Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Baolong GuoSuggested from co-authorship
- Jeng‐Shyang PanSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works299 from public data
- MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment442
A no-reference IQA metric based on deep meta-learning that outperforms the state-of-the-arts by a large margin and can be easily generalized to authentic distortions, which is highly desired in real-world applications of IQA metrics.
- 270
- 246
- 237
- 168
- 167
- No-Reference and Robust Image Sharpness Evaluation Based on Multiscale Spatial and Spectral Features144
- 137
- Personalized Image Aesthetics Assessment with Rich Attributes132
Experimental results indicate that the conditional PIAA model can outperform the control group, which is also the first attempt to demonstrate how image aesthetics and subject characters interact to produce the intricate personalized tastes on image aesthetics.
- 131
- 122
- 121
- Geometrically invariant image watermarking using Polar Harmonic Transforms119
Experimental results illustrate that the proposed scheme outperforms ZM/PZM based schemes in terms of embedding capacity and watermark robustness and is also robust to both geometric and signal processing based attacks.
- 112
- 106
- 101
- Orientation selectivity based visual pattern for reduced-reference image quality assessment98
Experimental results on five public databases demonstrate that the proposed RR IQA method has performance consistent with the human perception under a small amount of reference data (only 9 values).
- 97
- AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception96
An Expert-labeled Aesthetics Perception Database (EAPD), which features diversified image contents and high-quality annotations provided by professional aesthetic experts, and a set of integrative criteria to measure the aesthetic perception abilities of MLLMs from four perspectives.
- RIRNet96
This work proposes a novel no-reference VQA framework named Recurrent-In-Recurrent Network (RIRNet), which integrates concepts from motion perception in human visual system (HVS), which is manifested in the designed network structure composed of low- and high- level processing.
- Detecting copy-move forgery under affine transforms for image forensics94
A method for detecting this kind of image tampering based on circular pattern matching using Polar Harmonic Transform and lexicographically sorting the forged regions are detected by finding the similar block pairs after proper post-processing.
- AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception89
A comprehensively annotated Aesthetic Multi-Modality Instruction Tuning (AesMMIT) dataset is introduced, which serves as the footstone for building multi-modality aesthetics foundation models, achieving multi-modality Aesthetic Expert models, dubbed AesExpert.
- 89
- An efficient forgery detection algorithm for object removal by exemplar-based image inpainting89
An efficient forgery detection algorithm for object removal by exemplar-based inpainting is presented, which integrates central pixel mapping (CPM), greatest zero-connectivity component labeling (GZCL) and fragment splicing detection (FSD).
- 80
- 76
- No-reference quality assessment of deblocked images75
Experimental results conducted on the DBID database demonstrate that the proposed metric is effective in evaluating the quality of deblocked images, and it significantly outperforms the existing metrics.
- A robust forgery detection algorithm for object removal by exemplar-based image inpainting73
Inspired by the strong ability of joint probability density matrix (JPDM) in characterizing such correlation, a hybrid forensics strategy is proposed which can effectively detect object removal by exemplar-based inpainting either with or without post-processing.
- 69
- 68
- Reversible data hiding based on an adaptive pixel-embedding strategy and two-layer embedding68
A novel RDH method based on pixel value ordering and prediction-error expansion that can embed data adaptively into a block according to the local complexity and outperforms existing RDH methods.
- Localized image watermarking in spatial domain resistant to geometric attacks68
Simulation results show that the proposed scheme is robust to both geometric attacks and traditional signal processing attacks.
- SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network67
A novel Scene-Object interreLated Visual Emotion Reasoning network (SOLVER) to predict emotions from images and demonstrates that the proposed SOLVER consistently outperforms the state-of-the-art methods by a large margin.
- 66
- 65
- 60
- Detecting seam carving based image resizing using local binary patterns60
A blind image forensics approach is proposed for seam-carved forgery detection and shows that compared with the state-of-the-art methods, the proposed approach improves the detection accuracy by 3.5-19.1% for resized images with different scaling ratios.
- Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention57
A novel feature-level masked processing frame-work: VSR with Masked Intra and inter-frame Attention (MIA-VSR), which improves the memory and computation efficiency over state-of-the-art methods, without trading off PSNR accuracy.
- Accurate and Lightweight Image Super-Resolution With Model-Guided Deep Unfolding Network56
This paper presents and advocate an explainable approach toward SISR named model-guided deep unfolding network (MoG-DUN), and targets at breaking the coherence barrier by integrating deep denoising and nonlocal regularization as trainable modules within a deep learning framework.
