Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks118 from public data
- Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement2,451
A novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network and shows that it generalizes well to diverse lighting conditions.
- 924
- LightenNet: A Convolutional Neural Network for weakly illuminated image enhancement506
A trainable Convolutional Neural Network is proposed for weakly illuminated image enhancement, namely LightenNet, which takes a weakly illumination image as input and outputs its illumination map that is subsequently used to obtain the enhanced image based on Retinex model.
- UIEC^2-Net: CNN-based underwater image enhancement using two color space405
This method is the first to use HSV color space for underwater image enhancement based on deep learning and efficiently and effectively integrate both RGB Color Space and HSV Color Space in one single CNN.
- A hybrid method for underwater image correction220
Subjective and objective performance evaluations demonstrate that the proposed method significantly improves both color and visibility of degraded underwater images, and is comparable to and even outperforms several state-of-the-art methods.
- 193
- Passive forensics for copy-move image forgery using a method based on DCT and SVD183
The proposed method can effectively detect multiple copy-move forgery and precisely locate the duplicated regions, even when an image was distorted by Gaussian blurring, AWGN, JPEG compression and their mixed operations.
- 170
- A Cascaded Convolutional Neural Network for Single Image Dehazing105
Qualitatively and quantitatively experimental results demonstrate that the proposed method effectively removes haze from such images, and outperforms several state-of-the-art dehazing methods.
- 105
- Is Underwater Image Enhancement All Object Detectors Need?101
This study uses 18 state-of-the-art underwater image enhancement algorithms, covering traditional, CNN-based, and GAN-based algorithms, to preprocess underwater object detection data and retrain seven popular deep learning-based object detectors using the corresponding results enhanced by different algorithms, obtaining 126 underwater object detection models.
- 99
- Underwater image enhancement by dehazing and color correction96
The enhanced images, as a result of implementing the proposed approach, are characterized by relatively genuine color, increased contrast and brightness, reduced noise level, and better visibility.
- Transductive Zero-Shot Learning With a Self-Training Dictionary Approach91
A bidirectional mapping-based semantic relationship modeling scheme that seeks for cross-modal knowledge transfer by simultaneously projecting the image features and label embeddings into a common latent space is proposed.
- Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation89
This work proposes a novel domain adaptation framework via cross-domain correlation distillation, called CCDistill, which achieves the state-of-the-art performance for nighttime semantic segmentation and is a one-stage domain adaptation network which can avoid affecting the inference time.
- Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning88
A novel stacked semantics-guided attention (S2GA) model to obtain semantic relevant features by using individual class semantic features to progressively guide the visual features to generate an attention map for weighting the importance of different local regions.
- Image denoising using modified Perona–Malik model based on directional Laplacian81
A modified Perona-Malik (MPM) model based on directional Laplacian, which diffuses image along the edge direction of the original image, is proposed, which can alleviate the staircasing effect, preserve sharp discontinuities, and remove noise simultaneously.
- 79
- Zero-Shot Learning via Latent Space Encoding76
Extensive experimental results on four benchmark datasets clearly demonstrate the superiority of the proposed encoder–decoder approach, namely latent space encoding (LSE), on several ZSL tasks, including traditional ZSL, generalized Z SL, and zero-shot retrieval.
- Single underwater image enhancement based on color cast removal and visibility restoration50
Experimental results demonstrate that the proposed underwater image-enhancement method can effectively remove color cast, improve contrast and visibility, and recover natural appearance of degraded underwater images.
- Conditional mutual information-based feature selection algorithm for maximal relevance minimal redundancy47
A feature selection algorithm based on conditional mutual information for maximal relevance minimal redundancy (CMI-MRMR) is proposed and compared with several feature selection algorithms to validate the performance and show that it can achieve better feature selection performance.
- Transductive Zero-Shot Learning With Adaptive Structural Embedding45
Two corresponding methods named Adaptive STructural Embedding (ASTE) and Self-PAced Selective Strategy (SPASS) for visual-semantic embedding and domain adaptation in cross-modality learning and unseen class prediction steps are presented.
- Manifold regularized cross-modal embedding for zero-shot learning37
A Manifold regularized Cross-Modal Embedding (MCME) approach for ZSL is proposed by formulating the manifold constraint for intrinsic structure of the visual features as well as aligning pairwise consistency in order to preserve the locally visual structure in the embedding process.
