Related papers: Visual Attention Network

Existing models of human visual attention are generally unable to incorporate direct task guidance and therefore cannot model an intent or goal when exploring a scene. To integrate guidance of any downstream visual task into attention…

The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…

Vision transformers using self-attention or its proposed alternatives have demonstrated promising results in many image related tasks. However, the underpinning inductive bias of attention is not well understood. To address this issue, this…

Due to the lack of automated methods, to diagnose cerebrovascular disease, time-of-flight magnetic resonance angiography (TOF-MRA) is assessed visually, making it time-consuming. The commonly used encoder-decoder architectures for…

In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is…

Background and Objective: In the realm of ophthalmic imaging, accurate vascular segmentation is paramount for diagnosing and managing various eye diseases. Contemporary deep learning-based vascular segmentation models rival human accuracy…

Accurate medical image segmentation is essential for diagnosis and treatment planning of diseases. Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they are…

Recently, transformer-based methods have demonstrated impressive results in various vision tasks, including image super-resolution (SR), by exploiting the self-attention (SA) for feature extraction. However, the computation of SA in most…

Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does…

The Transformer architecture has achieved significant success in natural language processing, motivating its adaptation to computer vision tasks. Unlike convolutional neural networks, vision transformers inherently capture long-range…

Learning semantic correspondence between image and text is significant as it bridges the semantic gap between vision and language. The key challenge is to accurately find and correlate shared semantics in image and text. Most existing…

Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Existing point-cloud based 3D object detectors use convolution-like operators to process information in a local neighbourhood with fixed-weight kernels and aggregate global context hierarchically. However, non-local neural networks and…

Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images. However, these algorithms often yield significant artifacts when dealing with real-world super-resolution problems due to…

While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present…

Local and non-local attention-based methods have been well studied in various image restoration tasks while leading to promising performance. However, most of the existing methods solely focus on one type of attention mechanism (local or…

Vision-and-Language Navigation (VLN) tasks agents with locating specific objects in unseen environments using natural language instructions and visual cues. Many existing VLN approaches typically follow an 'observe-and-reason' schema, that…

For fine-grained visual classification, objects usually share similar geometric structure but present variant local appearance and different pose. Therefore, localizing and extracting discriminative local features play a crucial role in…

The goal of weakly-supervised video moment retrieval is to localize the video segment most relevant to the given natural language query without access to temporal annotations during training. Prior strongly- and weakly-supervised approaches…