- 54
- A shallow convolutional neural network for blind image sharpness assessment54
Experiments on Gaussian blur images from LIVE-II, CSIQ, TID2008 and TID2013 demonstrate that CNN features with SVR achieves the best overall performance, indicating high correlation with human subjective judgment.
- 53
- Detecting image seam carving with low scaling ratio using multi-scale spatial and spectral entropies53
A blind detection approach is presented for seam carved image with low scaling ratio (LSR) and achieves superior detection accuracy over the state-of-the-art works, especially for resized image by seam carving with LSRs.
- Robust Depth Completion with Uncertainty-Driven Loss Functions52
This work introduces uncertainty-driven loss functions to improve the robustness of depth completion and handle the uncertainty in depth completion, and proposes a multiscale joint prediction model that can simultaneously predict depth and uncertainty maps.
- A Circular-Structured Representation for Visual Emotion Distribution Learning52
A well-grounded circular-structured representation to utilize the prior knowledge for visual emotion distribution learning is proposed and the results demonstrate that the proposed method outperforms the state-of-the-art methods.
- AesCLIP: Multi-Attribute Contrastive Learning for Image Aesthetics Assessment50
A CLIP-based multi-attribute contrastive learning framework for IAA, dubbed AesCLIP, which combines aesthetic attribute-based comment classification and attribute-aware learning, aiming to mitigate the domain shift from the general visual domain to the aesthetics domain.
- Can Signal-to-Noise Ratio Perform as a Baseline Indicator for Medical Image Quality Assessment50
Whether off-the-shelf NIQA models can predict MR image quality is considered by using SNR values as the reference scores, and the correlation betweenSNR values and NIQE results is evaluated.
- 48
- 47
- 47
- 46
- Multiple‐parameter fractional quaternion Fourier transform and its application in colour image encryption45
The proposed MPFrQFT-based encryption algorithm has an overall better performance than eight compared algorithms in security test and robustness test: it is more secure than theCompared frequency-based algorithms due to the larger key space and the more sensitive key `transform orders'; it is also more robust than the compared spatial-domain algorithms.
- No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics45
A no-reference quality metric for defocus deblured images based on Natural Scene Statistics (NSS) is presented and experimental results demonstrate the advantages of the proposed metric over the relevant state-of-the-arts.
- 44
- 44
- Rotation invariant watermark embedding based on scale-adapted characteristic regions44
Two rotation invariant watermark embedding schemes in the non-subsampled contourlet transform (NSCT) domain based on the scale-adapted local regions are presented and can efficiently resist both signal processing attacks and geometric attacks.
- 43
- 41
- A consistency evaluation of signal-to-noise ratio in the quality assessment of human brain magnetic resonance images41
When SNR measurement performs as the quality indicator of MR images, BRISQUE and BLIINDS-II can be conditionally used for the automated quality estimation of human brain MR images.
- 40
- AEDNet: Asynchronous Event Denoising with Spatial-Temporal Correlation among Irregular Data39
An innovative asynchronous event denoise neural network, named AEDNet, is established, which directly consumes the correlation of the irregular signal in spatial-temporal range without destroying its original structural property.
- Subjective and objective quality assessment for image restoration: A critical survey39
This survey paper provides a comprehensive description of the existing subjective quality databases, a thorough insight into existing objective quality metrics and two applications of image restoration quality metrics, namely, parameter selection and benchmarking image restoration algorithms.
- Blind image quality assessment with improved natural scene statistics model39
To take the fitting errors into account as well as the fitting parameters for feature extraction, and propose a novel NR IQA algorithm, the statistical distributions of the distorted images are discussed in detail.
- Image quality assessment based on multi-scale representation of structure38
An image quality assessment algorithm using representation of image structures in scale space based on the finding that difference-of-Gaussian (DoG) can capture the structures of an image with flexibility and it is sensitive to image degradations is presented.
- 37
- 37
- Fractional quaternion cosine transform and its application in color image copy-move forgery detection37
Experimental results demonstrate that the proposed efficient implementation method of FrQCT takes only half the computational time of the direct method, and the proposed FrQ CT-based forgery detection algorithm can achieve a better performance than some state-of-the-art algorithms, especially in the additional operation case.
- 36
- Multimodal medical image fusion based on discrete T chebichef moments and pulse coupled neural network36
A new multimodal medical image fusion method based on discrete Tchebichef moments and pulse coupled neural network to overcome the aforementioned problems and outperforms state‐of‐the‐art methods.
