Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks188 from public data
- 268
- 182
- 123
- 115
- AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results110
The AIM 2019 challenge on real world super-resolution addresses the real world setting, where paired true high and low-resolution images are unavailable, and aims to advance the state-of-the-art and provide a standard benchmark for this newly emerging task.
- 104
- AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results101
The AIM 2020 challenge on efficient single image super-resolution was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images with focus on the proposed solutions and results.
- A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Prediction100
A gated peripheral-foveal convolutional neural network that aims to mimic the functions of peripheral vision to encode the holistic information and provide the attended regions for the fovea and a gated information fusion network to weigh their contributions.
- 91
- 90
- Haze removal for a single visible remote sensing image90
The evaluation results with qualitative and quantitative assessments demonstrate that the proposed method is superior to the traditional methods, and can recover a haze-free image with high quality.
- 84
- No Reference Quality Assessment for Screen Content Images Using Stacked Autoencoders in Pictorial and Textual Regions78
An effective and novel blind quality evaluation metric for SCIs by using stacked autoencoders (SAE) based on pictorial and textual regions based on a weighted model is presented.
- 77
- No-reference image quality assessment in contourlet domain75
The contourlet transform is utilized to NSS of images, and then the relationship of contour let coefficients is represented by the joint distribution, and an image-dependent threshold is adopted to reduce the effect of content to the statistical model.
- Image quality assessment and human visual system72
This paper summaries the state-of-the-art of image quality assessment (IQA) and human visual system (HVS) and introduces the basic theories and development histories of the above two kinds of HVS-based IQA methods.
- Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution66
A purposeful and interpretable detail-fidelity attention network to progressively process these smoothes and details in a divide-and-conquer manner, which is a novel and specific prospect of image super-resolution for the purpose of improving detail fidelity.
- 59
- A Blind Stereoscopic Image Quality Evaluator With Segmented Stacked Autoencoders Considering the Whole Visual Perception Route58
A Deep Edge and COlor Signal INtegrity Evaluator (DECOSINE) based on the whole visual perception route from eyes to the frontal lobe and especially focus on the edge and color signal processing in retinal ganglion cells and lateral geniculate nucleus is proposed.
- NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results54
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results and gauges the state-of-the-art in single image super- resolution.
- 54
- 3D Panoramic Virtual Reality Video Quality Assessment Based on 3D Convolutional Neural Networks53
A free available data set (VRQ-TJU) for VR quality assessment is proposed with subjective scores for each sample data and an end-to-end 3-D convolutional neural network is introduced to predict the VR video quality without a referenced VR video.
- 49
- 46
- 44
- No Reference Quality Assessment of Stereo Video Based on Saliency and Sparsity44
A simple model to combine and analyze the diverse features of stereoscopic video, which is based on saliency and sparsity is constructed, and the proposed method is fitting well with the subjective scores.
- Quality assessment metric of stereo images considering cyclopean integration and visual saliency43
A novel saliency map in SIQA metric for the cyclopean image called "cyclopean saliency", which avoids complex calculations and produces good results in detecting saliency regions is proposed.
- 42
- 40
- Quality Index for Stereoscopic Images by Jointly Evaluating Cyclopean Amplitude and Cyclopean Phase40
A full reference stereo image quality assessment (SIQA) framework which focuses on the innovation of binocular visual properties and applications of low-level features is proposed, and a novel binocular modulation function in spatial domain is adopted into the overall quality prediction of amplitude and phase.
- A natural image quality evaluation metric40
A novel RR IQA metric based on hybrid wavelets and directional filter banks and with HWD as a pre-processing stage, this metric mainly focuses on subbands coefficients of the distorted and original images.
- MSCAN: Multimodal Self-and-Collaborative Attention Network for image aesthetic prediction tasks38
A Multimodal Self-and-Collaborative Attention Network that calculates the response at a position by attending to all positions in the images, thus it can effectively encode spatial interaction of the visual elements.
