Related papers: FGA: Fourier-Guided Attention Network for Crowd Co…

Transformer-based pre-trained models, such as BERT, have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, deploying these models can be prohibitively costly, as the…

Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers. To increase the receptive field, Graph…

Crowd counting has been widely studied by computer vision community in recent years. Due to the large scale variation, it remains to be a challenging task. Previous methods adopt either multi-column CNN or single-column CNN with multiple…

Crowd counting in single-view images has achieved outstanding performance on existing counting datasets. However, single-view counting is not applicable to large and wide scenes (e.g., public parks, long subway platforms, or event spaces)…

The attention mechanism forms the foundational blocks for transformer language models. Recent approaches show that scaling the model achieves human-level performance. However, with increasing demands for scaling and constraints on hardware…

The U-Net architecture and its variants have remained state-of-the-art (SOTA) for retinal vessel segmentation over the past decade. In this study, we introduce a Full-Scale Guided Network (FSG-Net), where a novel feature representation…

In real-world crowd counting applications, the crowd densities in an image vary greatly. When facing density variation, humans tend to locate and count the targets in low-density regions, and reason the number in high-density regions. We…

Attention is a general reasoning mechanism than can flexibly deal with image information, but its memory requirements had made it so far impractical for high resolution image generation. We present Grid Partitioned Attention (GPA), a new…

Graph Transformers (GTs) have demonstrated superior performance compared to traditional message-passing graph neural networks in many studies, especially in processing graph data with long-range dependencies. However, GTs tend to suffer…

Our work proposes a novel deep learning framework for estimating crowd density from static images of highly dense crowds. We use a combination of deep and shallow, fully convolutional networks to predict the density map for a given crowd…

Accurate spectrum prediction is crucial for dynamic spectrum access (DSA) and resource allocation. However, due to the unique characteristics of spectrum data, existing methods based on the time or frequency domain often struggle to…

Recently Transformer-based hyperspectral image (HSI) change detection methods have shown remarkable performance. Nevertheless, existing attention mechanisms in Transformers have limitations in local feature representation. To address this…

Video crowd localization is a crucial yet challenging task, which aims to estimate exact locations of human heads in the given crowded videos. To model spatial-temporal dependencies of human mobility, we propose a multi-focus Gaussian…

In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.…

Fine-grained visual classification (FGVC) is becoming an important research field, due to its wide applications and the rapid development of computer vision technologies. The current state-of-the-art (SOTA) methods in the FGVC usually…

Radar gait recognition is robust to light variations and less infringement on privacy. Previous studies often utilize either spectrograms or cadence velocity diagrams. While the former shows the time-frequency patterns, the latter encodes…

While Graph Neural Networks have gained popularity in multiple domains, graph-structured input remains a major challenge due to (a) over-smoothing, (b) noisy neighbours (heterophily), and (c) the suspended animation problem. To address all…

Point cloud registration is a fundamental task in many applications such as localization, mapping, tracking, and reconstruction. Successful registration relies on extracting robust and discriminative geometric features. Though existing…

The channel attention mechanism is a useful technique widely employed in deep convolutional neural networks to boost the performance for image processing tasks, eg, image classification and image super-resolution. It is usually designed as…

This work introduced a novel GAN architecture for unsupervised image translation on the task of face style transform. A spectral attention-based mechanism is embedded into the design along with spatial attention on the image contents. We…