- Detecting video frame-rate up-conversion based on periodic properties of edge-intensity36
An edge-intensity based passive forensics approach is proposed to detect the possible FRUC operation in candidate video and shows that the proposed approach is not only effective for simple frame repetition and linear interpolation, but also valid for advanced FRUC techniques such as MCFI.
- Detecting video frame rate up-conversion based on frame-level analysis of average texture variation36
The proposed forensics approach is efficient and effective for the detection of existing typical FRUC approaches such as linear frame averaging and motion-compensated interpolation (MCI) and is superior to the existing approaches in terms of time efficiency and detection accuracy.
- 35
- Detection of image seam carving by using weber local descriptor and local binary patterns35
A blind forensics approach is proposed to detect resized images by seam carving by exploiting two excellent texture descriptors including Weber Local Descriptor and Local Binary Patterns for seam carving forgery detection.
- 34
- 34
- Starvqa: Space-Time Attention for Video Quality Assessment32
A novel space-time attention network for the VQA problem, named StarVQA, which designs a vectorized regression loss by encoding the mean opinion score to the probability vector and embedding a special vectorized label token as the learnable variable.
- 32
- 31
- 31
- Characteristic region based watermark embedding with RST invariance and high capacity31
Experimental results on Stirmark benchmark 4.0 show that the proposed scheme can resist both traditional signal processing attacks and geometric attacks and Comparisons also demonstrate the advantages of the scheme.
- 29
- Multi-Attention Segmentation Networks Combined with the Sobel Operator for Medical Images29
This work proposes a Sobel operator combined with multi-attention networks for COVID-19 lesion segmentation (SMA-Net) and shows that the average Dice similarity coefficient (DSC) and joint intersection over union (IOU) of the proposed SMA- net model are better than those in most existing segmentation networks.
- 29
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events28
A novel spatial-temporal collaboration network (STCNet) is proposed for event-based motion deblurring with a differential-modality based cross-modal calibration strategy to suppress redundancy for complementarity enhancement and an elaborate cross-modal co-attention mechanism to weight the contributions of them for importance balance.
- On the use of a scanpath predictor and convolutional neural network for blind image quality assessment28
This paper proposes an efficient method that estimates the quality of 2D images without access to the pristine image based on the relevant patches selected by saliency information and a convolution neural network.
- 28
- 28
- 27
- 27
- Deep Maximum a Posterior Estimator for Video Denoising27
This work presents a novel deep MAP-based video denoising method named MAP-VDNet with adaptive temporal fusion and deep image prior, and presents a robust multi-frame fusion strategy for predicting spatially varying fusion weights by a neural network.
- 27
- Seeking Subjectivity in Visual Emotion Distribution Learning26
A novel Subjectivity Appraise-and-Match Network (SAMNet) is proposed, aiming at assigning unordered emotion labels to ordered individual predictions in a one-to-one correspondence with the Hungarian algorithm, and a subjectivity loss is further proposed to guarantee the divergence between different individuals.
- 26
- 26
- Detecting Removed Object from Video with Stationary Background26
In this paper, the block based motion estimation method is employed to extract motion information from adjacent video frames to differentiate the authentic region and the forged region.
- 24
- Performance Evaluation of Visual Tracking Algorithms on Video Sequences With Quality Degradation24
The initial investigation shows that it is still challenging for effective object tracking for existing visual tracking algorithms on video sequences with quality degradation, and proposes a method for robustness measurement of visual tracking (RMVT) algorithms by accuracy rate and performance stability.
- Perceptual quality evaluation for image defocus deblurring24
A quality enhancement module is proposed based on Gray Level Co-occurrence Matrix (GLCM), which is mainly used to measure the loss of texture naturalness caused by deblurring, and demonstrates the effectiveness of the proposed method.
- GridSAR: Grid strength and regularity for robust evaluation of blocking artifacts in JPEG images24
A robust no-reference blocking artifacts evaluation metric for JPEG images based on grid strength and regularity (GridSAR) is presented, which achieves the state-of-the-art performance, and is robust to block misalignments.
- 23
- 23
- 23
- Uncertainty Learning in Kernel Estimation for Multi-stage Blind Image Super-Resolution23
This work introduces uncertainty learning in the latent space when estimating the blur kernel, aiming at improving the robustness to the estimation error, and proposes a novel SR network by unfolding the joint MAP estimator with a learned Laplacian Scale Mixture (LSM) prior and the estimated kernel.
- CNN-GRNN for Image Sharpness Assessment23
Experiments on Gaussian blurring images in LIVE, CSIQ, TID2008 and TID2013 show that CNN-GRNN outperforms the state-of-the-art algorithms and gets closer to human subjective judgment.