- 37
- Panoramic Video Quality Assessment Based on Non-Local Spherical CNN36
The proposed end-to-end neural network model combines spherical convolutional neural networks (CNN) and non-local neural networks, which can effectively extract complex spatiotemporal information of the panoramic video.
- A Deep Evaluator for Image Retargeting Quality by Geometrical and Contextual Interaction36
A deep quality evaluator for image retargeting based on the segmented stacked AutoEnCoder (SAE) is proposed, which through the help of regularization, the designed deep learning framework can solve the overfitting problem.
- Image quality assessment based on S-CIELAB model35
A new image quality assessment framework which is based on color perceptual model based on the S-CIELAB color space, which has an excellent performance for mimicking the perceptual processing of human color vision.
- Wavelet-based contourlet in quality evaluation of digital images34
This paper first proposes an objective reduced-reference image quality evaluation metric based on contourlet transform and demonstrates that this new objective metric achieves consistent imagequality evaluation results with what gained by subjective evaluation.
- 33
- Stereoscopic video quality assessment based on 3D convolutional neural networks33
A 3D convolutional neural networks (CNN) based SVQA framework that can model not only local spatio-temporal information but also global temporal information with cubic difference video patches as input and outperforms state-of-the-art methods by a large margin is introduced.
- Blind assessment for stereo images considering binocular characteristics and deep perception map based on deep belief network30
Experimental results demonstrate that the proposed stereo image quality evaluation model has high superiority over existing methods and achieve higher consistency with subjective quality assessments.
- 26
- 26
- 26
- A no-reference optical flow-based quality evaluator for stereoscopic videos in curvelet domain26
This paper proposes an effective multi-view feature learning metric for blind stereoscopic video quality assessment (BSVQA), which jointly focuses on spatial information, temporal information and inter-frame spatio-temporal information.
- Video quality assessment by compact representation of energy in 3D-DCT domain25
Experimental results show that the proposed VQA method has a good consistency with human perception and is competitive with the state-of-the-art methods.
- Spectral–Spatial Feature Extraction for Hyperspectral Image Classification Using Enhanced Transformer with Large-Kernel Attention23
A novel classification network by extracting spectral–spatial features with an enhanced Transformer with Large-Kernel Attention (ETLKA), surpassing several advanced techniques currently in use is introduced.
- Deep multi-label learning for image distortion identification23
A CNN-based multi-label learning model is proposed to identify distortions for different scenarios, including images having no distortion, single distortion and multiple distortions, and the network architecture of the CNN model can make flexible adjustment according to the different requirements.
- A WAVELET-BASED IMAGE QUALITY ASSESSMENT METHOD22
A novel reduced-reference image quality assessment method is proposed based on wavelet transform that takes the variance of the visual sensitive coefficients into account to measure a distorted image.
- 21
- No reference quality evaluation for screen content images considering texture feature based on sparse representation21
An accurate blind metric evaluating screen content images (SCIs) considering texture feature via sparse representation is proposed and has the better superiority over existing the-state-of-art algorithms and delivers consistency and accuracy in relation with subjective evaluation.
- 20
- 19
- 19
- Deep blind image quality assessment based on multiple instance regression19
A novel deep blind IQA algorithm under the multiple instance regression (MIR) framework is proposed, which can be used as a unified framework to improve the performance of any patch-based deep IQA models.
- Precise Measurement of Position and Attitude Based on Convolutional Neural Network and Visual Correspondence Relationship19
An object pose measurement scheme based on convolutional neural network is proposed and successfully implemented end-to-end position and attitude detection and generating image encoder is generated to guarantee the detection performance of the training model in practical applications.
- A spatiotemporal model of video quality assessment via 3D gradient differencing19
A novel VQA metric via spatiotemporal 3D gradient differencing is proposed to describe the degradation of video quality effectively and shows a good consistency with the subjective perception and performs better than traditional metrics.
- Sparse representation based stereoscopic image quality assessment accounting for perceptual cognitive process18
A sparse representation based Reduced-Reference Image Quality Assessment (RR-IQA) index for stereoscopic images from the following two perspectives is proposed: 1) Human visual system always tries to infer the meaningful information and reduces uncertainty from the visual stimuli, and the entropy of primitive can well describe this visual cognitive progress when perceiving natural images.
