Related papers: Omni Aggregation Networks for Lightweight Image Su…
Visual recognition requires rich representations that span levels from low to high, scales from small to large, and resolutions from fine to coarse. Even with the depth of features in a convolutional network, a layer in isolation is not…
Lack of texture often causes ambiguity in matching, and handling this issue is an important challenge in optical flow estimation. Some methods insert stacked transformer modules that allow the network to use global information of cost…
In this paper, we propose an efficient human pose estimation network -- SFM (slender fusion model) by fusing multi-level features and adding lightweight attention blocks -- HSA (High-Level Spatial Attention). Many existing methods on…
Recent advances in the design of convolutional neural network (CNN) have yielded significant improvements in the performance of image super-resolution (SR). The boost in performance can be attributed to the presence of residual or dense…
In this work, we propose to leverage a deep-learning (DL) based reconstruction framework for high quality Swept-Source Optical Coherence Tomography (SS-OCT) images, by incorporating wavelength ({\lambda}) space interferometric fringes.…
Attention operator has been widely used as a basic brick in visual understanding since it provides some flexibility through its adjustable kernels. However, this operator suffers from inherent limitations: (1) the attention kernel is not…
Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard…
This paper presents MOAT, a family of neural networks that build on top of MObile convolution (i.e., inverted residual blocks) and ATtention. Unlike the current works that stack separate mobile convolution and transformer blocks, we…
Recent transformer-based super-resolution (SR) methods have achieved promising results against conventional CNN-based methods. However, these approaches suffer from essential shortsightedness created by only utilizing the standard…
The tradeoff between reconstruction quality and compute required for video super-resolution (VSR) remains a formidable challenge in its adoption for deployment on resource-constrained edge devices. While transformer-based VSR models have…
The prevalence of convolution neural networks (CNNs) and vision transformers (ViTs) has markedly revolutionized the area of single-image super-resolution (SISR). To further boost the SR performances, several techniques, such as residual…
The lack of efficient segmentation methods and fully-labeled datasets limits the comprehensive assessment of optical coherence tomography angiography (OCTA) microstructures like retinal vessel network (RVN) and foveal avascular zone (FAZ),…
Deep learning methods have shown outstanding performance in many applications, including single-image super-resolution (SISR). With residual connection architecture, deeply stacked convolutional neural networks provide a substantial…
By developing sophisticated image priors or designing deep(er) architectures, a variety of image Super-Resolution (SR) approaches have been proposed recently and achieved very promising performance. A natural question that arises is whether…
Screen content (SC) differs from natural scene (NS) with unique characteristics such as noise-free, repetitive patterns, and high contrast. Aiming at addressing the inadequacies of current learned image compression (LIC) methods for SC, we…
Few-Shot Remote Sensing Scene Classification (FS-RSSC) presents the challenge of classifying remote sensing images with limited labeled samples. Existing methods typically emphasize single-modal feature learning, neglecting the potential…
Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature degradation caused by fast motion or multiple poses. Current…
While transformer models have been demonstrated to be effective for natural language processing tasks and high-level vision tasks, only a few attempts have been made to use powerful transformer models for single image super-resolution.…
An important component of computer vision research is object detection. In recent years, there has been tremendous progress in the study of construction site images. However, there are obvious problems in construction object detection,…
Medical Hyperspectral Imaging (MHSI) has emerged as a promising tool for enhanced disease diagnosis, particularly in computational pathology, offering rich spectral information that aids in identifying subtle biochemical properties of…