相关论文: Modeling Selective Feature Attention for Represent…

Sequential recommendation (SR) systems excel at capturing users' dynamic preferences by leveraging their interaction histories. Most existing SR systems assign a single embedding vector to each item to represent its features, and various…

Recent Transformer-based diffusion models have shown remarkable performance, largely attributed to the ability of the self-attention mechanism to accurately capture both global and local contexts by computing all-pair interactions among…

This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV). In the proposed structure, the frame-level multi-task learning along with the…

The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training. Efficient transformers, on the other hand, often rely on…

Existing methods for few-shot speaker identification (FSSI) obtain high accuracy, but their computational complexities and model sizes need to be reduced for lightweight applications. In this work, we propose a FSSI method using a…

Vision Transformers have achieved impressive performance in video classification, while suffering from the quadratic complexity caused by the Softmax attention mechanism. Some studies alleviate the computational costs by reducing the number…

Identifying anomalies has become one of the primary strategies towards security and protection procedures in computer networks. In this context, machine learning-based methods emerge as an elegant solution to identify such scenarios and…

Softmax attention is the principle backbone of foundation models for various artificial intelligence applications, yet its quadratic complexity in sequence length can limit its inference throughput in long-context settings. To address this…

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Attention mechanisms underpin the computational power of Transformer models, which have achieved remarkable success across diverse domains. Yet understanding and extending the principles underlying self-attention remains a key challenge for…

This paper explores the application of spiking neural networks (SNNs), known for their low-power binary spikes, to bearing fault diagnosis, bridging the gap between high-performance AI algorithms and real-world industrial scenarios. In…

The trade-off between feature representation power and spatial localization accuracy is crucial for the dense classification/semantic segmentation of aerial images. High-level features extracted from the late layers of a neural network are…

Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…

Attention mechanisms are the core of foundation models, but their quadratic complexity remains a critical bottleneck for scaling. This challenge has driven the development of efficient attention mechanisms, with sparsity emerging as the…

Lightweight image super-resolution (SR) networks have the utmost significance for real-world applications. There are several deep learning based SR methods with remarkable performance, but their memory and computational cost are hindrances…

Recently, it has been demonstrated that the performance of a deep convolutional neural network can be effectively improved by embedding an attention module into it. In this work, a novel lightweight and effective attention method named…

Speech self-supervised learning (SSL) represents has achieved state-of-the-art (SOTA) performance in multiple downstream tasks. However, its application in speech enhancement (SE) tasks remains immature, offering opportunities for…

Aggregating features in terms of different convolutional blocks or contextual embeddings has been proven to be an effective way to strengthen feature representations for semantic segmentation. However, most of the current popular network…

Deep learning-based models are utilized to achieve state-of-the-art performance for recommendation systems. A key challenge for these models is to work with millions of categorical classes or tokens. The standard approach is to learn…

Modern data analysis pipelines are becoming increasingly complex due to the presence of multi-view information sources. While graphs are effective in modeling complex relationships, in many scenarios a single graph is rarely sufficient to…