- Densely convolutional attention network for image super-resolution16
A novel Densely Convolutional Attention Network for SISR is presented which adds an weighted skip-connection joint the original convolution to improve the quality of reconstructed images.
- A Visual Residual Perception Optimized Network for Blind Image Quality Assessment16
A visual residual perception optimized network (VRPON) that can effectively solve blind image quality assessment problems and not only has better performance than state-of-the-art methods on synthetic distorted images, but also has better robustness for different authentic distortions.
- 15
- Dominant vanishing point detection in the wild with application in composition analysis15
A semantic-texture fusion network to detect the dominant vanishing point in the image and adopt the Squeeze-and-Excitation block to model the interdependencies between the semantic features and the textural features.
- No-Reference Stereoimage Quality Assessment for Multimedia Analysis Towards Internet-of-Things15
A new no-reference stereoscopic image quality assessment model for multimedia analysis towards Internet of Things is built, which is based on a deep learning model to learn from the class labels and image representations to shine upon the quality from the feature vector.
- 14
- 14
- 14
- Fusion global and local deep representations with neural attention for aesthetic quality assessment13
A novel convolutional networks with two branches to encode global and local features and a sobel-based attention layer is integrated with the second branch to enhance fine details encoding.
- A Video Quality Assessment Metric Based on Human Visual System13
Experimental results prove the proposed video quality assessment metric based on visual perception outperforms the most existing methods and is comparable to LHS and PVQM.
- 12
- 12
- 12
- No-Reference Quality Assessment of Stereoscopic Videos With Inter-Frame Cross on a Content-Rich Database12
A comprehensive subjective evaluation of stereoscopic video quality in newly established TJU-SVQA databases that contain various contents, mixed resolution coding and symmetrically/asymmetrically distorted stereoscopic videos and proposes a new inter-frame cross map to predict the objective quality scores.
- 11
- Electroencephalography Microstate Alterations in Otogenic Vertigo: A Potential Disease Marker11
There are several temporal dynamic alterations of EEG microstates in patients with otogenic vertigo, especially in Microstate D, reflecting the underlying process of visual-vestibular reorganization and attention redistribution.
- RETRACTED: A Deep Learning Model for Three-Dimensional Nystagmus Detection and Its Preliminary Application11
A three-dimensional nystagmus recognition model and a benign paroxysmal positional vertigo automatic diagnosis system based on deep neural network architectures (Chinese Clinical Trials Registry ChiCTR-IOR-17010506) are designed and applied in real-world medical practices.
- No-reference stereoscopic image quality assessment based on hue summation–difference mapping image and binocular joint mutual filtering11
A novel NR stereo image quality assessment (SIQA) method that mimics the summation and difference channels, which consider the binocular interactive perception property, to process the visual information.
- Blind image quality assessment via semi-supervised learning and fuzzy inference11
A semi-supervised and fuzzy framework for blind image quality assessment, S2F2, is proposed and the semi- supervised local linear embedding (SS-LLE) is introduced to learn the mapping function from the image features to the truth values using both the labeled and unlabeled images.
- 11
- 10
- Beauty Aware Network10
A trainable network named Beauty Aware Network (BAN) for makeup product retrieval is proposed using an unsupervised cluster method to train the beauty classification network and a covariance pooling layer is introduced to leverage the statistical information.
- No-reference image quality assessment based on neighborhood co-occurrence matrix10
A new approach is proposed for NR-IQA, in which the neighborhood co-occurrence matrix (NCM) is introduced to describe spatial correlation of pixels for quality assessment, which has superior performance against compared methods, and achieves significant improvements on distortions associated with color or locality.
- Statistical modeling in the shearlet domain for blind image quality assessment10
Experimental results on benchmark databases illustrate that the proposed BIQA algorithm based on shearlet transform without using human scored images has a good consistency with the subjective assessment of human beings.