- An efficient and effective blind camera image quality metric via modeling quaternion wavelet coefficients23
The natural scene statistics of the third phase of QWT is used to measure structure degradations in the proposed CIQM, which outperforms the relevant state-of-the-art models for both authentically distorted images and multiply distorted images.
- Color image quality assessment based on sparse representation and reconstruction residual23
Experiments on public databases demonstrate that the proposed method achieves promising performance in evaluating traditional distortions, and it outperforms the existing metrics when used for quality evaluation of color-distorted images.
- Dehazed Image Quality Evaluation: From Partial Discrepancy to Blind Perception22
This paper proposes a Reduced-Reference dehazed image quality evaluation approach based on Partial Discrepancy (RRPD) and then extends it to a No-Reference quality assessment metric with Blind Perception (NRBP), and introduces three groups of features: luminance discrimination, color appearance, and overall naturalness.
- 22
- Event-based Motion Deblurring with Modality-Aware Decomposition and Recomposition22
A novel dual-stream based framework is proposed for motion deblurring (DS-Deblur), which flexibly utilizes the respective advantages from frame and event and is well-grounded on the hierarchical process in twopathway visual system.
- 22
- Inferring Personality Traits from Attentive Regions of User Liked Images Via Weakly Supervised Dual Convolutional Network22
An end-to-end weakly supervised dual convolutional network (WSDCN) for personality prediction, which consists of a classification network and a regression network, and is able to predict the BF personality traits simultaneously by training the WSDCN network only once.
- Rotation, scaling and translation invariant image watermarking using feature points22
A novel robust image watermarking scheme is presented to resist rotation, scaling, and translation (RST) and is robust to traditional signal processing attacks, RST attacks, as well as some combined attacks.
- 21
- 21
- Evaluating attributed personality traits from scene perception probability21
Inspired by the relationship between users’ attributed personality traits and preferred image scenes, a personality prediction method based on image scene perception probability is proposed that is superior to the state-of-the-art approaches.
- Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Survey20
The NTIRE 2024 Portrait Quality Assessment Challenge is reviewed, highlighting the proposed solutions and results, and providing a gauge for the current state-of-the-art in Portrait Quality Assessment.
- 20
- Transductive Aesthetic Preference Propagation for Personalized Image Aesthetics Assessment20
A meta learning-based Transductive Aesthetic Preference Propagation (TAPP-PIAA) algorithm under regression manner to substitute the fine-tuning strategy and can surpass the state-of-the-art methods on benchmark databases.
- Perceptual quality assessment for multimodal medical image fusion20
Experimental results based on the MMIFID indicate that the presented method outperforms the existing image fusion quality evaluation metrics, and it provides a satisfactory correlation with subjective scores, which shows effectiveness in the quality assessment of medical fused images.
- Visual structural degradation based reduced-reference image quality assessment20
Experimental results demonstrate that the proposed RR IQA method is highly consistent with the human perception, which uses a small amount of reference data and achieves a promising improvement on quality evaluation accuracy.
- Geometrically robust image watermarking using scale-invariant feature transform and Zernike moments20
A robust image watermarking algorithm is proposed using scale-invariant feature transform (SIFT) and Zernike moments and is robust to both geometric attacks and signal processing attacks.
- 19
- BMI-Net: A Brain-inspired Multimodal Interaction Network for Image Aesthetic Assessment19
A brain-inspired multimodal interaction network (BMI-Net) that simulates how the association area of the cerebral cortex processes sensory stimuli is proposed and the knowledge integration LSTM (KI-LSTM) is proposed to learn the image-text interaction relation.
- 19
- 19
- Self-feature Distillation with Uncertainty Modeling for Degraded Image Recognition19
This paper proposes a novel self-feature distillation method with uncertainty modeling for better producing HQ-like features from low-quality observations and demonstrates that this model can extract HQ- like features better even when the inputs are degraded images, which makes the model more robust than other approaches.
- 19
- 18
- 18
- 18
- 18
- 18
- 17
- Learning for Motion Deblurring with Hybrid Frames and Events17
A novel dual-stream based framework is proposed for motion deblurring (DS-Deblur), which flexibly utilizes the respective advantages from frame and event and is well-grounded on the hierarchical process in twopathway visual system.
- No-reference quality assessment of DIBR-synthesized videos by measuring temporal flickering17
A two-stage flickering region detection method is proposed by calculating the gradient distance between the matching blocks in adjacent frames followed by a refinement operation and the distortion intensity of flickering regions is measured in singular value decomposition domain.