- 33
- TIENet: task-oriented image enhancement network for degraded object detection32
A task-oriented image enhancement network (TIENet) to directly improve degraded object detection’s performance by enhancing the degraded images by presenting a fast Fourier transform-based structure loss for the enhancement task.
- 32
- 25
- A feature selection algorithm based on redundancy analysis and interaction weight22
A feature selection algorithm based on redundancy analysis and interaction weight is proposed in this paper, which can obtain better feature selection performance.
- A Feature Selection Algorithm Based on Equal Interval Division and Minimal-Redundancy–Maximal-Relevance22
Experimental results demonstrate that the EID–mRMR algorithm can achieve better feature selection performance, and the idea of equal interval division is proposed and combined with ranking to process the interval of mutual information between features and the class label.
- 21
- Multi-Strategy Improved Flamingo Search Algorithm for Global Optimization17
An improved algorithm known as the Multi-Strategy Improved Flamingo Search Algorithm (IFSA) is presented, which utilizes a cube chaotic mapping strategy to generate initial populations, which enhances the quality of the initial solution set and provides a new optimization algorithm for solving complex optimization problems.
- Attention Network for Non-Uniform Deblurring17
A novel dense feature fusion block that consists of a channel attention module and a pixel attention module is proposed that is able to generate photo-realistic sharp images from real-world blurring images and outperforms state-of-the-art methods.
- Image copy-move forgery detection using SURF in opponent color space16
Experimental results show that the proposed CMFD method by using speeded-up robust feature SURF in the opponent color space can effectively expose the duplicated regions with various transformations, even when the duplication regions are flat.
- Semantic softmax loss for zero-shot learning15
This letter proposes a nonlinear approach to impose ZSL as a multi- class classification problem via a Semantic Softmax Loss by embedding the class semantic descriptors into the softmax layer of multi-class classification network.
- Zero-shot learning with regularized cross-modality ranking15
This paper employs the hinge ranking loss to exploit the structures among different modalities and devise efficient regularizers to constrain the variation of the samples in the identical modality.
- Salient object detection in low-light RGB-T scene via spatial-frequency cues mining14
This work proposes an RGB-T SOD model by mining spatial-frequency cues by mining spatial-frequency cues, called SFMNet, for low-light scenes, and can achieve higher accuracy than the existing models for low-light scenes.
- 14
- A Feature Selection Algorithm Based on Equal Interval Division and Conditional Mutual Information13
This paper proposes an objective function based on conditional mutual information, a method of equal interval division and ranking with the objective function to select features, and proposes a feature selection algorithm named EID-CMI that can achieve better feature selection performance.
- A feature subset selection algorithm based on equal interval division and three-way interaction information13
A feature subset selection algorithm based on equal interval division and three-way interaction information based on symmetric uncertainty between features and the class label to remove redundant features is proposed.
- EGAN: Non-uniform image deblurring based on edge adversarial mechanism and partial weight sharing network13
A generative adversarial network (GAN) framework based on an edge adversarial mechanism and a partial weight sharing network is proposed that is able to generate photo-realistic sharp images from real-world blurring images and outperforms state-of-the-art methods.
- Transformer guidance dual-stream network for salient object detection in optical remote sensing images12
A transformer guidance dual-stream network (TGDNet) is proposed for SOD in optical RSIs inspired by the long-range dependencies of transformer to extract multi-scale features by global receptive fields and separately refine them according to the characteristics of feature hierarchies.
- A study on Subtractive Pixel Adjacency Matrix features12
A Novel Feature Selection (NFS) algorithm and an Improved Feature Selection algorithm are proposed and experimental results show that the NFS algorithm can achieve higher detection accuracy than several existing algorithms.
- Illumination-Guided progressive unsupervised domain adaptation for low-light instance segmentation11
An Illumination-Guided Progressive Unsupervised Domain Adaptation method, called IPULIS, for low-light instance segmentation by progressively exploring the alignment of features at image-, instance, and pixel-levels between normal- and low-light conditions under illumination guidance.
- Spatial-domain steganalytic feature selection based on three-way interaction information and KS test11
A spatial-domain steganalytic feature selection method based on three-way interaction information and Kolmogorov–Smirnov (KS) test that can achieve better feature selection performance is proposed.
