Related papers: Unifying Top-down and Bottom-up Scanpath Predictio…

Spatio-temporal alignment is crucial for temporal modeling of end-to-end (E2E) perception in autonomous driving (AD), providing valuable structural and textural prior information. Existing methods typically rely on the attention mechanism…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Recent neural models for image captioning usually employ an encoder-decoder framework with an attention mechanism. However, the attention mechanism in such a framework aligns one single (attended) image feature vector to one caption word,…

Recently, with the advance of deep Convolutional Neural Networks (CNNs), person Re-Identification (Re-ID) has witnessed great success in various applications. However, with limited receptive fields of CNNs, it is still challenging to…

Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled…

Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack of multi-scale…

The quadratic cost of attention in transformers motivated the development of efficient approaches: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in…

Many image understanding tasks involve identifying what is present and where it appears. However, tasks that address where, such as object discovery, detection, and segmentation, are often considerably more complex than image…

Attention modules for Convolutional Neural Networks (CNNs) are an effective method to enhance performance on multiple computer-vision tasks. While existing methods appropriately model channel-, spatial- and self-attention, they primarily…

Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each…

The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are…

The transformer architecture has catalyzed revolutionary advances in language modeling. However, recent architectural recipes, such as state-space models, have bridged the performance gap. Motivated by this, we examine the benefits of…

Recently, Transformer architecture has been introduced into image restoration to replace convolution neural network (CNN) with surprising results. Considering the high computational complexity of Transformer with global attention, some…

Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spatially-structured tasks. Existing approaches introduce…

The task of Stance Detection involves discerning the stance expressed in a text towards a specific subject or target. Prior works have relied on existing transformer models that lack the capability to prioritize targets effectively.…

In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features…

Human attention mechanisms often work in a top-down manner, yet it is not well explored in vision research. Here, we propose the Top-Down Attention Framework (TDAF) to capture top-down attentions, which can be easily adopted in most…

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Recently, the vision transformer (ViT) has made breakthroughs in image recognition. Its self-attention mechanism (MSA) can extract discriminative labeling information of different pixel blocks to improve image classification accuracy.…

Visual attention mechanisms play a crucial role in human perception and aesthetic evaluation. Recent advances in Vision Transformers (ViTs) have demonstrated remarkable capabilities in computer vision tasks, yet their alignment with human…