- 16
- Personalized Image Aesthetics Assessment with Attribute-guided Fine-grained Feature Representation16
Experimental results show that the proposed attribute-guided fine-grained feature-aware personalized image aesthetics assessment method outperforms existing mainstream PIAA methods, and can effectively infer users' personalized aesthetics of images.
- Training-free referenceless camera image blur assessment via hypercomplex singular value decomposition16
A novel training-free blind quality assessment method considering the integral color information and singular values of the distorted image is proposed to evaluate the sharpness of camera images and results have demonstrated the effectiveness of the proposed metric compared with popular sharpness image quality metrics.
- 16
- 15
- 15
- Blind image quality prediction with hierarchical feature aggregation15
In this paper, hierarchical degradation is systematically analyzed by quantitative and qualitative experiments using interpretable hierarchical features and a novel end-to-end BIQA framework based on hierarchical feature aggregation is proposed, which eminently analyzed the degradations and correlations on hierarchical features.
- 14
- 14
- 14
- 14
- 14
- 14
- 14
- Attended Visual Content Degradation Based Reduced Reference Image Quality Assessment14
A novel attended visual content degradation-based RR IQA method is introduced and experimental results demonstrate that the proposed method uses only several values and performs consistently with the subjective perception.
- Blind quality index for camera images with natural scene statistics and patch-based sharpness assessment14
This paper addresses the problem of quality assessment of camera images from two respects, natural scene statistics (NSS) and local sharpness, and associated three types of features, and is the first to propose modular framework for camera images.
- 14
- 14
- 13
- CUID: A New Study Of Perceived Image Quality And Its Subjective Assessment13
This paper presents a new study of image quality perception where subjective ratings were collected in a controlled lab environment and investigates how quality perception is affected by a combination of different categories of images and different types and levels of distortions.
- 12
- IE-IQA: Intelligibility Enriched Generalizable No-Reference Image Quality Assessment12
This paper presents a new framework for building highly generalizable image quality model by integrating the intelligibility, and demonstrates that the proposed approach outperforms the state-of-the-art metrics, and theelligibility task consistently improves metric performance and generalization ability.
- Blind Quality Assessment of Dehazed Images by Analyzing Information, Contrast, and Luminance.12
A blind quality metric for dehazing images is proposed and three groups of features are extracted for characterizing the quality of dehazed images, including information, contrast, and luminance, which demonstrates the efficiency and advantage of the proposed metric.
- 11
- Deep Shape-Texture Statistics for Completely Blind Image Quality Evaluation11
The proposed DSTS delicately utilizes shape-texture statistical relations between different data scales in the deep domain and achieves state-of-the-art (SOTA) quality prediction performance on images with artificial and authentic distortions.
- 11
- 11
- Quality assessment for view synthesis using low-level and mid-level structural representation11
A quality metric for view synthesis using both Low-level and Mid-level Structural representation (LMS), aiming to accurately evaluate the distortions in the whole view synthesis process.
- Towards a blind image quality evaluator using multi-scale second-order statistics11
A Blind image Quality Evaluator based on Multi-scale Second-order Statistics (BQEMSS) is proposed and extensive experiments on several public image quality databases demonstrate that B QEMSS is superior over the relevant state-of-the-art general-purpose blind IQA models.
- 10
- 10
- 10
- 10
- 10
- HVS Revisited: A Comprehensive Video Quality Assessment Framework10
A no-reference VQA framework with five modules simulating HVS with five representative characteristics is proposed, and extensive experiments show that the HVS-5M outperforms the state-of-the-art V QA methods.
- Perceptual quality evaluation for motion deblurring10
A new quality metric for motion deblurred images by measuring NRRB is proposed and Experimental results demonstrate that the proposed metric significantly outperforms the existing quality metrics.
- Reduced-reference quality assessment of DIBR-synthesized images based on multi-scale edge intensity similarity10
This paper presents a reduced-reference quality metric for DIBR-synthesized images by only extracting several feature values, namely multi-scale Edge Intensity Similarity (EIS).
- Asymmetric Hierarchical Difference-aware Interaction Network for Event-guided Motion Deblurring9
A novel Asymmetric Hierarchical Difference-aware Interaction Network (AHDINet) is proposed for event-based motion deblurring, which explores the complementarity of two modalities with differential dependence modeling of cross-modal hierarchical features.
- Attribute-Driven Multimodal Hierarchical Prompts for Image Aesthetic Quality Assessment9
The proposed IAQA method based on hierarchical prompts outperforms existing methods significantly on multiple IAQA databases and can explicitly simulate users' aesthetic judgment of images to obtain more precise aesthetic quality.