- 11
- 10
- Blind face images deblurring with enhancement9
A generative adversarial network (GAN) is proposed, which includes a perception-inspired blurry removal generator and a discriminator that reconstructs the latent deblurred image by a U-net based network that contains an enhancement module.
- Robust principal component analysis via truncated nuclear norm minimization8
The idea of truncated nuclear norm regularization (TNNR) is extended to the robust PCA and considered instead of nuclear norm minimization (NNM), which is much more robust in terms of the rank of the reconstructed matrix and the sparsity of the error.
- 8
- 7
- RGB-D salient object detection via convolutional capsule network based on feature extraction and integration7
This paper proposes a novel convolutional capsule network based on feature extraction and integration for dealing with the object-part relationship, with less computation demand and results show that the proposed method outperforms 23 state-of-the-art algorithms.
- 7
- 7
- 6
- ELUNet: an efficient and lightweight U-shape network for real-time semantic segmentation6
This work proposes an efficient and lightweight U-shape network (ELUNet) for real-time semantic segmentation and proposes an upsample feature fusion module to capture global contextual information, significantly improving the ability of the network to extract spatial information.
- 6
- Illumination-based adaptive saliency detection network through fusion of multi-source features6
The proposed ‘illumination based multi-source fused salient object detection network’ (IAN-MF-SOD network) guides features from two sources to fuse adaptively and intelligently, so that the method can enhance both of their advantages.
- Hierarchical feature concatenation-based kernel sparse representations for image categorization6
This paper proposes to find sparse representation based on feature concatenation using hierarchical kernel orthogonal matching pursuit (HKOMP) and shows that the proposed scheme outperforms many kernel learning based and other competitive image categorization algorithms.
- 6
- 5
- PaIaNet: position-aware and identification-aware network for low-light salient object detection5
A position-aware and identification-aware network (PaIaNet) for SOD, inspired by the hunting mechanism of predators in biology, that performs favorably from comparisons of qualitative and quantitative evaluations against other state-of-the-art methods in SOD of low-light images, and even achieves competitive performance when extended to normal-light scenes.
- A multi-source feature extraction network for salient object detection5
A novel multi-source feature extraction network (MFEN) is proposed, which is capable of integrating salient features, boundary features and global feature, simultaneously, simultaneously and outperforms recent 18 SOD methods.
- 5
- Blind text images deblurring based on a generative adversarial network5
The authors recognise the text deblurring problem as a semantic generation task, which can be achieved by a generative adversarial network, and propose a structural loss function and a detailed loss function to regularise the recovery of text images.
- 5
- Image compressed sensing based on non-convex low-rank approximation5
The experimental results show that the proposed non-convex low-rank regularization namely weighted Schatten p-norm minimization (WSNM) outperforms the state-of-the-art CS recovery algorithms not only in PSNR index, but also in local structure preservation.
- 4
- Jdlmask: joint defogging learning with boundary refinement for foggy scene instance segmentation4
A joint defogging learning with boundary refinement (JDLMask) framework that enables the joint learning of defogging and instance segmentation in foggy environments, and proposes a multi-scale feature fusion mask head, based on the encoder–decoder architecture, which enhances the model’s feature representation capacity.
- EGBNet: a real-time edge-guided bilateral network for nighttime semantic segmentation4
A self-adaptive feature fusion module is proposed for the bilateral segmentation network to enhance the feature representation and generalization ability by fully using multi-scale feature maps and uses the knowledge distillation strategy to improve the segmentation performance.
- Evaluation of Physical Electrical Experiment Operation Process Based on YOLOv5 and ResNeXt Cascade Networks4
A method to infer the experimental operation process by detecting the state changes of the experimental equipment is proposed, and the evaluation grade of automatic scoring is consistent with the teacher’s evaluation grade, which can reflect the students’ experimental operation level.
- K-means clustering algorithm based on improved flower pollination algorithm4
Compared with k-means and FPA, IFPA-KM improves the accuracy of clustering and has better stability, and the results show that IFPA is better than FPA in convergence speed and search optimization accuracy.
