Search
Search Results
-
A novel single kernel parallel image encryption scheme based on a chaotic map
The development of communication technologies has increased concerns about data security, increasing the prominence of cryptography. Images are one...
-
A Judicious way to restore random impulse noise using iterative weighted total variation diffusion technique
Various types of pixel candidates are available in the literature to replace impulse noise after effective detection. However, using them in the...
-
MDUNet: deep-prior unrolling network with multi-parameter data integration for low-dose computed tomography reconstruction
The goal of this study is to reconstruct a high-quality computed tomography (CT) image from low-dose acquisition using an unrolling deep...
-
An adversarial sample detection method based on heterogeneous denoising
Deep learning has been used in many computer-vision-based applications. However, deep neural networks are vulnerable to adversarial examples that...
-
A framework of specialized knowledge distillation for Siamese tracker on challenging attributes
In recent years, Siamese network-based trackers have achieved significant improvements in real-time tracking. Despite their success, performance...
-
A novel two-stage omni-supervised face clustering algorithm
Face clustering has applications in organizing personal photo album, video understanding and automatic labeling of data for semi-supervised learning....
-
Real-time water surface target detection based on improved YOLOv7 for Chengdu Sand River
It has been a challenge to obtain accurate detection results in a timely manner when faced with complex and changing surface target detection....
-
Exploring methods for the generation of visual counterfactuals in the latent space
In the field of eXplainable Artificial Intelligence (XAI), the generation of counterfactuals is a promising method for human-interpretable...
-
EdgeNet: a low-power image recognition model based on small sample information
Existing deep convolutional neural networks that rely on large datasets typically require images with high resolution and deep neural network models...
-
Boosting person ReID feature extraction via dynamic convolution
Extraction of discriminative features is crucial in person re-identification (ReID) which aims to match a query image of a person to her/his images,...
-
Exploration and Exploitation of Unlabeled Data for Open-Set Semi-supervised Learning
In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both...
-
DTS: dynamic training slimming with feature sparsity for efficient convolutional neural network
Deep convolutional neural networks have achieved remarkable progress on computer vision tasks over last years. In this paper, we proposed a dynamic...
-
Infproto-Powered Adaptive Classifier and Agnostic Feature Learning for Single Domain Generalization in Medical Images
Designing a single domain generalization (DG) framework that generalizes from one source domain to arbitrary unseen domains is practical yet...
-
IAFPN: interlayer enhancement and multilayer fusion network for object detection
Feature pyramid network (FPN) improves object detection performance by means of top-down multilevel feature fusion. However, the current FPN-based...
-
GOA-net: generic occlusion aware networks for visual tracking
Occlusion is a frequent phenomenon that hinders the task of visual object tracking. Since occlusion can be from any object and in any shape, data...
-
An improved multi-scale and knowledge distillation method for efficient pedestrian detection in dense scenes
Pedestrian detection in densely populated scenes, particularly in the presence of occlusions, remains a challenging issue in computer vision....
-
ChemScraper: leveraging PDF graphics instructions for molecular diagram parsing
Most molecular diagram parsers recover chemical structure from raster images (e.g., PNGs). However, many PDFs include commands giving explicit...
-
Lightweight safety helmet detection algorithm using improved YOLOv5
In response to the challenges faced by existing safety helmet detection algorithms when applied to complex construction site scenarios, such as poor...
-
Online camera auto-calibration appliable to road surveillance
Camera calibration is an essential prerequisite for road surveillance applications, which determines the accuracy of obtaining three-dimensional...
-
Low resource Twi-English parallel corpus for machine translation in multiple domains (Twi-2-ENG)
Although Ghana does not have one unique language for its citizens, the Twi dialect stands a chance of fulfilling this purpose. Twi is among the...