- 9
- 9
- 9
- No-reference quality assessment of compressive sensing image recovery9
A no-reference CS Recovered Image Quality (CSRIQ) metric based on the measurement of both local and global distortions in CS recovered images, which is used for automatic parameter selection for CS image recovery algorithms.
- 9
- High Capacity Watermark Embedding Based on Invariant Regions of Visual Saliency9
A new image watermarking scheme is presented to achieve high capacity information hiding and geometric invariance simultaneously and the idea of locally most salient region (LMSR) is proposed to generate the disjoint invariant regions.
- Combining Interest Point and Invariant Moment for Geometrically Robust Image Watermarking9
A new robust image watermarking scheme for resisting both traditional and geometric attacks, which is robust against traditional signal processing attacks, rotation, scaling, flipping, Stirmark random bending as well as combined attacks.
- Semantics-Aware Image Aesthetics Assessment using Tag Matching and Contrastive Ranking8
A semantics-aware image aesthetics assessment approach is presented, which first analyzes the semantic content of images and then models the aesthetic distinctions among images from two perspectives, i.e., aesthetic attribute and aesthetic level.
- 8
- 8
- No-reference Sharpness Index for Scanning Electron Microscopy Images Based on Dark Channel Prior8
The experimental results on the SEM blurred image database show that the proposed algorithm outperforms both the existing state-of-the-art image sharpness metrics and the general-purpose no-reference quality metrics.
- 8
- 8
- A novel fingerprinting algorithm with blind detection in DCT domain for images8
Experimental results show that the proposed blind fingerprint detection scheme has larger capacity and is more efficient than the existing algorithms.
- 8
- 7
- Transfer learning for just noticeable difference estimation7
A novel deep transfer learning-based pixel-wise JND estimation model based on residual dense network (RDN) is proposed and it is found that relevant knowledge from the learning experience of full reference image quality assessment (FR-IQA) can be applied to JND estimation.
- 7
- No-Reference Video Quality Assessment with Heterogeneous Knowledge Ensemble7
A novel no-reference VQA (NR-VQA) method with HEterogeneous Knowledge Ensemble (HEKE), which can theoretically reach a lower infimum, and learn richer representation due to the heterogeneity.
- DIBR-Synthesized Image Quality Assessment via Statistics of Edge Intensity and Orientation7
This letter proposes a DIBR-synthesized image quality metric by measuring the Statistics of both Edge Intensity and Orientation (SEIO) by using the Canny operator to detect edges.
- Naturalization of Screen Content Images for Enhanced Quality Evaluation7
A simple and effective method to naturalize SCIs, so that the traditional quality models can be applied for SCI quality prediction and bicubic interpolation-based up-sampling is proposed to achieve this goal.
- Color-Enriched Gradient Similarity for Retouched Image Quality Evaluation7
Experimental results demonstrate that the proposed metric outperforms the state-of-the-arts and the performance of RETIQUE is evaluated on a public Digitally Retouched Image Quality (DRIQ) database.
- NSCT-Based Multimodal Medical Image Fusion With Sparse Representation and Pulse Coupled Neural Network.7
A novel multi-modal medical image fusion method by combining sparse representation (SR) and pulse coupled neural network (PCNN) in nonsubsampled contourlet transform (NSCT) domain is presented which outperforms the state-of-the-art methods in subjective quality and objective evaluation criteria.
- 7
- Image Blur Assessment with Feature Points7
A new blind blur assessment metric based on feature points is proposed, which outperforms several no-reference image blur metrics, as well as some representative general-purpose blind image quality metrics.
- No-reference Quality Metric of Blocking Artifacts Based on Orthogonal Moments7
A no-reference quality metric for evaluating the blocking artifacts in images based on a finding that the blocking artifact has direct distribution on the distribution of discrete Tchebichef moments is presented.
- 7
- 7
- InstructCrop: Teaching Multimodal Large Language Models to Crop Aesthetic Images6
InstructCrop is introduced, a multimodal large language model (MLLM)-based AIC framework, which can understand user instructions and provide explanatory reasons for cropping results and corresponding explanations, and enables effective and interpretable image cropping, which aligns better with user intentions.
- 6
- Image Quality Caption with Attentive and Recurrent Semantic Attractor Network6
A novel quality caption model is inventively developed to assess the image quality with hierarchical semantics, in which the quality is represented as patterns of activation distributed across the diverse degradations on hierarchical semantics.
