Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks252 from public data
- 264
- 239
- Underwater Camera: Improving Visual Perception Via Adaptive Dark Pixel Prior and Color Correction231
Experimental results show that the novel method for underwater image restoration outperforms state-of-the-art methods, demonstrating its efficacy in dealing with uneven lighting and diverse underwater environments.
- 227
- HCLR-Net: Hybrid Contrastive Learning Regularization with Locally Randomized Perturbation for Underwater Image Enhancement210
The HCLR-Net, a novel approach built upon a distinctive hybrid contrastive learning regularization strategy that incorporates a unique methodology for constructing negative samples, significantly enhances the visual quality of underwater images, establishing its innovative and practical applicability.
- 204
- SGDNet176
Experimental results on both authentically and synthetically distorted IQA datasets demonstrate the superiority of the SGDNet, as compared to the state-of-the-art approaches.
- 159
- A Dilated Inception Network for Visual Saliency Prediction158
This work proposes an end-to-end dilated inception network (DINet) for visual saliency prediction that captures multi-scale contextual features effectively with very limited extra parameters and improves the performance of the saliency model by using a set of linear normalization-based probability distribution distance metrics as loss functions.
- 154
- 148
- 132
- 125
- 117
- 115
- 115
- No-Reference Quality Assessment for 360-Degree Images by Analysis of Multifrequency Information and Local-Global Naturalness101
This model is the first no-reference quality assessment method for 360-degree images that combines multifrequency information and image naturalness and outperforms state-of-the-art full-reference (FR) and NR approaches.
- 99
- 96
- Progressive Self-Guided Loss for Salient Object Detection96
It is demonstrated that this new loss function can guide the SOD model to highlight more complete salient objects step-by-step and meanwhile help to uncover the spatial dependencies of the salient object pixels in a region growing manner.
- 90
- 87
- Underwater Image Enhancement With Cascaded Contrastive Learning84
The proposed CCL-Net involves two cascaded stages, i.e., a color correction stage tailored to the color deviation issue and a haze removal stage tailored to improve the visibility and contrast of underwater images, and applies contrastive loss as an additional constraint to guide the training of each stage.
- Blind quality assessment for image superresolution using deep two-stream convolutional networks82
Experimental results on three publicly available SR image quality databases demonstrate the effectiveness and generalization ability of the proposed DeepSRQ method compared with state-of-the-art image quality assessment algorithms.
- A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels79
A new weakly-supervised SOD task under hybrid labels, where the supervision labels include a large number of coarse labels generated by the traditional unsupervised method and a small number of real labels, and a new pipeline framework with three sophisticated training strategies is designed.
- 73
- 71
- 66
- 65
- Toward Top-Down Just Noticeable Difference Estimation of Natural Images65
This work conducts subjective experiments to determine the critical points of 500 images and finds that the distribution of cumulative normalized KLT coefficient energy values over all 500 images at these critical points can be well characterized by a Weibull distribution.
- 63
- 58
- 53
- MMNet53
This paper proposes a novel Multi-stage and Multi-Scale Fusion Network (MMNet), which consists of a cross-modal multi-stage fusion module (CMFM) and a bi-directionalmulti-scale decoder (BMD) that can achieve consistently superior performance over the other state-of-the-art methods on six popular RGB-D datasets when evaluated by 8 different metrics.
- BCS-Net: Boundary, Context, and Semantic for Automatic COVID-19 Lung Infection Segmentation From CT Images50
A novel network for automatic COVID-19 lung infection segmentation from computed tomography (CT) images, named BCS-Net, which considers the boundary, context, and semantic attributes, and outperforms the existing competitors both qualitatively and quantitatively.
- Three-dimensional visual comfort assessment via preference learning50
This study proposes to train a robust VCA model on a set of preference labels instead of MOSs, inspired by the fact that humans tend to conduct a preference judgment between two stereoscopic images in terms of visual comfort.
- 49
- 48
- Consistent Quality Oriented Rate Control in HEVC Via Balancing Intra and Inter Frame Coding48
A new framework is proposed for consistent quality oriented IQP prediction, and then unqualified IQP candidates are removed using the proposed penalty term, and this method reduces quality fluctuation greatly and can have satisfactory results on rate-distortion performance, bit accuracy and buffer control.
- Object Segmentation by Mining Cross-Modal Semantics47
A novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features, with the aim of controlling the modal contribution based on relative entropy.
