Search Results

In-context Learning (ICL) has achieved notable success in large language models (LLMs) applications. By adding only a few input-output pairs demonstrating a new task, LLMs can efficiently learn the task during inference without modifying their ...

To overcome the challenges of complex time-varying satellite channels and severe inter-user interference in non-orthogonal multiple access (NOMA), rational power allocation and accurate multi-user joint detection methods are essential. In this paper, a ...

To prevent misuse of privacy, numerous anonymous authentication schemes with linkability and/or traceability have been proposed to ensure different types of accountabilities. Previous schemes cannot simultaneously achieve public linking and ...

The multi-modal tracker realizes robust tracking by complementing the unique information between modalities. However, there is still a serious data deficiency problem in multi-modal tracking, which leads to inadequate learning of fusion modules ...

• We propose a universal multi-modal tracking framework, named MixRGBX.
• We introduce a symmetric complementary fusion module for arbitrary modality fusion.
• Our model has achieved state-of-the-art results in various multi-modal ...

Indoor localization using wireless fidelity (WiFi) fingerprint has attracted considerable attention due to its extensive deployment and low cost. Most indoor fingerprint localization methods could be computationally inefficient and behave with ...

• A particle swarm optimized indoor positioning in the online stage is proposed.
• The fitness function is the sum of standard deviations between two fingerprints.
• The testing fingerprint compares with generated one by IDW, not the ...

Voice Conversion (VC) can manipulate the source speaker's identity of speech signal to make it sound like some specific target speaker, which makes it harder for a human being or a speaker verification/identification system to trace the real ...

Adversarial examples reveal the vulnerability of neural networks, thereby increasing the demand for formal verification of their robustness. Verification methods employing branch and bound technique have shown excellent performance for this task ...

With the advance of deep learning, adversarial attack and defense has becoming a hot research topic. However, existing defense methods rely on the prior knowledge of the adversarial attacks, and are also vulnerable to adaptive attacks. In this ...

• An adversarial defense framework by fusing downsampling and upsampling.
• Pairwise random downsampling to resist normal and adaptive adversarial attacks.
• A new deep learning architecture to perform speech super-resolution.

A key step to single channel speech enhancement is the orthogonal separation of speech and noise. In this paper, a dual branch complex convolutional recurrent network (DBCCRN) is proposed to separate the complex spectrograms of speech and noises ...

• A dual-branch network to estimate speech and noise simultaneously.
• Scale-aware loss to ensure speech waveforms with correct scale.
• A new evaluation metric to measure the scale error.
• The proposed method achieves state-of-the-...

In the field of coherent direction of arrival (DOA) estimation, traditional subspace-based algorithms encounter difficulties due to the loss of rank in the signal covariance matrix. To mitigate this concern, we introduce a novel technique called ...

The negative effects of media multitasking have been addressed in previous studies, and the widespread adoption of online learning to control the outbreak of COVID-19 has further increased concerns about the media use, especially media ...

Most existing voice conversion methods focus primarily on separating speech content from speaker information while overlooking the decoupling of pitch information. Additionally, the quality of converted speech significantly degrades when the ...

Statistical model checking (SMC) is a simulation-based formal verification technique to deal with the scalability problem faced by traditional model checking. The main workflow of SMC is to perform iterative simulations. The number of simulations depends ...

RGBT tracking has been widely used in various fields such as robotics, surveillance processing, and autonomous driving. Existing RGBT trackers fully explore the spatial information between the template and the search region and locate the target based on ...

Unsupervised learning (UL) is one of the most important areas in artificial intelligence. UL systems are capable of learning patterns from unlabeled data and playing an increasingly critical role in many fields. Therefore, more and more attention ...

Federated learning (FL) is a distributed machine learning framework that aims to provide privacy for local datasets while learning a global machine learning model. However, the updates exchanged in FL may indirectly reveal information about the ...

The rapid evolution of society, changing industrial structures, and the advancement of intelligent technologies pose new challenges and opportunities for specialty colleges and universities in nurturing talent. This paper firstly introduces the status ...

Attribute-based anonymous credential schemes have been envisioned with the motivation to allow users to prove the possession of their attributes interactively with service providers anonymously. So far, three major properties: delegation, ...