• By leveraging the flexibility of fuzzy logic and the robust representation learning abilities of deep learning, the proposed system constructs an adaptable depth blur layering system.
• Furthermore, it enriches the system with higher-...

This study proposed the Deep Fuzzy Hierarchical System (DFHS) to solve the issue of rule explosion when modeling uncertain data with many dimensions. First, the data is classified into continuous and discrete space functions based on its value to ...

Graph Contrastive Learning (GCL), which learns node or graph representation from supervision signals derived from the graph data itself, has recently attracted extensive research attention and achieved great success. Remarkably, most of the ...

Non-autoregressive video captioning methods generate visual words in parallel but often overlook semantic correlations among them, especially regarding verbs, leading to lower caption quality. To address this, we integrate action information of ...

Video Shadow Detection (VSD) aims to detect the shadow masks with frame sequence. Existing works suffer from inefficient temporal learning. Moreover, few works address the VSD problem by considering the characteristic (i.e., boundary) of shadow. ...

For two graphs G and H, the Gallai–Ramsey number${\text{gr}}_k(G:H)$ is defined as the minimum integer n such that any k-edge-coloring of $K_n$ must contain either a rainbow copy of G or a monochromatic copy of H. In this paper, we obtain the exact values of ${\text{gr}}_k(...$${}_{\mathrm{}\mathrm{}}{}_{\mathrm{}}^{}{}_{\mathrm{}}$${}_{\mathrm{}}^{}$${}_{\mathrm{}}$

This workshop introduces generative AI applications for enterprise, with a focus on retrieval-augmented generation (RAG) systems. Generative AI is a field of artificial intelligence that can create new content and solve complex problems. RAG systems are ...

The hybrid platform is emerging into online retailing market based on reselling and direct selling, forming the dual-channel model composed of third-party operated and platform self-operated channels. To achieve structural matching between ...

BCH codes have been widely used in consumer devices, communication systems, and data storage systems. In this paper, we study the dimensions of four families of the BCH codes C ( q , n , δ , 0 ) of length n = q m + 1, where designed distances δ ...

By drawing inspiration from the computer vision domain, contrastive learning has emerged as another paradigm for unsupervised sentence embedding. By using contrastive learning, most recent sentence embedding methods have achieved promising ...

Many hashing algorithms including minwise hashing (MinHash), one permutation hashing (OPH), and consistent weighted sampling (CWS) generate integers of B bits. With k hashes for each data vector, the storage would be BXk bits; and when used for large-...

This paper addresses the problem of animating a person in static images, the core task of which is to infer future poses for the person. Existing approaches predict future poses in the 2D space, suffering from entanglement of pose action and ...

Display Omitted

Traffic flow prediction in spatio-temporal networks is a crucial aspect of Intelligent Transportation Systems (ITS). Existing traffic flow forecasting methods, particularly those utilizing graph neural networks, encounter limitations. When ...

• Introduction of a novel deep knowledge distillation model for enhanced traffic data analysis.
• Application of mutual learning and self-distillation modules for bidirectional knowledge transfer.
• Superior prediction accuracy validated ...

We examine the coefficients in front of Chern numbers for complex genera, and pay special attention to the Td 1 2-genus, the Γ-genus as well as the Todd genus. Some related geometric applications to hyper-Kähler and Calabi-Yau manifolds are ...

The application of deep convolutional neural networks (CNNs) makes the lightweight single image super-resolution (SISR) task develop rapidly in recent years. However, existing lightweight SISR networks for the terminals with limited computing ...

• We propose a powerful but lightweight blueprint residual network (LBRN).
• We propose a novel module named LBRB to learn high-frequency information.
• We propose an effective feature fusion residual block for discriminative feature.

With the continuous popularity of deep learning and representation learning, fast vector search becomes a vital task in various ranking/retrieval based applications, say recommendation, ads ranking and question answering. Neural network based ranking is ...

The enhancement of power transfer from the piezoelectric transducer to the load with a compact size is explored in this paper. Large physical inductors are no more required to create resonance in piezoelectric energy harvesting schemes while ...

Due to privacy, security, and costly labeling of images, unsupervised semantic segmentation with very few samples has become a promising direction, but still remains unexplored. This inspires us to introduce the few-sample unsupervised semantic ...

Railway intrusion seriously threatens railway safety and can cause enormous loss of life and property. Therefore, railway intrusion detection is crucial for the safety of railway operation. Among the current methods of intrusion detection, machine vision-...

In recent years, with the development of science and technology, the accuracy of online machine translation has been significantly improved, and subsequently many English majors have applied online machine translation tools in graduation thesis writing. ...

Significant advancements have been made in colorization in recent years, especially with the introduction of deep learning technology. However, challenges remain in accurately colorizing images under certain lighting conditions, such as shadow. ...