- 47
- 46
- 45
- 45
- 45
- 44
- A depth perception and visual comfort guided computational model for stereoscopic 3D visual saliency44
Experimental results show that the proposed 3D saliency model outperforms the state-of-the-art models on predicting human eye fixations and visual comfort assessment.
- 43
- Blind Quality Assessment of Dense 3D Point Clouds with Structure Guided Resampling43
The proposed Structure Guided Resampling (SGR) is a general-purpose blind quality assessment method without the assistance of any reference information that can compete with state-of-the-art full-reference, reduced-reference, and no-reference quality assessment algorithms.
- 43
- 42
- 41
- 40
- Automated Quality Assessment of Fundus Images via Analysis of Illumination, Naturalness and Structure40
A fundus image quality classifier via the analysis of illumination, naturalness, and structure is proposed, which use three effective secondary indices (or 5-D feature set) and different classification methods to determine the recommendation indexes of fundus images for further diagnosis.
- 39
- Vision-Language Consistency Guided Multi-Modal Prompt Learning for Blind AI Generated Image Quality Assessment39
This letter introduces learnable textual and visual prompts in language and vision branches of CLIP models, respectively, and designs a text-to-image alignment quality prediction task, whose learned vision-language consistency knowledge is used to guide the optimization of the above multi-modal prompts.
- Blind stereoscopic 3D image quality assessment via analysis of naturalness, structure, and binocular asymmetry39
Experimental results on four publicly available databases demonstrate that the proposed method of S3D quality assessment is superior to several mainstream image quality assessment (IQA) metrics.
- 38
- 38
- Pixel-Level Anomaly Detection via Uncertainty-aware Prototypical Transformer37
This work designs a memory-guided prototype learning transformer encoder to learn and memorize the prototypical representations of anomalies for enabling the model to capture the diversity of anomalies and proposes an uncertainty-aware prototypical transformer decoder, which takes into account both the diversity and uncertainty of anomaly.
- 36
- No-reference quality assessment of underwater image enhancement36
This paper proposes a highly effective yet accurate no-reference quality assessment method to evaluate UIE results by analyzing the statistics of underwater images, and first extracts quality-aware features in terms of three key aspects: colorfulness; contrast; 3) visibility.
- Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric36
A new sparse representation-based method is proposed, which computes the quality of AST image according to the sparse feature similarity, and experimental results on the AST-IQAD have demonstrated the superiority of the proposed method.
- 35
- 35
- 35
- 35
- 34
- 34
- 32
- 32
- 32
- 32
- Learning a referenceless stereopair quality engine with deep nonnegativity constrained sparse autoencoder32
The contribution of the model is that hierarchical feature evolution and nonlinear feature mapping are jointly optimized in a unified and perceptual-aware deep network (DNCSAE), which well resembles several important visual properties, i.e., hierarchy, sparsity, and non-negativity.
- 31
- 31
- 31
- 31
- 30
- 30
- Learning a Unified Blind Image Quality Metric via On-Line and Off-Line Big Training Instances29
Through extensive experiments, it has been validated that the proposed blind IQM is capable of simultaneously inferring the quality of NS and SC images, and it has attained superior performance as compared with popular and state-of-the-art IQMs on the subjective NS andSC image quality databases.
- 28
- No-Reference Point Cloud Quality Assessment via Graph Convolutional Network28
A novel no-reference PCQA method is proposed by using a graph convolutional network (GCN) to characterize the mutual dependencies of multi-view 2D projected image contents to achieve superior performance than state-of-the-art quality assessment metrics.
- 28
- 28
- 28
- Image Quality Assessment–driven Reinforcement Learning for Mixed Distorted Image Restoration28
The limitations of a single deep network in dealing with multiple distortion types and then a hierarchical toolkit with distinguished powerful tools are illustrated and an efficient representation of images combined with a reinforcement learning (RL) paradigm helps to deal with tool noise in continuous restoration.
- A brief survey on adaptive video streaming quality assessment28
It is found that existing video streaming QoE assessment models still have limited performance, which makes it difficult to be applied in practical communication systems, and based on the success of deep learned feature representations for traditional video quality prediction, the off-the-shelf deep convolutional neural network (DCNN) is applied.
- 28
- 27
- 26
- 3D Visual Attention for Stereoscopic Image Quality Assessment25
The experimental results show that compared with other schemes, the proposed 3D visual attention-based pooling scheme can achieve higher consistency with the subjective assessment of stereoscopic images.