- Detection of seam carving‐based video retargeting using forensics hash6
A forensics hash-based tampering detection and localization approach is proposed for seam carving-based video retargeting and shows that the proposed forensics approach can effectively estimate the exact amount and rough locations of deleted seam carving surfaces.
- 5
- 5
- 5
- No‐reference quality assessment for live broadcasting videos in temporal and spatial domains5
A no-reference quality evaluation model for live broadcasting videos (LBVQA) in temporal and spatial domains is presented and the advantages of the proposed metric over the state-of-the-art image and video quality metrics are demonstrated.
- Scale-Space Feature Based Image Watermarking in Contourlet Domain5
A novel image watermarking scheme is presented by combining scale-space feature based watermark synchronization and nonsubsampled Contourlet transform (NSCT) based water mark embedding that can efficiently resist signal processing attacks, geometric attacks as well as some combined attacks.
- Image adaptive RST invariant watermark using pseudo-Zernike moments5
An image adaptive RST invariant watermark is proposed by using the rotation invariant property of pseudo-Zernike moments (PZM) and oddeven quantization and experimental results show its robustness to rotation and scaling.
- 4
- 4
- 4
- AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity4
- 4
- 4
- 4
- 4
- 4
- 4
- Blind quality assessment of gamut-mapped images via local and global statistical analysis4
This paper presents an objective blind image quality assessment (BIQA) metric for gamut-mapped images based on natural scene statistics that outperforms the state-of-the-art general-purpose BIQA models and achieves encouraging performance.
- Detecting Affine-Distorted Duplicated Regions in Images by Color Histograms4
This paper presents a method to detect the region-duplication forgery under affine distortions and proposes a post-processing scheme to reduce the false matches and the regions are located in a pixel-based manner, which is called pixel-based marking.
- Saliency Guided Gradient Similarity for Fast Perceptual Blur Assessment4
This letter presents a NR perceptual blur metric using Saliency Guided Gradient Similarity (SGGS), which produces blur scores with a fixed range of (0, 1), which features fixed range, fast computation and better consistency with the HVS.
- 4
- Video Watermarking by Space-Time Interest Points4
This letter presents a novel robust video watermarking scheme based on space-time interest points, which is a blind scheme and the watermark can be extracted from any position of the video.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- Perceptual Evaluation of Scanning Electron Microscopy Imaging.3
The present study shows that the existing quality metrics are limited in predicting the quality of SEM images, and creates a database composed of 650 SEM images and conducts user study.
- No reference quality evaluation of medical image fusion3
A no reference quality evaluation of medical image fusion is presented and it is revealed that the proposed quality evaluation metric is superior to the existing state‐of‐the‐art metrics, which is more applicable to evaluate MIF images.
- 3
- An Improved PSO Algorithm for Interval Multi-Objective Optimization Systems3
Results show that the proposed interval multiobjective particle swarm optimization algorithm is capable of generating excellent approximation of the true Pareto front.
- No-reference Image Quality Assessment With A Gradient-induced Dictionary3
Experimental results demonstrate that the proposed metric can generate quality scores highly consistent with human perception, and it outperforms the state-of-the-arts.
- 3
- Robust Image Watermarking Based on Scale-Space Feature Points3
This chapter introduces a set of image watermarking schemes which can resist both geometric attacks and traditional signal processing attacks simultaneously, and follows a uniform framework, which is based on the detection of scale-space feature points.
- 2
- 2
- 2
- Image Cropping with Content and Composition Attribute-aware Global Relation Reasoning2
An image cropping method based on the content and composition attribute-aware global relation reasoning, which aims at guiding the generation of cropped sub-images by exploring critical attributes based on content and composition as well as global object correlations that affect aesthetics in images.
- 2
- 2
- 2
- Inferring Personality Traits from User Liked Images via Weakly Supervised Dual Convolutional Network2
Experimental results on the annotated PsychoFlickr database show that the proposed end-to-end weakly supervised dual convolutional network for personality prediction is superior to the state-of-the-art approaches, and the BF personality traits can be predicted simultaneously by the trained WSDCN model.
- Color Image Quality Assessment with Quaternion Moments2
A full-reference color image quality assessment metric based on Quaternion Tchebichef Moments (QTMs) is presented, demonstrating that the proposed method outperforms the state-of-the-arts.
- No-Reference Quality Assessment of Camera-Captured Distortion Images2
The quality metric is achieved via an SVR-based machine learning tool and its performance is proved to be statistically better than state-of-the-art competitors on the CID2013 database, which is dedicated to the quality assessment of camera-captured images.
