scholarly journals Collaborative and Attentive Learning for Personalized Image Aesthetic Assessment

2018 ◽  
Author(s):  
Guolong Wang ◽  
Junchi Yan ◽  
Zheng Qin
Keyword(s):  
Neural Network ◽  
Collaborative Filtering ◽  
Deep Neural Network ◽  
Regions Of Interest ◽  
Experimental Results ◽  
Visual Images ◽  
Learning Method ◽  
Aesthetic Quality ◽  
The Public ◽  
Public Dataset

The ever-increasing volume of visual images has stimulated the demand for organizing such data by aesthetic quality. Automatic and especially learning based aesthetic assessment methods have shown potential by recent works. Existing image aesthetic prediction is often user-agnostic which may ignore the fact that the rating to an image can be inherently individual. We fill this gap by formulating the personalized image aesthetic assessment problem with a novel learning method. Specifically, we collect user-image textual reviews in addition with visual images from the public dataset to organize a review-augmented benchmark. Using this enriched dataset, we devise a deep neural network with a user/image relation encoding input for collaborative filtering. Meanwhile an attentive mechanism is designed to capture the user-specific taste for image semantic tags and regions of interest by fusing the image and user's review. Extensive and promising experimental results on the review-augmented benchmark corroborate the efficacy of our approach.

scholarly journals Deep Residual Network with Sparse Feedback for Image Restoration

2018 ◽  
Vol 8 (12) ◽  
pp. 2417 ◽  
Author(s):  
Zhenyu Guo ◽  
Yujuan Sun ◽  
Muwei Jian ◽  
Xiaofeng Zhang
Keyword(s):  
Neural Network ◽  
Image Restoration ◽  
Deep Neural Network ◽  
Convergence Speed ◽  
Fast Convergence ◽  
Experimental Results ◽  
Residual Network ◽  
Unknown Parameters ◽  
Noisy Images ◽  
Blurred Images

A deep neural network is difficult to train due to a large number of unknown parameters. To increase trainable performance, we present a moderate depth residual network for the restoration of motion blurring and noisy images. The proposed network has only 10 layers, and the sparse feedbacks are added in the middle and the last layers, which are called FbResNet. FbResNet has fast convergence speed and effective denoising performance. In addition, it can also reduce the artificial Mosaic trace at the seam of patches, and visually pleasant output results can be produced from the blurred images or noisy images. Experimental results show the effectiveness of our designed model and method.

scholarly journals Environmental Attention-Guided Branchy Neural Network for Speech Enhancement

2020 ◽  
Vol 10 (3) ◽  
pp. 1167 ◽  
Author(s):  
Lu Zhang ◽  
Mingjiang Wang ◽  
Qiquan Zhang ◽  
Ming Liu
Keyword(s):  
Neural Network ◽  
Noise Reduction ◽  
Speech Enhancement ◽  
Deep Neural Network ◽  
Experimental Results ◽  
Noisy Environments ◽  
Neural Structure ◽  
Noise Interference ◽  
Noise Type ◽  
Speech Reconstruction

The performance of speech enhancement algorithms can be further improved by considering the application scenarios of speech products. In this paper, we propose an attention-based branchy neural network framework by incorporating the prior environmental information for noise reduction. In the whole denoising framework, first, an environment classification network is trained to distinguish the noise type of each noisy speech frame. Guided by this classification network, the denoising network gradually learns respective noise reduction abilities in different branches. Unlike most deep neural network (DNN)-based methods, which learn speech reconstruction capabilities with a common neural structure from all training noises, the proposed branchy model obtains greater performance benefits from the specially trained branches of prior known noise interference types. Experimental results show that the proposed branchy DNN model not only preserved better enhanced speech quality and intelligibility in seen noisy environments, but also obtained good generalization in unseen noisy environments.

An Useful Review on Optical Character Recognition for Smart Era Generation

2021 ◽  
pp. 1-41
Author(s):  
Abhishek Das ◽  
Mihir Narayan Mohanty
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Processing ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Deep Neural Network ◽  
Machine Learning Method ◽  
Learning Method ◽  
Result Section ◽  
Optical Character

In this chapter, the authors have reviewed on optical character recognition. The study belongs to both typed characters and handwritten character recognition. Online and offline character recognition are two modes of data acquisition in the field of OCR and are also studied. As deep learning is the emerging machine learning method in the field of image processing, the authors have described the method and its application of earlier works. From the study of the recurrent neural network (RNN), a special class of deep neural network is proposed for the recognition purpose. Further, convolutional neural network (CNN) is combined with RNN to check its performance. For this piece of work, Odia numerals and characters are taken as input and well recognized. The efficacy of the proposed method is explained in the result section.

Deep Learning for Detecting Sleep Apnea from ECG Signals

2020 ◽  
Vol 10 (6) ◽  
pp. 1265-1273
Author(s):  
Lili Chen ◽  
Huoyao Xu
Keyword(s):  
Neural Network ◽  
Sleep Apnea ◽  
Deep Neural Network ◽  
Experimental Results ◽  
Support Vector ◽  
Ecg Signals ◽  
Novel Approach ◽  
Learning Machine ◽  
High Level ◽  
Electrocardiogram Ecg

Sleep apnea (SA) is a common sleep disorders affecting the sleep quality. Therefore the automatic SA detection has far-reaching implications for patients and physicians. In this paper, a novel approach is developed based on deep neural network (DNN) for automatic diagnosis SA. To this end, five features are extracted from electrocardiogram (ECG) signals through wavelet decomposition and sample entropy. The deep neural network is constructed by two-layer stacked sparse autoencoder (SSAE) network and one softmax layer. The softmax layer is added at the top of the SSAE network for diagnosing SA. Afterwards, the SSAE network can get more effective high-level features from raw features. The experimental results reveal that the performance of deep neural network can accomplish an accuracy of 96.66%, a sensitivity of 96.25%, and a specificity of 97%. In addition, the performance of deep neural network outperforms the comparison models including support vector machine (SVM), random forest (RF), and extreme learning machine (ELM). Finally, the experimental results reveal that the proposed method can be valid applied to automatic SA event detection.

Sign in / Sign up

Export Citation Format

Share Document