Search Results for author:
Found 22 papers, 3 papers with code
A Parametric Rate-Distortion Model for Video Transcoding
By utilizing our model in this manner, quality improvements up to 2 dB and bitrate savings of up to 46% of the original target bitrate are possible.
High-Quality Live Video Streaming via Transcoding Time Prediction and Preset Selection
One solution is to predict each preset's transcoding time and select the preset that ensures the highest quality while adhering to live streaming time constraints.
Supervised Deep Learning for Content-Aware Image Retargeting with Fourier Convolutions
In our approach, a mask is generated to show the desired size and location of the object.
A New Non-Negative Matrix Factorization Approach for Blind Source Separation of Cardiovascular and Respiratory Sound Based on the Periodicity of Heart and Lung Function
In this study, a modified version of the affine non-negative matrix factorization (NMF) approach is proposed to blindly separate lung and heart sounds recorded by a digital stethoscope.
Endoscopy Classification Model Using Swin Transformer and Saliency Map
Endoscopy is a valuable tool for the early diagnosis of colon cancer.
SFI-Swin: Symmetric Face Inpainting with Swin Transformer by Distinctly Learning Face Components Distributions
None of the powerful existing models can fill out the missing parts of an image while considering the symmetry and homogeneity of the picture.
Dynamic-Pix2Pix: Noise Injected cGAN for Modeling Input and Target Domain Joint Distributions with Limited Training Data
Helping the cGAN learn the target distribution from noise input results in a better model generalization during the test time and allows the model to fit almost perfectly to the target domain distribution.
OAIR: Object-Aware Image Retargeting Using PSO and Aesthetic Quality Assessment
The PSO algorithm uses aesthetic quality assessment as its objective function to identify the best location and size for the objects to be placed in the background.
Adaptive search area for fast motion estimation
This search area is similar to that of the full search (FS) algorithm but smaller for most blocks of a frame.
MSGDD-cGAN: Multi-Scale Gradients Dual Discriminator Conditional Generative Adversarial Network
In this work, we propose a method called MSGDD-cGAN, which first stabilizes the performance of the cGANs using multi-connections gradients flow.
Conditional Image Generation
Generative Adversarial Network
+1
Robust Watermarking using Diffusion of Logo into Autoencoder Feature Maps
In this paper, we propose to use an end-to-end network for watermarking.
Classification of Diabetic Retinopathy Using Unlabeled Data and Knowledge Distillation
Knowledge distillation addresses some of the shortcomings associated with transfer learning by generalizing a complex model to a lighter model.
A fast semi-automatic method for classification and counting the number and types of blood cells in an image
A novel and fast semi-automatic method for segmentation, locating and counting blood cells in an image is proposed.
Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutions
In this paper, a new method for CNN processing in the FFT domain is proposed, which is based on input splitting.
Unlabeled Data Deployment for Classification of Diabetic Retinopathy Images Using Knowledge Transfer
Knowledge distillation is recently proposed to transfer the knowledge of a model to another one and can be useful to cover the shortcomings of transfer learning.
Splitting Convolutional Neural Network Structures for Efficient Inference
For convolutional neural networks (CNNs) that have a large volume of input data, memory management becomes a major concern.
Convolutional Neural Network Pruning Using Filter Attenuation
In the proposed attenuation approach, weak filters are not abruptly removed, and there is a chance for these filters to return to the network.
Real time ridge orientation estimation for fingerprint images
Most of the automatic verification systems are based on matching of fingerprint minutiae.
Vessel Segmentation and Catheter Detection in X-Ray Angiograms Using Superpixels
In this framework we use our catheter detection and tracking method which detects the catheter by finding its ridge in the first frame and traces in other frames by fitting a second order polynomial on it.
Adaptive Real-Time Removal of Impulse Noise in Medical Images
In this paper a low complexity de-noising method is proposed that removes the noise by local analysis of the image blocks.
OCRAPOSE II: An OCR-based indoor positioning system using mobile phone images
Then, it finds depth and angle-of-view of the query using the information provided by the OCR engine in order to refine the location estimate.
Subjective and Objective Quality Assessment of Image: A Survey
Measuring the image quality is of fundamental importance for numerous image processing applications, where the goal of image quality assessment (IQA) methods is to automatically evaluate the quality of images in agreement with human quality judgments.