- Efficient CU and PU Decision Based on Neural Network and Gray Level Co-Occurrence Matrix for Intra Prediction of Screen Content Coding24
This work proposes an efficient CU and prediction unit (PU) decision based on neural network (NN) and gray level co-occurrence matrix (GLCM) for SCC intra prediction and outperforms eight state-of-the-art algorithms in terms of computational complexity reduction and RD performance.
- Visual discomfort relaxation for stereoscopic 3D images by adjusting zero-disparity plane for projection24
A visual comfort improvement scheme by adjusting zero-disparity plane (ZDP) for projection that is effective in improving visual comfort while preserving the unchanged depth sensation is proposed.
- 24
- 23
- 23
- 23
- 23
- 22
- Blind Quality Assessment of 3D Dense Point Clouds with Structure Guided Resampling22
This paper proposes an objective point cloud quality index with Structure Guided Resampling (SGR) to automatically evaluate the perceptually visual quality of 3D dense point clouds and proves that the proposed SGR can compete with state-of-the-art full- reference, reduced-reference, and no-reference quality assessment algorithms.
- 21
- 21
- Learning content-specific codebooks for blind quality assessment of screen content images21
A novel blind quality assessment method for screen content images (SCIs) by learning content-specific codebooks that delivers low computational complexity, making it well suitable for real-time applications.
- 20
- 20
- 20
- 20
- 20
- Quality Assessment of Retargeted Images Using Hand-Crafted and Deep-Learned Features20
A new image retargeting quality assessment metric is proposed, which constructs the metric using both hand-crafted features and deep-learned features, and can achieve superior performance to the state-of-the-art metrics.
- 19
- 18
- 18
- Local and global sparse representation for no-reference quality assessment of stereoscopic images18
Experimental results on three 3D image quality databases show that in comparison with the existing methods, the devised BLQELGSR can achieve better prediction performance to be in line with subjective assessment.
- 17
- Perception-Oriented Bidirectional Attention Network for Image Super-Resolution Quality Assessment17
The Perception-oriented Bidirectional Attention Network (PBAN) for image SR FR-IQA is proposed, which is composed of three modules: an image encoder module, a perception-oriented bidirectional attention (PBA) module, and a quality prediction module that outperforms state-of-the-art quality assessment methods.
- 17
- 17
- 17
- TSPR: Deep network-based blind image quality assessment using two-side pseudo reference images17
A deep network-based blind image quality assessment (BIQA) using two-side pseudo reference (TSPR) images is presented, which delivers superior performance over the state-of-the-art NR methods.
- Leveraging visual attention and neural activity for stereoscopic 3D visual comfort assessment17
A novel two-stage framework is proposed to address the challenges of visual comfort assessment, and comparison results with five state-of-the-art relevant models on a standard benchmark database confirm the superior performance of the proposed method.
- 16
- 16
- 16
- 16
- 15
- 14
- A large-scale remote sensing database for subjective and objective quality assessment of pansharpened images14
A large-scale database named Pansharpened Remote Sensing Image Quality Database (PRSIQD) is constructed from both qualitative and quantitative perspectives, which contains 13,620 pansharpens images acquired from IKONOS, QuickBird, Gaofen-1, WorldView-2, World view-3 and WorldView -4 satellite sensors.
- 13
- Multimodal Representation Distribution Learning for Medical Image Segmentation13
A novel multi-modal learning method for medical image segmentation that is adopted to model the commonalities and differences between text and image, and design a prompt encoder to achieve fine-grained segmentation.
- 13
- 13
- Visual comfort assessment for stereoscopic images based on sparse coding with multi-scale dictionaries13
Experimental results on two benchmark databases demonstrate that the proposed VCA method can achieve higher consistency with human subjective perception compared with some state-of-the-art approaches.
- 12
- 12
- 12
- 12
- Multistage Pooling for Blind Quality Prediction of Asymmetric Multiply-Distorted Stereoscopic Images12
- Using Saliency-Weighted Disparity Statistics for Objective Visual Comfort Assessment of Stereoscopic Images12
A novel two-stage objective VCA framework is proposed that combines an adaptive 3D visual saliency detection model to derive saliency map of a stereoscopic image, and a set of saliency-weighted disparity statistics are computed and combined to form a single feature vector to represent a stereoscope in terms of visual comfort.