- A high capacity and strong robust fingerprinting for compressed images2
A digital fingerprinting algorithm based on non-subsampled contourlet transform (NSCT) for compressed images is proposed, devoted to high capacity and strong robustness for compressed image fingerprinting.
- 2
- Forecasting Coal and Rock Dynamic Disaster Based on Adaptive Neuro-Fuzzy Inference System2
Forecasting model of coal rock electromagnetic radiation was built with combining time series analyze and adaptive neuro-fuzzy inference system (ANFIS), which indicates that the ANFIS has better learning ability and generalization performance, thus, the model is creditable and feasible.
- 2
- A new Image denoising method based on the nonsubsampled contourlet transform2
A new image denoising scheme is presented, which combines the nonsubsampled Contourlet transform and Gaussian scale mixture model, which outperforms the existing schemes in regard of both the denoised performance and the edge preservation ability.
- A krawtchouk moment based video watermarking scheme2
A new video watermarking scheme based on Krawtchouk moments achieves good image quality and it is robust to frame cropping and common signal processing attacks.
- 1
- RAM-VQA: Restoration Assisted Multi-Modality Video Quality Assessment1
This work proposes the Restoration-Assisted Multi-modality VQA (RAM-VQA) framework, a novel approach to VQA that leverages video restoration as a proxy to explicitly model distortion-sensitive features and achieves state-of-the-art performance across diverse benchmarks.
- Low-light Image Enhancement Quality Assessment: A Real-World Dataset and An Objective Method1
A low light enhanced image quality assessment method based on Multi-level Illumination Injection and Hierarchical Discrepancy Perception (MIIHDP), which is to hierarchically inject separated illumination information into the feature extraction process, then tailor the processing of difference information at different scales to obtain a more comprehensive representation.
- 1
- 1
- 1
- Quality Index for Benchmarking Image Inpainting Algorithms with Guided Regional Statistics1
An objective quality index for benchmarking image inpainting algorithms that outperforms the relevant state-of-the-art quality metrics is presented.
- Sparse Representation Based Image Quality Assessment with Adaptive Sub-dictionary Selection1
A sparse representation based image Quality metric with Adaptive Sub-Dictionaries QASD is presented, with the consideration that sparse features are insensitive to weak distortions and image quality is affected by various factors.
- Visual pattern degradation based image quality assessment1
Inspired by the orientation selectivity mechanism in the primary visual cortex, a novel visual pattern is introduced to represent the structure of a local region and the proposed IQA method performs better than the existing IQA metrics.
- Frame-based skip mode decision for distributed video coding1
With the proposed technique, the encoding and decoding time are reduced by about 9% and 50% respectively and the rate-distortion performance is improved by an average of 0.49 dB compared with the well-known DISCOVER DVC codec.
- 1
- Gradient based restoration of coal mine images obtained by underground wireless transmissions1
Curvature-driven diffusion (CDD) principles were used to develop a novel gradient based image restoration algorithm that eliminates the staircase effect and accelerates the convergence rate.
- 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.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Content-Adaptive Image Retouching Guided by Attribute-Based Text Representation–
A content-adaptive curve mapping module, which leverages a series of basis curves to establish multiple color mapping relationships and learns the corresponding weight maps, enabling content-aware color adjustments, which achieves state-of-the-art performance.
- Towards Real-world Image Quality Assessment–
The latest advances in generalizable image quality assessment will be reviewed, with focus on the distortion diversity and content/theme/scene variation dilemmas.
- –
- No-Reference Quality Index for View Synthesis Based on Multi-scale Texture Naturalness–
A blind quality evaluation metric for the Synthesized Views based on multi-scale Texture naturalness (SVT) is proposed and the experimental results on the MCL-3D database demonstrate the superiority of the proposed SVT method.
- –
- –
- –
- –
- Content Based Invariant Image Watermarking with High Capacity–
This chapter proposes two methods that can embed high capacity watermark images, while maintaining robustness to the general geometric attacks, in a content based manner.
- –
- Watermark Synchronization Based on Locally Most Stable Feature Points–
Simulation results have demonstrated the effectiveness of the proposed feature based watermark synchronization scheme and the idea of locally most stable feature points (LMSP) is proposed to generate some non-overlapped circular areas.
- A statistic-quantization based image watermarking algorithm resisting geometric attacks–
Experimental results show that the proposed scheme is robust to rotation, scaling and cropping attacks, as well as some signal processing attacks, such as median filtering, added noise.
- Watermarking Based on Energy Region and Texture Feature–
Experimental results indicate that the presented scheme is transparent and robust to significant volumetric distortions (including additive noise, low-pass filtering and lossy compression) and a part of geometric distortions.
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.