As privacy concerns and regulatory constraints on data protection continue to grow, the distribution of collected data has become more dispersed, resembling a ”data silo” style. To harness these data effectively without exchanging raw data, ...

• Introduced GANFAT for robust federated learning with skewed label distribution.
• Enhanced robustness against FGSM attacks by 9.30% on SVHN compared to FedRBN.
• Achieved 6.68% improvement in natural accuracy on CIFAR-100 over CalFAT.

Despite extensive algorithms for epilepsy prediction via machine learning, most models are tailored for offline scenarios and cannot handle actual scenarios where data changes over time. Catastrophic forgetting(CF) for learned ...

• Proposed Patient-IL adapts to dynamic patient increase for seizure prediction, facilitating EEG-based incremental learning studies.
• Proposed MP strategy tackles CF in epilepsy prediction due to EEG data interference, integrating ...

The acoustic levitation technology expands the possibility of non-contact mass measurements, avoiding contact contamination and loss, particularly for tiny objects. Current acoustic levitated object mass estimation methods focus on the mechanism ...

Image super-resolution reconstruction (SR) is an important ill-posed problem in low-level vision, which aims to reconstruct high-resolution images from low-resolution images. Although current state-of-the-art methods exhibit impressive ...

Display Omitted

Teaching popular science in primary school science courses has gained significant attention due to the national strategy for promoting science and education. 12.5% of the sixth-grade science curriculum is focused on astronomical content, but the ...

Existing learning-based image deblurring algorithms tend to focus on single source of image information, and the network structure and dynamic scene blur characteristics make it difficult to recover the missing details of the image. Therefore, a ...

• We propose a cascading Transformer to address the computational bottleneck of the Transformer in handling complex tasks with blurry images.
• We propose the Deep Separable Attention (DSA) mechanism to replace the vanilla self-attention ...

In dynamic scenes, motion blur can often occur, which is non-uniform and can be difficult to remove. Recently, the Transformer has shown excellent performance in various image-related tasks such as classification, recognition, and segmentation. ...

In near-field applications, 3-D imaging with the millimeter-wave multiple-input-multiple-output (MIMO) array provides accurate reconstruction with high dynamic range. However, current algorithms make it difficult to process multidimensional echo ...

Strong infrared radiation interference is a common type of interference in optoelectronic countermeasures. An optical system exposed to strong light would disrupt the acquisition of image information and even damage the device. In this paper, we aim to ...

Inter-organizational cooperation in innovation has evolved into a complex form featuring multilayer network interactions. By collecting diverse and heterogeneous data on cooperative innovation, the paper constructs a complex multilayer network ...

• A comprehensive topology integration scheme for Zero-Shot Learning (ZSL).
• A strong topology-based ZSL benchmark with state-of-the-art performance.
• Exploration of the topological validity within/across different modalities.

Zero-shot learning (ZSL) aims to discriminate object categories through the identification of their attributes and has received much attention for its capability to predict unseen categories without collecting training data. Recently, excellent ...

The project portfolio selection problem (PPSP) is closely tied to achieving the strategic objectives of an enterprise. However, due to limited budgetary constraints, the number of available projects is restricted. Moreover, the project portfolio ...

The virtual try-on technology can satisfy the demands for online shopping and help consumers experience online clothes through image generation technology. Compared with image-based try-on, the 3D virtual try-on methods can realize the multi-...

Various optimal gradient-based algorithms have been developed for smooth nonconvex optimization. However, many nonconvex machine learning problems do not belong to the class of smooth functions and therefore the existing algorithms are sub-optimal. ...

Many important machine learning applications involve regularized nonconvex bi-level optimization. However, the existing gradient-based bi-level optimization algorithms cannot handle nonconvex or nonsmooth regularizers, and they suffer from a high ...$\stackrel{}{\mathcal{}}{}^{\mathrm{}}{}^{\mathrm{}}$

The objective of the nurse rostering problem (NRP) is to obtain a scheduling plan that optimizes the allocation of human resources, effectively reducing work pressure on nurses and improving work efficiency and quality. Because various ...

• An attempt to apply neural network to solve nurse rostering problem.
• The neural ...

The Markov game is a popular reinforcement learning framework for modeling competitive players in a dynamic environment. However, most of the existing works on Markov games focus on computing a certain equilibrium following uncertain interactions among ...

Position detection is essential for precise contactless manipulation as it can play an important role in analyzing the behavior patterns and motion regularities of levitated objects. However, traditional detection methods have several limitations, ...

Constrained Markov game is a fundamental problem that covers many applications, where multiple agents compete with each other under behavioral constraints. The existing literature has proved the existence of Nash equilibrium for constrained Markov games, ...

Audio deep synthesis techniques have been able to generate high-quality speech whose authenticity is difficult for humans to recognize. Meanwhile, many anti-spoofing systems have been developed to capture artifacts in the synthesized speech that are ...