- 10
- No-reference image quality assessment focusing on human facial region9
A no-reference (NR) IQA metric is proposed that uses global features of an image and local features extracted from detected facial regions by a convolutional neural network (CNN) based tiny face detector and is competitive with the previous 2D NR IQA metrics.
- Fast image quality assessment via supervised iterative quantization method9
This paper proposes a fast no-reference image quality assessment via hash coding method, named NRHC, which achieves comparable performance and has higher computational efficiency and stronger robustness compared with the state-of-the-art NR-IQA methods.
- On combining visual perception and color structure based image quality assessment9
A novel IQA framework which utilizes minimum amount of structure coefficients to capture the variation of color structure and distortion of degraded image by applying a VPT to remove the visual unperceived coefficients is proposed.
- Single image super resolution based on sparse domain selection7
Experimental results indicate that the proposed approach is more capable of modeling the relationships from feature of LR to those of HR, thus improves the quality of reconstruction image.
- 7
- 6
- 6
- 6
- MFNN: Position and Attitude Measurement Neural Network Based on Multi-Feature Fusion6
This paper effectively introduces the HOG operator as an image feature and combine it with the original image for a specific ratio and proposes a new type of position and attitude measurement network architecture, MFNN, which has further improved the accuracy of related measurements.
- 6
- Blind image quality assessment utilising local mean eigenvalues6
The authors study the correlation between local mean eigenvalues (LMEs) and perceptual quality of images, and demonstrate the applicability of LMEs in IQA.
- Stereoscopic image quality assessment combining statistical features and binocular theory6
Combining binocular characteristics, an efficient no-reference stereoscopic image quality assessment according to binocular adding and subtracting channels is proposed and achieves high consistent with the subjective quality scores.
- 6
- Distilling with Residual Network for Single Image Super Resolution5
Experiments on benchmark datasets demonstrate that the simple and efficient distilling with residual network (DRN) for SISR is superior to the state-of-the-art methods, specifically has a better trade-off between performance and model size.
- Rank Learning for Dehazed Image Quality Assessment5
In this paper, a rank learning algorithm is proposed that is highly consistent with the subjective feeling of human eye and is superior to the traditional dehazed image quality evaluation algorithms and has a strong expansibility.
- No-reference stereoscopic image-quality metric accounting for left and right similarity map and spatial structure degradation5
A no-reference stereoscopic image quality assessment (SIQA) model based on the proposed left and right (LR)-similarity map and structural degradation is developed that is strongly correlated to subjective quality evaluations and competitive to the state-of-the-art SIQA algorithms.
- 5
- An image quality assessment metric with no reference using hidden Markov tree model5
Experimental results show that the proposed NR-IQA metric is consistent well with the subjective evaluation results, and outperforms the existing models on difference distortions.
- 5
- 5
- Targeting mitochondrial dysfunction: Innovative strategies to combat glaucoma neuroinflammation4
A deeper comprehension of the link between mitochondrial dysfunction and microglial activation in glaucoma may provide valuable insights into the underlying pathogenesis of glaucoma.
- Multi-Window Fusion Spatial-Frequency Joint Self-Attention for Remote-Sensing Image Super-Resolution4
This approach introduces a multi-window fusion strategy, which merges windows with similar textures to allow self-attention mechanisms to capture long-range dependencies effectively, therefore expanding the receptive field of the feature extractor.
- Unpaired Remote Sensing Image Super-Resolution with Multi-Stage Aggregation Networks4
This paper proposes a perceptually unpaired super-resolution method by constructing a multi-stage aggregation network (MSAN), which employs the generative adversarial network (GAN) to adding photo-realistic textures by constraining perceptual-distribution consistency.
- 4
- Efficient Video Quality Assessment via 3D-Gradient Similarity Deviation4
Experimental results show that the proposed novel efficient VQA metric via 3D-gradient similarity deviation has a good consistency with the subjective perception and perform better than traditional metrics.
- [A solution for display and processing of DICOM images in web PACS].4
The method designed in this paper can make users display and process DICOM images directly by using ordinary Web browser, which makes Web PACS not only have the advantages of B/S model, but also have the disadvantages of the C/S models.