- Exposing region duplication through local geometrical color invariant features4
This work proposes a CMFD method using local geometrical color invariant features to detect duplicated regions with various transforms and poor structure, and evaluates the detection performance and computational complexity of the proposed method.
- Low-complexity distributed multi-view video coding for wireless video sensor networks based on compressive sensing theory4
The proposed approach can explore the sparsity of video images, allow for low complexity encoder and the exploitation of inter-camera correlation without communications among cameras, and outperforms the baseline compressive sensing-based scheme of intra frame coding by 3–5 dB.
- 4
- Semantic segmentation in adverse scenes with fewer labeled images3
This study proposes a novel two-step training pipeline that separately handles the training of labeled and unlabeled images to prevent overfitting, and develops a class adaptive threshold with label perception (CATLP) to generate accurate pseudo-labels.
- 3
- A Novel Edge-Inspired Depth Quality Evaluation Network for RGB-D Salient Object Detection3
An edge-inspired depth quality evaluation network, which evaluates the quality of the depth images based on the edge information, and outperforms previous high-performance RGB-D salient object detection.
- 3
- 2
- 2
- 2
- 2
- 2
- Weakly-supervised Salient Object Detection with Label Decoupling Siamese Network2
A label decoupling siamese network (LDSN) is introduced, which implements weakly-supervised salient object detection by learning from scribble labels, and is compared with several pixel-level label supervised methods.
- 2
- Efficient recovery of group-sparse signals with truncated and reweighted l2, 1-regularization2
In order to recover groupsparse signals with a better sparsity-measurement tradeoff, the truncated l 2,1 -norm regularization and reweighted l 1,2 - norm regularization are proposed for the recovery of group-sparse signals based on the iterative support detection.
- An Overview on Passive Image Forensics Technology for Automatic Computer Forgery2
The authors provide a comprehensive overview of the state-of-the-art passive detection methods for automatic computer forgery.
- 1
- FANet: A frequency domain information aware network for no-reference image quality assessment1
In FANet, a Frequency Domain Information Aware Network (FANet) is proposed that leverages frequency domain features to capture complementary information across domains to effectively learn the relationship between spatial and frequency representations.
- 1
- 1
- 1
- Edge-guided dynamic feature fusion network for object detection under foggy conditions1
This work presents an edge-guided dynamic feature fusion network (EDFFNet), which formulates the edge head as a guide to the localization task, and demonstrates that it makes the model pay attention to the edge of object instances and improves the generalization and localization ability of the network.
- 1
- MS-DRDNet: Optimization-Inspired Deep Compressive Sensing Network for MRI1
A novel deep CS network—-Multi-scale Deep Residual Dense Network (MS-DRDNet), by combining the traditional model-based CS methods and data-driven deep learning methods in MRI image reconstruction accuracy is proposed.
- 1
- An Analysis and Application of Fast Nonnegative Orthogonal Matching Pursuit for Image Categorization in Deep Networks1
Fast nonnegative OMP (FNOMP) is studied as an efficient encoder which can be accelerated by the implementation of factorization and iterations of coefficients in deep networks for full-size image categorization task and significantly improves the classification accuracy compared to OMP based algorithm.
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- LMF-Net: a Mamba-based enhancement network for low-light object detection–
This work introduces a frequency channel attention mechanism to better utilize multi-spectral features in low-light images, and proposes a detection-oriented enhancement network that jointly optimizes both tasks, Low-light Mamba Frequency Network (LMF-Net).
- Frequency-based dual attention network for nighttime semantic segmentation–
A frequency-based dual attention network (FDANet) is proposed to address the problem of targets hidden in the background caused by uneven exposure and low contrast that are difficult to distinguish and to deeply explore hidden features from frequency information.
- –
- A survey: research on firework algorithms–
This article focuses on summarizing the current research progress of the firework algorithm and its improved algorithm, as well as prospects for its future research directions.
- –
- MB-DAMPNet: a novel multi-branch denoising-based approximate message passing algorithm via deep neural network for image reconstruction–
A novel multi-branch denoising-based approximate message passing algorithm via deep neural network, dubbed MB-DAMPNet, which significantly outperforms other state-of-the-art methods in image reconstruction accuracy.
- –
- –
- –
- –
- Combined soft-threshold wavelet de-noising with MRA on the detection of turbulent coherent structure–
- –
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.