- 11
- 11
- CD-iNet: Deep Invertible Network for Perceptual Image Color Difference Measurement11
The resulting metric, referred to as CD-iNet, is end-to-end optimized on color patch datasets and image datasets simultaneously and can produce competitive local CD maps without requiring dense supervision and be robust against geometric distortions.
- 11
- 11
- 11
- Quality Assessment of 3D Synthesized Images via Measuring Local Feature Similarity and Global Sharpness11
A new quality model for 3-D synthesized images is proposed by measuring the block-wise texture similarity and color contrast similarity in critical areas, and the global gradient magnitude deviation, which achieves higher quality prediction accuracy than the state-of-the-art quality metrics.
- 10
- 10
- 10
- 10
- Optimizing visual comfort for stereoscopic 3D display based on color-plus-depth signals10
The main motivation of this work is to remap the depth range of color-plus-depth signals to a new depth range that is suitable to comfortable S3D display, and presents a two-stage global and local depth optimization solution to solve the visual comfort problem.
- 9
- MorphQPV: Exploiting Isomorphism in Quantum Programs to Facilitate Confident Verification9
MorphQPV is proposed, a confident assertion-based verification methodology that can effectively obtain the program states under various inputs while avoiding repeated executions and is formulated as a constraint optimization problem with a confidence estimation model to enable rigorous analysis.
- Progressive Point Cloud Denoising with Cross-Stage Cross-Coder Adaptive Edge Graph Convolution Network9
This paper proposes a Cross-stage Cross-coder Adaptive Edge Graph Convolution Network (C2AENet) to denoise point clouds and introduces a geometric graph and adaptively calculate edge attention based on the local and global structural information of the points.
- 9
- Prediction of water quality based on artificial neural network with grey theory9
The results showed that the prediction by using the generalized regression neural network has the averaged relative error 0.61%, and c <0.65, p>0.7.
- 8
- 8
- Learning Video Salient Object Detection Progressively From Unlabeled Videos8
A novel VSOD method via a progressive framework that locates and segments salient objects in sequence without utilizing any video annotation is proposed, and it is demonstrated that the method outperforms the state-of-the-art weakly and unsupervised methods.
- 8
- 7
- 7
- 7
- 7
- 7
- SKIP: Accurate Fall Detection Based on Skeleton Keypoint Association and Critical Feature Perception7
- 6
- 6
- 6
- 6
- Deep Decomposition and Bilinear Pooling Network for Blind Night-Time Image Quality Evaluation6
A novel deep decomposition and bilinear pooling network (DDB-Net) to better address the issue of night-time images (NTIs) which usually suffers from complicated authentic distortions such as reduced visibility, low contrast, additive noises, and color distortions.
- 6
- Security of MVD-based 3D video in 3D-HEVC using data hiding and encryption6
Experimental results demonstrate that the proposed method keeps the good quality of the virtual view after embedding data, protects the video contents efficiently, and has a limited influence on the bitrate.
- 5
- 5
- 5
- 5
- 5
- The safety evaluation of management in chemical enterprise with generalized regression neural network5
Artificial neural networks including the back-propagation neural network, radial basis function neural network and generalized regression neural network were used to evaluate and predict the safety of chemical enterprises.
- StereoEditor: controllable stereoscopic display by content retargeting5
A stereoscopic editing method, named as StereoEditor, to achieve controllable stereoscopic display that can achieve a better tradeoff among shape preservation, depth control and object layout, leading to promising viewing experience.
- 4
- 4
- 4
- 4
- A Data Matrix Code Recognition Method Based on L-Shaped Dashed Edge Localization Using Central Prior4
A novel DM code recognition method based on locating the L-shaped dashed edge by incorporating the prior information of the center of the DM code is proposed, which outperforms the compared methods in terms of recognition accuracy rate and time consumption.
- 4
- Seam Manipulator: Leveraging Pixel Fusion for Depth-Adjustable Stereoscopic Image Retargeting4
This paper proposes a seam manipulator tool to optimize the process for scaling factor determination of stereoscopic seams and can achieve promising performances on depth perception and visual comfort adjustment for better visual experience.
- 4
- Combining Global and Local Feature Analyses for Quality Evaluation of Tone-Mapped HDR Images4
A no reference (NR) quality evaluation method for tone-mapped (TM) HDR images based on global and local feature analyses that outmatches several mainstream NR image quality assessment methods designed for both natural scene images and TM HDR images.
- Simulating receptive fields of human visual cortex for 3D image quality prediction4
A new 3D image quality prediction approach by simulating receptive fields (RFs) of human visual cortex by extracting the RFs from a complete visual pathway, and calculating their similarity indices between the reference and distorted 3D images.