- 3
- 3
- RETRACTED ARTICLE: Real-time monitoring of sports performance based on ensemble learning algorithm and neural network3
A sports performance prediction model based on ensemble learning algorithms under the guidance of machine learning ideas and the L1 regularization method to sparsely weight and combine multiple STELM models to achieve selective integration is built.
- Primary Acute Angle-Closure Glaucoma: Three-Dimensional Reconstruction Imaging of Optic Nerve Heard Structure in Based on Optical Coherence Tomography (OCT)3
Three-dimensional reconstruction was used to identify OCT images between glaucoma patients and the control group with significant differences and to reconstruct the volume data of three-dimensional optic nerve head (ONH), and make morphological measurements.
- No-Reference Image Quality Assessment via Multi-order Perception Similarity3
An innovative strategy is presented and a novel NR-IQA approach based on multi-order perception similarity to overcome the difficulty of lack of reference and reduce the dependence of features on image content.
- Blind Image Quality Assessment in Shearlet Domain3
A valid BIQA algorithm based on shearlet transform without using human scored images is presented and experimental results on two benchmarking databases indicate the rationality and validity of the proposed method.
- 3
- FCA$^{\bf 2}$: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution2
This work introduces a compression-driven dimensionality reduction strategy that reduces computational complexity, accelerates inference, and enhances the extraction of temporal information across frames, and offers a practical and efficient pathway for advancing VSR technology.
- EIMGDNet: An Edge-Induced and Multi-Dimensional Grouped Difference Network for Remote Sensing Image Change Detection2
This work proposes EIMDGNet, a novel architecture that enhances boundary representation and cross-scale feature interaction for accurate and robust change detection, and designs the Multi-Scale Hierarchical Progressive Fusion Module, a bottom-up progressive strategy to hierarchically integrate low-level spatial details with high-level semantic abstractions.
- 2
- Distributed Intelligent Learning and Decision Model Based on Logic Predictive Control2
The intelligent learning system feedback delay is studied, combined with mobile communication which led to the artificial intelligence online sports games teaching, pattern recognition, and virtual technology combined with innovative teaching interaction and experience, and a dual channel awareness scheduling strategy under the model predictive control framework was proposed.
- 2
- 2
- 2
- 2
- 2
- An Image Quality Evaluation Method Based on Joint Deep Learning2
An image quality evaluation method based on joint deep learning (JDL) with deep belief networks (DBNs) and convolutional neural network (CNNs) used together to evaluate the quality of the images.
- Stereoscopic Image Quality Assessment Based on Binocular Adding and Subtracting2
Different from other SIQA methods which focus on complex binocular visual properties, this work simply uses the visual information from adding and subtracting to describe binocularity (also known as ocular dominance) which is closely related to distortion types.
- Depth estimation for image dehazing of surveillance on education2
Experimental results show the proposed is better to obtain haze-free scenes with sharp edges, abundant details and vivid color while dealing well with bright areas while dealing well with bright areas.
- Spatiotemporal Saliency Detection based Video Quality Assessment2
A novel VQA algorithm is proposed based on spatiotemporal saliency detection using Random Walk with Restart (RWR) and has excellent performance and has a good consistency with human perception.
- A Novel Image Quality Assessment for Color Distortions2
Experimental results on color-related distortions of TID2013 database show the superiority of this new approach and comparative experiments reveal the rationality and the validity of this novel assessment metric for color distortions.
- Image Quality Assessment Based on Mutual Information in Pixel Domain2
A new image quality assessment framework in image pixel domain based on mutual information is proposed, and the experimental results show that the proposed framework has good consistency with subjective perception values.
- Image Quality Assessment Based on Local Pixel Correlation2
A novel image quality assessment based on the pixel correlation is proposed, where image is parted based on mutual information, and three kinds of mutual information between the pixel intensity and the image patches are extracted to catch the variation of thepixel correlation.
