implemented to represent contractual actions once a given access condition is satisfied. Analysis of the scheme's security and performance demonstrates that it is reliable and efficient.

This paper addresses the problem of a single rumor source detection with multiple observations, from a statistical point of view of a spreading over a network, based on the susceptible-infectious model. For tree networks, multiple sequential observations for one single instance of rumor spreading cannot improve over the initial snapshot observation. The situation dramatically improves for multiple independent observations. We propose a unified inference framework based on the union rumor centrality, and provide explicit detection performance for degree-regular tree networks. Surprisingly, even with merely two observations, the detection probability at least doubles that of a single observation, and further approaches one, i.e., reliable detection, with increasing degree. This indicates that a richer diversity enhances detectability. For general graphs, a detection algorithm using a breadth-first search strategy is also proposed and evaluated. Besides rumor source detection, our results can be used in network forensics to combat recurring epidemic-like information spreading such as online anomaly and fraudulent email spams.

Suppose that a rumor originating from a single source among a set of suspects spreads in a network, how to root out this rumor source? With the a priori knowledge of suspect nodes and a snapshot observation of infected nodes, we construct a maximum a posteriori (MAP) estimator to identify the rumor source using the susceptible-infected (SI) model. We propose to use a notion of local rumor center to characterize Pc(n), the correct detection probability of the source estimator upon observing n infected nodes, in both the finite and asymptotic regimes, for regular trees of node degree δ. First, when all nodes are suspects, limn→∞Pc(n) grows from 0.25 to 0.307 as δ increases from three to infinity, a result first established in Shah and Zaman (2011, 2012) via a different approach; furthermore, Pc(n) monotonically decreases with n and increases with δ even in the finite-n regime. Second, when the suspect nodes form a connected subgraph of the network, limn→∞Pc(n) significantly exceeds the a priori probability if δ ≥ 3, and reliable detection is achieved as δ becomes sufficiently large; furthermore, Pc(n) monotonically decreases with n and increases with δ. Third, when there are only two suspect nodes, limn→∞Pc(n) is at least 0.75 if δ ≥ 3; and Pc(n) increases with the distance between the two suspects. Fourth, when there are multiple suspect nodes, among all possible connection patterns, that all the suspects form a single connected subgraph yields the smallest Pc(n). Our analysis leverages ideas from the Pólya's urn model in probability theory and sheds insight into the behavior of the rumor spreading process not only in the asymptotic regime but also for the general finite-n regime.

To cope with the ever increasing demand for bandwidth and increasing number of users, future wireless networks will be designed with the radio resource allocation techniques able to get good performance with low complexity and feedback. In this paper we study an allocation problem for OFDMA networks formulated with the objective of minimizing the load of each cell in the system or maximizing the number of accessing users subject to the constraint that each user meets its target rate. We formulate the two problem as one framework of finding the maximum weighted independent set (MWIS) in graph theory. In addition, we propose a minimal weighted-degree greedy (MWDG) algorithm. The control information requested to perform the allocation is limited and the computational burden is shared between the base station and the user equipments. Simulations have been carried out under constant bit rate traffic model and the results show MWDG has excellent performance and outperforms all other techniques.

ABSTRACT Rayleigh fading channel is widely modeled using sum‐of‐sinusoids simulators. In the paper, the construction method of an accuracy simulator is of concern. The intrinsic relationships between path gain, angle of incoming wave (angle of arrival), and initial phase are analyzed. At the same time, rules of simulator construction were proposed. According to these rules, the second‐order statistical properties of designed simulators match to the desired ones perfectly. Furthermore, our method can be an elicitation to generate simulators with correct high‐order statistical properties. In addition, a realization based on the construction method is designed to example how to use these construction rules. The new realization can be used to generate multiple uncorrelated fading waveforms for frequency‐selective fading channels, multiple‐input multiple‐output channels, and diversity combining scenarios. Copyright © 2011 John Wiley & Sons, Ltd.