Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks132 from public data
- 2,961
- Kindling the Darkness1,856
This work builds a simple yet effective network for Kindling the Darkness (denoted as KinD), which, inspired by Retinex theory, decomposes images into two components that are robust against severe visual defects, and user-friendly to arbitrarily adjust light levels.
- Beyond Brightening Low-light Images1,056
This work builds a simple yet effective network, which, inspired by Retinex theory, decomposes images into two components, followed a divide-and-conquer principle, and is trained with paired images shot under different exposure conditions.
- 951
- FusionDN: A Unified Densely Connected Network for Image Fusion658
A new unsupervised and unified densely connected network for different types of image fusion tasks, termed as FusionDN, which obtains a single model applicable to multiple fusion tasks by applying elastic weight consolidation to avoid forgetting what has been learned from previous tasks when training multiple tasks sequentially.
- Rethinking the Image Fusion: A Fast Unified Image Fusion Network based on Proportional Maintenance of Gradient and Intensity641
This paper unify the image fusion problem into the texture and intensity proportional maintenance problem of the source images, and defines a uniform form of loss function based on these two kinds of information, which can adapt to different fusion tasks.
- Locality Preserving Matching601
The authors' method can accomplish the mismatch removal from thousands of putative correspondences in only a few milliseconds, and achieves better or favorably competitive performance in accuracy while intensively cutting time cost by more than two orders of magnitude.
- A review of multimodal image matching: Methods and applications532
This survey provides a comprehensive review of multimodal image matching methods from handcrafted to deep methods for each research field according to their imaging nature, including medical, remote sensing and computer vision.
- Pan-GAN: An unsupervised pan-sharpening method for remote sensing image fusion471
This work proposes a novel unsupervised framework for pan-sharpening based on a generative adversarial network, termed as Pan-GAN, which does not rely on the so-called ground-truth during network training and has shown promising performance in terms of qualitative visual effects and quantitative evaluation metrics.
- Infrared and visible image fusion via detail preserving adversarial learning456
This paper proposes an end-to-end model for infrared and visible image fusion based on detail preserving adversarial learning that is able to overcome the limitations of the manual and complicated design of activity-level measurement and fusion rules in traditional fusion methods.
- 380
- Single Image Deraining: A Comprehensive Benchmark Analysis371
A comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images, and provides a rich variety of criteria for dehazing algorithm evaluation.
- 317
- 283
- 281
- Low-light Image Enhancement via Breaking Down the Darkness272
A novel framework inspired by the divide-and-rule principle is presented, greatly alleviating the degradation entanglement of images captured in low-light environments by converting an image from the RGB colorspace into a luminance-chrominance one.
- A feature selection algorithm of decision tree based on feature weight262
Experimental results show that FWDT the authors' proposed method performs better for the measures of accuracy, recall and F1-score and it can reduce the required time in constructing the decision tree.
- 236
- 207
- 204
- 185
- Multi-view subspace clustering with intactness-aware similarity181
A novel multi-view subspace clustering model that attempts to form an informative intactness-aware similarity based on the intact space learning technique is proposed and its superior performance over other state-of-the-art alternatives is revealed.
- 179
- LIME135
This paper proposes a very simple and effective method, named as LIME, to enhance low-light images, where the illumination of each pixel is first estimated individually by finding the maximum value in R, G and B channels.
- 126
- 122
- Bilateral attention decoder: A lightweight decoder for real-time semantic segmentation101
A lightweight bilateral attention decoder for real-time semantic segmentation that consists of two blocks and can fuse different level feature maps via two steps, i.e., information refinement and information fusion is proposed.
- Robust subspace segmentation by simultaneously learning data representations and their affinity matrix92
A novel method to simultaneously learn the representations of data and the affinity matrix of representation in a unified optimization framework is proposed and its superior performance over the state-of-the-art alternatives is demonstrated.
- 89
- Deep Multi-instance Learning with Dynamic Pooling87
The proposed dynamic pooling based multi-instance neural network is an adaptive scheme for both key instance selection and modeling the contextual information among instances in a bag and can interpret instance-to-bag relationship.
- NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results85
This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field.
- 83
- 82
- Single image rain removal via a deep decomposition–composition network80
A novel multi-task leaning architecture in an end-to-end manner to reduce the mapping range from input to output and boost the performance, and is applicable to other layer decomposition tasks like dust removal.
- 71
- 69
- 68
- 67
- 64
- Robust Unpaired Image Dehazing via Density and Depth Decomposition63
A robust self-augmented image dehazing framework for haze generation and removal that can be robustly trained on, not only synthetic indoor datasets, but also real outdoor scenes with remarkable improvement on the real-world image dehazing.
- Generative Landmark Guided Face Inpainting60
An effective deep learning based strategy to deal with inpaint face images in the wild, which comprises of a facial landmark predicting subnet and an image inpainting subnet, and assumes that high-quality completed faces together with their landmarks can be utilized as augmented data to further improve the performance of (any) landmark predictor.
- Robust Foreground Detection Using Smoothness and Arbitrariness Constraints59
This paper forms the problem in a unified framework from a probabilistic perspective, and design an effective algorithm to seek the optimal solution, and Experimental results on both synthetic and real data demonstrate the clear advantages of the method compared to the state of the art alternatives.