- Natural Image Dehazing Based on L 0 Gradient Minimization2
A natural image dehazing method based on L 0 gradient minimization is introduced and has a better ability to obtain haze-free scenes with abundant edges, smooth detail and vivid color.
- Blind Image Quality Assessment with Semi-supervised Learning and Fuzzy Logic2
This paper formulate the fuzzy process of subjective quality assessment by using fuzzy logic and introduces the semi-supervised local linear embedding (SS-LLE) to learn the mapping from the features to the truth values using both the labeled and unlabeled images.
- A NOVEL METRIC BASED ON MCA FOR IMAGE QUALITY2
A novel image quality metric is proposed by incorporating Morphological Component Analysis (MCA) and HVS, which is capable of assessing the image with different kinds of distortion, which prevails over some existing methods on LIVE database II.
- HyperAlign: Hyperbolic Entailment Cones for Adaptive Text-to-Image Alignment Assessment1
This work proposes HyperAlign, an adaptive text-to-image alignment assessment framework based on hyperbolic entailment geometry, which achieves highly competitive performance on both single database evaluation and cross-database generalization tasks, fully validating the effectiveness of hyperbolic geometric modeling for image-text alignment assessment.
- 1
- Brain MR Image Super-resolution via Second-order Propagation and Grid Connections1
A method that decomposes brain MR images into 2D slice sequences, employing a second-order Markov propagation strategy to exploit the correlation between adjacent slices for deep feature refinement and improves the model’s expressiveness is proposed.
- 1
- 1
- 1
- 1
- 1
- QoEVMA'201
This summary gives a brief overview of the workshop, which took place at October 16, 2020 in Seattle (U.S.), as a half-day workshop, on quality assessment of any visual multimedia applications both subjectively and objectively.
- 1
- Research on Communication Circuit Applied in Street Lamp Control System1
The overall design scheme of the control system is summarized, the high reliability of outbound Two Way Automatic Communication System within one transformer area and the low-cost characteristics of corresponding circuit are demonstrated.
- [A review on the research progress of the computer-aided detection of pulmonary nodule].1
The technology research and development of CAD of the pulmonary nodules which is based on CT image in recent years both home and abroad is reviewed and the advantages and shortcomings of different methods are analysed.
- A Remote Monitoring System of Water Injection well Based on TWACS1
This system, which is based on TWACS, can realize the datas remote multi-channel parallel transmission and monitoring, and has a small investment and no signal blind area, it is well suited in oilfield distribution.
- Research on TWACS Interference Suppression Based on the RLS Algorithm1
The field test signal simulations show good effect of the adaptive filter design, and it’s premised that the modulation signal is basically known, and the signal beyond modulation domain is regarded as reference signal to design an adaptive filter applied to TWACS.
- A new quality metric for compressed images based on DDCT1
A new no reference (NR) metric for compressed images to do IQA is proposed, which exploits the causes of distortion by JPEG and JPEG2000, employs the directional discrete cosine transform (DDCT) to obtain the detail and direction information of the images and incorporates with the visual perception to get the image quality index.
- 1
- 1
- IBCL-VQA: Video Quality Assessment with In-Batch Contrastive Learning and Two-Phase Feature Fusion–
An in-batch contrastive learning mechanism which, through the principles of maximizing intra-class similarity and minimizing inter-class similarity, combined with a dynamically adjusted penalty strategy, models the correlation between video quality levels.
- –
- –
- Mixture of Lie-Group Kernels for Equivariance-Inspired Feature Learning–
MoLiegroup is introduced, a framework that embeds multiple Lie-group priors as specialized kernel experts and adaptively fuses them via a geometry-aware gating mechanism to learn equivariance-inspired geometric features and supplies a practical, architecture-agnostic geometric inductive bias that improves expressivity and generalization across a wide range of vision tasks.
- –
- –
- –
- –
- –
- Energy optimization strategy for data center electrothermal coupling system based on task scheduling–
- –
- QoEVMA'22: 2nd Workshop on Quality of Experience (QoE) in Visual Multimedia Applications–
A brief overview of the workshop is given, which took place on October 14, 2022 in Lisbon, Portugal, as a half-day workshop, on the QoE assessment of any visual multimedia applications both subjectively and objectively.