- 3
- 3
- 3
- 3
- 3
- 3
- SGNet: Style-Guided Network With Temporal Compensation for Unpaired Low-Light Colonoscopy Video Enhancement3
A Style-Guided Network (SGNet) for unpaired Low-Light Colonoscopy Video Enhancement (LLCVE) is proposed, in which a Temporal Compensation module and a Style Guidance module are proposed to alleviate the flickering problem and achieve flexible style transfer.
- 3
- 3
- 3
- 3
- 3D Visual Comfort Assessment via Sparse Coding3
Experimental results on the proposed VCA metric demonstrate that the proposed metric outperforms some representative VCA metrics in the regard of consisting with human subjective judgment.
- 3
- 2
- 2
- 2
- Delving into Underwater Image Utility: Benchmark Dataset and Prediction Model2
The proposed DeepUIUA model has superior performance compared with the existing NR-IQA methods in assessing UIUS and is comprehensively compared with that of 14 state-of-the-art no-reference image quality assessment (NR-IQA) methods by using the OD-UIUA dataset as the benchmark.
- 2
- InvJND: Just Noticeable Difference Estimation via Deep Invertible Network2
The well-known distortion visibility metric, i.e., High Dynamic Range Visual Difference Predictor (HDR-VDP), is utilized as an automatic tool to efficiently generate pseudo CPL labels, thereby creating a large-scale dataset with 8, 965 high-resolution pristine images and their corresponding pseudo CPL images as labels for JND model training.
- 2
- 2
- 2
- Dynamically attentive viewport sequence for no-reference quality assessment of omnidirectional images2
A novel no-reference ODI quality evaluation method that resorts to the law of gravity to detect the dynamically attentive regions of humans when viewing ODIs and can adopt a regression model to map the extracted QAFs to a single predicted quality score is proposed.
- Blind quality assessment for multiply distorted stereoscopic images towards IoT-based 3D capture systems2
A novel blind image quality assessment method towards IoT-based 3D capture systems is developed for multiply-distorted stereoscopic images (MDSIs), in which five complementary channels are jointly considered in dictionary learning for characterizing the monocular receptive field (MRF) and binocular receptiveField (BRF) properties of the visual cortex in response to MDSIs.
- User Controllable Content Retargeting and Depth Adaptation for Stereoscopic Display2
The experimental results demonstrate that the method achieves a preferable tradeoff among accuracy, comfortability, and controllability of information presentation in retargeting, obtaining satisfactory visual experience for users.
- Measuring Depth Perception for Stereoscopic Images Using a Phase-shift Model2
An effective depth perception assessment index for stereoscopic images using a phase-shift model that achieves high consistency alignment with subjective assessment is presented.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Codebook-Empowered Analysis-Friendly Extreme Underwater Image Compression–
A novel -quantized (VQ) codebook-driven framework for machine-centric UIC that effectively harnesses inter-image redundancy, combats joint degradation, and delivers compact, analysis-friendly representations, establishing a new paradigm for machine-centric UIC.
- –
- –
- –
- –
- –
- –
- –
- Toward Realistic Low-Light Image Enhancement via ISP-Driven Data Modeling–
This paper proposes an image signal processing (ISP)-driven data synthesis pipeline that addresses challenges by generating scalable paired training data and applies it to existing LLIE methods, demonstrating its impact on improving their practicality and generalizability in real-world applications.
- –
- SP-UIQA: Fusion segmentation priors and multi-scale features for underwater image quality assessment–
- –
- –
- –
- –
- DGNet: dynamic gradient-guided network for water-related optical image enhancement–
Experiments on multiple public datasets show that DGNet outperforms the latest methods, and extensive qualitative experiments have demonstrated that DGNet exhibits precise control over fine-grained features, highlighting its practical utility.
- –
- –
- –
- –
- –
- The prediction of the gas emission with artificial neural network–
This paper predicted the gas emission in mining face with the back propagation neural network, the radial basis function neural network and the general regression neural network.
- Implementation and evaluation distributed mixed pixels analysis algorithm for hyperspectral image based on constraint non-negative matrix factorization–
A new NMF-based mixed data analysis algorithm is presented, with maximum overall coverage constraint introduced in traditional NMF, to analyze mixed data in highly mixed hyperspectral data without pure pixels.
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 2026-10-14. 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.