- 49
- Good match exploration using triangle constraint48
This paper presents a novel method for addressing the problem of finding more good feature pairs between images, which is one of the most fundamental tasks in computer vision and pattern recognition and significantly improves both the number of correct matches and the matching score.
- 45
- Ensemble Soft-Margin Softmax Loss for Image Classification40
A soft-margin softmax function is introduced to explicitly encourage the discrmination between different classes of CNN models for image classification, and a novel loss, named as Ensemble Soft-Margin Softmax (EM-Softmax), is designed.
- MIFT: A Mirror Reflection Invariant Feature Descriptor38
The structure of MIFT is analyzed and it is shown how MIFT outperforms SIFT in the context of mirror reflection while performs as well as SIFT when there is no mirror reflection.
- Reasoning of Large Language Models over Knowledge Graphs with Super-Relations32
The ReKnoS framework is proposed, which aims to Reason over Knowledge Graphs with Super-Relations, and its key advantages include the inclusion of multiple relation paths through super-relations, enhanced forward and backward reasoning capabilities, and increased efficiency in querying LLMs.
- DAAL: Deep activation-based attribute learning for action recognition in depth videos32
Experiments on several public datasets for action recognition demonstrate that the deep activations achieve the state-of-the-art discriminative performance as feature vectors and the attribute learner can produce generic attributes, and thus obtains decent performance on zero-shot action recognition.
- 31
- 31
- 31
- 28
- Multi-scale Spatial Representation Learning via Recursive Hermite Polynomial Networks26
Recursive Hermite Polynomial Networks are proposed, which recursively constructs sub-scale representations to avoid the artifacts caused by naively applying the dilation convolution, and reveal its superiority over state-of-the-art alternatives on a variety of image recognition tasks.
- Practical Edge Detection via Robust Collaborative Learning25
The principle behind the PEdger is that, the information learned from different training moments and heterogeneous (recurrent and non recurrent in this work) architectures, can be assembled to explore robust knowledge against noisy annotations, even without the help of pre-training on extra data.
- Deep Flexible Structure Preserving Image Smoothing24
This paper develops a deep network in the light of flexibility in controlling, structure preservation in smoothing, and efficiency, and builds a UNet-in-UNet structure with carefully designed loss terms to seek visually pleasant smoothing results without paired data involved for training.
- 23
- 23
- Ntire 2025 Image Shadow Removal Challenge Report22
This work examines the findings of the NTIRE 2025 Shadow Removal Challenge, with 17 teams successfully submitting their solutions during the final evaluation phase, and one focusing on reconstruction fidelity and the other on visual perception through a user study.
- 22
- Bag similarity network for deep multi-instance learning22
This study proposes a novel neural network for MIL that emphasizes modeling the affinities between bags, and achieves a more effective bag representation than previous methods.
- 22
- Regional Attention For Shadow Removal21
A Regional Attention Shadow Removal Model (RASM), which leverages non-shadow areas to assist in restoring shadow ones and allows each shadow region to interact more rationally with its surrounding non-shadow areas, for seeking the regional contextual correlation between shadow and non-shadow areas.
- 21
- 19
- Exclusivity Regularized Machine: A New Ensemble SVM Classifier18
This paper defines a novel measurement of diversity, termed as exclusivity, and proposes an ensemble SVM classifier, namely Exclusivity Regularized Machine (ExRM), to jointly suppress the training error of ensemble and enhance the diversity between bases.
- 17
- 17
- 17
- 16
- 16
- 16
- Motion matters16
This paper introduces a novel framework for compressing surveillance videos that significantly reduces the size of videos while gains much higher PSNR compared to the state of the art codecs.
- Duplication Localization and Segmentation16
This paper proposes a novel method to automatically detect and segment the duplicate regions within an image using the modified Efficient Subwindow Search algorithm, and generalizes duplication from traditional pure copy-paste to more general cases, which involves planar homography transformation.
- 15
- 15
- 15
- 15
- A Stochastic Model for Detecting Overlapping and Hierarchical Community Structure15
This work proposes a generative model that employs a nonnegative matrix factorization formulization with a l2,1 norm regularization term, balanced by a resolution parameter, and derives the multiplicative update rule to learn the model parameters, and offers the proof of its correctness.
- MIFT: A framework for feature descriptors to be mirror reflection invariant15
This paper presents a framework, mirror-reflection invariant feature transform (MIFT), for improving their degenerated performance due to mirror reflections, and demonstrates the robust performance of MIFT.
- 14
- 14
- 14
- Semi-supervised Camouflaged Object Detection from Noisy Data13
This paper develops the first semi-supervised camouflaged object detection framework, which requires merely a small amount of samples even having noisy/incorrect annotations, and introduces an innovative pixel-level loss re-weighting technique to reduce possible negative impacts from imperfect labels, through a window-based voting strategy.
- 12
- 11
- 10
- Online robust low rank matrix recovery10
An online algorithm to solve the problem of low rank matrix completion and outlier support is robustly estimated from a perspective of mixture model and shows its superior performance over the state-of-the-arts.
