相关论文: AHMSA-Net: Adaptive Hierarchical Multi-Scale Atten…

Micro-expressions (MEs) are brief, involuntary facial movements that reveal genuine emotions, offering valuable insights for psychological assessment and criminal investigations. Despite significant progress in automatic ME recognition…

Discovering molecules with desirable molecular properties, including ADMET profiles, is of great importance in drug discovery. Existing approaches typically employ deep learning models, such as Graph Neural Networks (GNNs) and Transformers,…

3D object detection in point cloud data remains a challenging task due to the sparsity and lack of global structure inherent in the input. In this work, we propose a novel Multi-Scale Attention (MSA) mechanism integrated into the 3DETR…

Transformer-based methods have demonstrated excellent performance on super-resolution visual tasks, surpassing conventional convolutional neural networks. However, existing work typically restricts self-attention computation to…

Existing multi-scale solutions lead to a risk of just increasing the receptive field sizes while neglecting small receptive fields. Thus, it is a challenging problem to effectively construct adaptive neural networks for recognizing various…

In orthogonal frequency division multiplexing (OFDM), accurate channel estimation is crucial. Classical signal processing-based approaches, such as linear minimum mean-squared error (LMMSE) estimation, often require second-order statistics…

Recently, deep convolutional neural network (CNN) have been widely used in image restoration and obtained great success. However, most of existing methods are limited to local receptive field and equal treatment of different types of…

Compressed sensing (CS) is a challenging problem in image processing due to reconstructing an almost complete image from a limited measurement. To achieve fast and accurate CS reconstruction, we synthesize the advantages of two well-known…

Micro-expression recognition plays a pivotal role in understanding hidden emotions and has applications across various fields. Traditional recognition methods assume access to all training data at once, but real-world scenarios involve…

Micro-expression recognition (MER) is a challenging task due to the subtle and fleeting nature of micro-expressions. Traditional input modalities, such as Apex Frame, Optical Flow, and Dynamic Image, often fail to adequately capture these…

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…

Micro-expression (ME) recognition plays a crucial role in a wide range of applications, particularly in public security and psychotherapy. Recently, traditional methods rely excessively on machine learning design and the recognition rate is…

Micro-expression recognition is one of the most challenging topics in affective computing. It aims to recognize tiny facial movements difficult for humans to perceive in a brief period, i.e., 0.25 to 0.5 seconds. Recent advances in…

Micro-expressions (MEs) are spontaneous, unconscious facial expressions that have promising applications in various fields such as psychotherapy and national security. Thus, micro-expression recognition (MER) has attracted more and more…

Spatial-temporal feature learning is of vital importance for video emotion recognition. Previous deep network structures often focused on macro-motion which extends over long time scales, e.g., on the order of seconds. We believe…

We present SparseAttnNet, a new hierarchical attention-driven framework for efficient image classification that adaptively selects and processes only the most informative pixels from images. Traditional convolutional neural networks…

The traditional ingle-scale U-Net often leads to the loss of spatial information during deblurring, which affects the deblurring accracy. Additionally, due to the convolutional method's limitation in capturing long-range dependencies, the…

Channel attention mechanisms endeavor to recalibrate channel weights to enhance representation abilities of networks. However, mainstream methods often rely solely on global average pooling as the feature squeezer, which significantly…

The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is often sparse, existing static sparse methods cannot adapt to task- or input-dependent…