Related papers: Cascaded Multi-Scale Attention for Enhanced Multi-…

Attention modules connecting encoder and decoders have been widely applied in the field of object recognition, image captioning, visual question answering and neural machine translation, and significantly improves the performance. In this…

This article proposes a novel attention-based body pose encoding for human activity recognition that presents a enriched representation of body-pose that is learned. The enriched data complements the 3D body joint position data and improves…

In this work, we address the task of referring image segmentation (RIS), which aims at predicting a segmentation mask for the object described by a natural language expression. Most existing methods focus on establishing unidirectional or…

The advancement of deep learning has driven notable progress in remote sensing semantic segmentation. Attention mechanisms, while enabling global modeling and utilizing contextual information, face challenges of high computational costs and…

Semi-supervised learning offers an appealing solution for remote sensing (RS) image segmentation to relieve the burden of labor-intensive pixel-level labeling. However, RS images pose unique challenges, including rich multi-scale features…

Semantic segmentation of remote sensing images plays an important role in a wide range of applications including land resource management, biosphere monitoring and urban planning. Although the accuracy of semantic segmentation in remote…

Human face images usually appear with wide range of visual scales. The existing face representations pursue the bandwidth of handling scale variation via multi-scale scheme that assembles a finite series of predefined scales. Such…

Deep neural networks are increasingly applied in automated histopathology. Yet, whole-slide images (WSIs) are often acquired at gigapixel sizes, rendering them computationally infeasible to analyze entirely at high resolution. Diagnostic…

Recently, convolutional neural networks (CNNs) and attention mechanisms have been widely used in image denoising and achieved satisfactory performance. However, the previous works mostly use a single head to receive the noisy image,…

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…

The objective of image super-resolution is to reconstruct a high-resolution (HR) image with the prior knowledge from one or several low-resolution (LR) images. However, in the real world, due to the limited complementary information, the…

Existing two-stream models, such as CLIP, encode images and text through independent representations, showing good performance while ensuring retrieval speed, have attracted attention from industry and academia. However, the single…

Among prerequisites for a synthetic agent to interact with dynamic scenes, the ability to identify independently moving objects is specifically important. From an application perspective, nevertheless, standard cameras may deteriorate…

Few-Shot Learning (FSL) has attracted growing attention in computer vision due to its capability in model training without the need for excessive data. FSL is challenging because the training and testing categories (the base vs. novel sets)…

One of the common and promising deep learning approaches used for medical image segmentation is transformers, as they can capture long-range dependencies among the pixels by utilizing self-attention. Despite being successful in medical…

Characteristics such as low contrast and significant organ shape variations are often exhibited in medical images. The improvement of segmentation performance in medical imaging is limited by the generally insufficient adaptive capabilities…

Pansharpening is to fuse a multispectral image (MSI) of low-spatial-resolution (LR) but rich spectral characteristics with a panchromatic image (PAN) of high-spatial-resolution (HR) but poor spectral characteristics. Traditional methods…

We consider an MRI reconstruction problem with input of k-space data at a very low undersampled rate. This can practically benefit patient due to reduced time of MRI scan, but it is also challenging since quality of reconstruction may be…

Crowd counting research has made significant advancements in real-world applications, but it remains a formidable challenge in cross-modal settings. Most existing methods rely solely on the optical features of RGB images, ignoring the…

The Transformer architecture has achieved remarkable success in natural language processing and high-level vision tasks over the past few years. However, the inherent complexity of self-attention is quadratic to the size of the image,…