- Image Retrieval and Ranking via Consistently Reconstructing Multi-attribute Queries10
This work discovers the correlation among attributes via expanding the query representation, and imposing the group sparsity on representations to reduce the disturbance of noisy data.
- A Generalized Digraph Model for Expressing Dependencies9
A task model is proposed that generalizes the digraph model and its corresponding analysis for fixed-priority scheduling with limited preemption and formally certify the analysis for that general model such that the correctness proof of a more specific analysis boils down to specifying and proving its translation into the model.
- ROUTE: Robust Outlier Estimation for Low Rank Matrix Recovery9
A method for recovering the low rank matrix with robust outlier estimation, termed as ROUTE, in a unified manner is designed to demonstrate the efficacy of the proposed method and show its superiority over other state-of-the-arts methods.
- 9
- Augmented Image Retrieval using Multi-order Object Layout with Attributes9
A novel image search method is proposed, which allows the users to indicate any number of Regions Of Interest (ROIs) within the query as well as utilize various semantic concepts and spatial relations to search images.
- 8
- 8
- 7
- Hierarchical image peeling: A flexible scale-space filtering framework6
A modern framework for disassembling an image into a family of derived signals from a scale-space perspective is designed, and a formal definition of image disassembly is offered, which converts the original complex problem into a series of two-component separation sub-problems, significantly reducing the complexity.
- Monomodal registration with adaptive parameter computing6
An adaptive parameter computing method for monomodal image registration, employ the energy functional with probability density function searching the weight parameter corresponding to the local degrees of variability in matching.
- Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs5
EvoReasoner is proposed, a temporal-aware multi-hop reasoning algorithm that performs global-local entity grounding, multi-route decomposition, and temporally grounded scoring that outperforms both prompting-based and KG-enhanced baselines on dynamic question answering.
- ShadowHack: Hacking Shadows via Luminance-Color Divide and Conquer4
To brighten shadow regions and repair the corrupted textures in the luminance space, LRNet is customized, a $U$-shaped network with a rectified attention module, to enhance information interaction and recalibrate contaminated attention maps.
- 4
- Face Inverse Rendering via Hierarchical Decoupling4
A deep learning framework to disentangle face images in the wild into their corresponding albedo, normal, and lighting components is proposed with a hierarchical subdivision strategy, which takes image pairs captured from arbitrary viewpoints as input.
- 4
- 3
- Towards High-Fidelity Face Normal Estimation3
A coarse-to-fine framework to estimate face normal from an in-the-wild image with only a coarse exemplar reference is proposed, which can largely alleviate the negative impact caused by lacking training data, and focus on exploring the high-fidelity normal contained in natural images.
- 3
- Unsupervised Exemplar-Domain Aware Image-to-Image Translation3
This work designs a novel deep translator, namely exemplar-domain aware image-to-image translator (EDIT for short), which can flexibly and effectively work on multiple domains and arbitrary exemplars in a unified neat model.
- 3
- 3
- A new encryption scheme for surveillance videos3
Experimental results demonstrate that the proposed method is robust to known cryptanalytic attacks, and enhances the overall security due to the foreground and background separation, and is faster than competing methods, which do not conduct foreground extraction.
- Research on Smart City Road Network Capacity Optimization Configuration Based on Deep Learning Algorithms2
Results show that the SCRO-GNN can significantly improve the prediction accuracy, especially when dealing with the highly complex urban road network structure, and the proposed optimization strategy performed well in reducing traffic congestion and improving the efficiency of road use.
- Urban rail transit passenger flow forecasting based on prophet-GRU combined model2
A passenger flow forecasting method based on prophet-GRU combined model that shows that the weighted accuracy of passenger flow prediction reaches 96.13% for 159 stations and the root mean square error of the combined Prophet- GRU model is at least 49.69% lower than the ARIMA, GRU, and Prophet models.
- TSTTC: A Large-Scale Dataset for Time-to-Contact Estimation in Driving Scenarios2
This work presents a large-scale object oriented TTC dataset in the driving scene for promoting the TTC estimation by a monocular camera and provides several simple yet effective TTC estimation baselines to demonstrate their effectiveness.
- 2
- 2
- A Foreground-Aware Framework for Local Face Attribute Transfer2
A novel framework for semantically meaningful local face attribute transfer is developed, which can flexibly transfer the local attribute of a face organ from the reference image to a semantically equivalent organ in the input image, while preserving the background.
- Visual data deblocking using structural layer priors2
A simple and robust method is proposed to separate these two layers, which exploits structural layer priors including the gradient sparsity of the intrinsic layer, and the independence of the gradient fields of the two layers.
- 1
- 1
- 1
- 1
- 1
- Beautifying Fisheye Images using Orientation and Shape Cues1
A computational method for enhancing the aesthetics of fisheye images by exploiting the orientation and shape cues and can correct the rotation angle between the camera coordinate and the world coordinate to make the virtual camera oriented, and complete the missing part.
- 1
- –
- –
- –
- Broadband mode-selective couplers of dual-core hollow core negative curvature fiber in the 1 μm band–
- –
- –
- –
- –
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.