- –
- Corrections to “No-Reference Stereoimage Quality Assessment for Multimedia Analysis Towards Internet-of-Things”–
In the above article [1] , there is minor mistake caused by numerical type position.
- –
- Unified Image Aesthetic Prediction via Scanpath-Guided Feature Aggregation Network–
This work proposes a scanpath-guided feature aggregation model for aesthetic prediction that demonstrates the efficacy of this approach for unified aesthetic prediction tasks: (i) aesthetic quality classification; (ii) aesthetic score regression; and (iii) aesthetic Score distribution prediction.
- –
- –
- –
- –
- A Multi-scale Dehazing Network with Transmission Range Stretching–
A novel Dehazing Network to learn the relationship between the hazy image and its corresponding transmission map is presented and it uses jump connection and the layer of Multi-scale features fusion to obtain more feature related to haze density.
- Deep Convolutional Neural Network with Feature Fusion for Image Super-Resolution–
The authors' method use the interpolated low-resolution image as input, employ many skip-connections to combine low-level image features with the final reconstruction process, and these feature fusion strategies are based on pixel-level summation operations.
- Spatiotemporal Masking for Objective Video Quality Assessment–
Experimental results show that the VQA metric based on STMM has a good consistency with the subjective perception and performs better than its original metric.
- Cascade Error-Correction Mechanism for Human Pose Estimation in Videos–
This paper proposes a three-stage framework for human pose estimation, emphasizing on the improvement of wrist location accuracy, and demonstrates the superiority of the proposed algorithm compared to state-of-the-art methods.
- Blind Image Quality Assessment: Using Statistics of Color Descriptors in the DCT Domain–
Experimental results on several benchmarking databases show the proposed method is superior to other state-of-the-arts methods and reveal the rationality and the validity of the new approach.
- An Improved Image Quality Assessment in Gradient Domain–
An improved image quality assessment in gradient domain is proposed which utilizes minimum amount of gradient coefficients to capture the color and structure distortion of degraded image by applying a VPT to remove the unperceived gradient coefficients.
- Fast Image Quality Assessment via Hash Code–
Thorough experiments on standard databases show that the proposed NRHC obtains promising performance for NR-IQA and it has high computational efficiency and robustness for different databases and different distortions.
- [A probability segmentation algorithm for lung nodules based on three-dimensional features].–
Using the public Lung Imaging Database Consortium (LIDC) lung nodule datasets, the performance of proposed method was verified by comparing the probability map within LIDC datasets, which was drawn by four radiology doctors separately.
- Research on Wells Monitoring Background Management Software Based on Labview–
Well monitoring background software based on labview not only realize data collection and management, but also realize the system equipment monitoring and debugging.
- –
- Application of Power-Line Power Frequency Communication in Oilfield Distribution Network–
A scheme which can realize parallel transmission of multichannel upstream signals according to orthogonal coding creates favorable conditions for the transmission of greater capacity of oil monitoring information through the power frequency communication technology.
- Develop of Master Station Facility Based on the Distributed Structure of the Oil with TWACS Well Remote Monitoring System–
A TWACS master facility which based on the work of the distributed structure to Meet well remote monitoring and management is designed and implemented.
- Development of Pumping Wells Electrical Facility Remote Monitoring Terminal Based on DSP–
Aimed at the features of large quantity and wide distribution of oil wells, a pumping well remote monitoring terminal based on the two way automatic communication technology (TWACS) is designed.
- –
- A NOVEL COMPRESSED IMAGES QUALITY METRIC–
A new no reference (NR) metric for compressed images to do IQA is proposed, which exploits the causes of distortion by JPEG and JPEG2000, employs the directional discrete cosine transform (DDCT) to obtain detail and directional information of the images and incorporates with the visual perception to obtain the image quality index.
- –
- Improved methods on ASP.NET2.0 web site mangement tools–
The deficiencies of ASP.NET2.0 site management tools are analysed and the details of its improved methods are given in this paper.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.