Related papers: Cascaded Multi-Scale Attention for Enhanced Multi-…
The UNet architecture, based on Convolutional Neural Networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive…
Two-view correspondence learning is a key task in computer vision, which aims to establish reliable matching relationships for applications such as camera pose estimation and 3D reconstruction. However, existing methods have limitations in…
This paper proposes joint attention estimation in a single image. Different from related work in which only the gaze-related attributes of people are independently employed, (I) their locations and actions are also employed as contextual…
This paper is on long-term video understanding where the goal is to recognise human actions over long temporal windows (up to minutes long). In prior work, long temporal context is captured by constructing a long-term memory bank consisting…
Transformer-based methods have demonstrated impressive results in medical image restoration, attributed to the multi-head self-attention (MSA) mechanism in the spatial dimension. However, the majority of existing Transformers conduct…
Quality assessment of images and videos emphasizes both local details and global semantics, whereas general data sampling methods (e.g., resizing, cropping or grid-based fragment) fail to catch them simultaneously. To address the…
Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent…
Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-identification is considered. Attention mechanisms have…
This paper introduces a lightweight image super-resolution (SR) network, termed the Multi-scale Spatial Adaptive Attention Network (MSAAN), to address the common dilemma between high reconstruction fidelity and low model complexity in…
As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and…
In remote sensing applications, such as disaster detection and response, real-time efficiency and model lightweighting are of critical importance. Consequently, existing remote sensing image super-resolution methods often face a trade-off…
A large body of recent work targets semantically conditioned image generation. Most such methods focus on the narrower task of pose transfer and ignore the more challenging task of subject transfer that consists in not only transferring the…
Multimodal medical image fusion is a crucial task that combines complementary information from different imaging modalities into a unified representation, thereby enhancing diagnostic accuracy and treatment planning. While deep learning…
Visual-semantic embedding enables various tasks such as image-text retrieval, image captioning, and visual question answering. The key to successful visual-semantic embedding is to express visual and textual data properly by accounting for…
In recent years, deep learning has shown near-expert performance in segmenting complex medical tissues and tumors. However, existing models are often task-specific, with performance varying across modalities and anatomical regions.…
This paper presents a novel person re-identification model, named Multi-Head Self-Attention Network (MHSA-Net), to prune unimportant information and capture key local information from person images. MHSA-Net contains two main novel…
Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully differentiable end-to-end trainable model that samples and…
For many computer vision applications, such as image description and human identification, recognizing the visual attributes of humans is an essential yet challenging problem. Its challenges originate from its multi-label nature, the large…
Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…
Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this CVPR 2015 paper, we discover that a high-quality visual saliency model can be trained with multiscale features…