Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks141 from public data
- 393
- Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising314
This paper proposes a multi-channel (MC) optimization model for real color image denoising under the weighted nuclear norm minimization (WNNM) framework, concatenate the RGB patches to make use of the channel redundancy, and introduces a weight matrix to balance the data fidelity of the three channels in consideration of their different noise statistics.
- A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising286
This paper develops a trilateral weighted sparse coding (TWSC) scheme for robust real-world image denoising and introduces three weight matrices into the data and regularization terms of the sparse coding framework to characterize the statistics of realistic noise and image priors.
- Deep Hough Transform for Semantic Line Detection248
This paper incorporates the classical Hough transform technique into deeply learned representations and proposes a one-shot end-to-end learning framework for line detection by parameterizing lines with slopes and biases, which transforms the problem of detecting semantic lines in the spatial domain into spotting individual points in the parametric domain.
- RANet: Ranking Attention Network for Fast Video Object Segmentation241
This paper proposes a novel ranking attention module, which automatically ranks and selects these maps for fine-grained VOS performance, and develops a real-time yet very accurate Ranking Attention Network (RANet) for VOS.
- Learning to Learn with Variational Information Bottleneck for Domain Generalization206
A probabilistic meta-learning model for domain generalization is introduced, in which classifier parameters shared across domains are modeled as distributions, which enables better handling of prediction uncertainty on unseen domains.
- MobileSal: Extremely Efficient RGB-D Salient Object Detection175
This article proposes an implicit depth restoration (IDR) technique to strengthen the mobile networks’ feature representation capability for RGB-D SOD, and proposes compact pyramid refinement (CPR) for efficient multi-level feature aggregation to derive salient objects with clear boundaries.
- 170
- 154
- 154
- Sparse, collaborative, or nonnegative representation: Which helps pattern classification?144
This paper investigates the use of nonnegative representation (NR) for pattern classification, which is largely ignored by previous work and reveals that NR can boost the representation power of homogeneous samples while limiting the representationPower of heterogeneous samples, making the representation sparse and discriminative simultaneously and thus providing a more effective solution to representation based classification than SR/CR.
- External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising142
This work proposes to exploit the information in both external data and the given noisy image, and develop an external prior guided internal prior learning method for real-world noisy image denoising.
- Gradient-Induced Co-Saliency Detection135
A gradient-induced co-saliency detection (GICD) method that first abstracts a consensus representation for the grouped images in the embedding space; then, by comparing the single image with consensus representation, utilizes the feedback gradient information to induce more attention to the discriminative co- salient features.
- Temporal Modulation Network for Controllable Space-Time Video Super-Resolution130
A Temporal Modulation Network (TMNet) to interpolate arbitrary intermediate frame(s) with accurate high-resolution reconstruction and demonstrates that the TMNet outperforms previous STVSR methods.
- 129
- 108
- Conditional Variational Image Deraining91
A Conditional Variational Image Deraining (CVID) network is proposed for better deraining performance, leveraging the exclusive generative ability of Conditionalvariational Auto-Encoder on providing diverse predictions for the rainy image.
- 88
- 88
- ICNet: Intra-saliency Correlation Network for Co-Saliency Detection84
An Intra-saliency Correlation Network (ICNet) is proposed to extract intra-saliency cues from the single image saliency maps (SISMs) predicted by any off-the-shelf SOD method, and obtain inter-saliency cues by correlation techniques.
- 76
- A Simple Yet Effective Network Based on Vision Transformer for Camouflaged Object and Salient Object Detection73
A simple yet effective network (SENet) based on vision Transformer, employing a simple design of an asymmetric ViT-based encoder-decoder structure that yield competitive results on both tasks, exhibiting greater versatility than meticulously crafted ones is proposed.
- Learning deconvolutional deep neural network for high resolution medical image reconstruction71
A super resolution algorithm (SR-DCNN) is proposed for medical images that is based on a neural network and employs a deconvolution operation to effectively establish an end-to-end mapping between the low and high resolution images.
- 68
- 63
- Reweighted sparse subspace clustering62
Though the proposed RSSC achieves the better performance than other algorithms, the results suggest that novel algorithms that focus on segmentation of non-rigid motions are still in need.
- 60
- Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution54
The Semi-Cycled Generative Adversarial Networks (SCGAN) is able to alleviate the adverse effects of the domain gap between the real-world LR face images and the synthetic LR ones, and to achieve accurate and robust face SR performance by the shared restoration branch regularized by both the forward and backward cycle-consistent learning processes.
- Simplified object-based deep neural network for very high resolution remote sensing image classification43
A simplified object-based deep neural network (SO-DNN) is proposed for very high resolution remote sensing image classification that relies on fewer models and easier-to-obtain samples than traditional methods, and its stable performance makes SO- DNN more valuable for practical applications.
- 42
- TSTSS: A two-stage training subset selection framework for cross version defect prediction41
A novel method, called Two-Stage Training Subset Selection (TSTSS), which leverages a dissimilarity-based sparse subset selection method to further refine the selected module subset, which enables the selected modules to well represent the modules of the current version.
- 40
- 39
- NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results35
The 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results establishes a new benchmark for stereo image SR.
- Displaying status of recipiency through reactive tokens in Mandarin task-oriented interaction34
This model suggests that recipients employ reactive tokens as a negotiating resource to collaboratively achieve, in the emerging interaction, either disengagement or involvement on this continuum of displayed recipiency.
- 28
- Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis27
A novel medical slice synthesis to increase the inter-slice resolution by introducing the incremental cross-view mutual distillation strategy to accomplish this task in the self-supervised learning manner and demonstrating the effectiveness of the proposed approach.
- 26
- An object-based and heterogeneous segment filter convolutional neural network for high-resolution remote sensing image classification26
Experimental results show that the OHSF-CNN not only can take full advantage of the recognition capabilities of deep learning methods but also can effectively avoid the jagged errors along land cover boundaries and the expansion/shrinkage of land cover areas originating from traditional CNN structures.
- 23
- 23
- An End-to-End and Localized Post-Processing Method for Correcting High-Resolution Remote Sensing Classification Result Images22
An end-to-end and localized post-processing method (ELP) to correct the result images of high-resolution remote sensing image classification methods and improves classification accuracy.
- Dynamic Message Propagation Network for RGB-D and Video Salient Object Detection21
This article integrates DMP into a Siamese-based network to process the RGB image and depth map separately and design a multi-level feature fusion module to explore cross-level information between refined RGB and depth features.
- 21
- 20
- Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks19
A Mask Guided Acceleration (MGA) scheme to reduce the computational costs of existing SR networks while maintaining their SR capability and experiments demonstrate that the MGA scheme reduces the FLOPs of five popular SR networks by 10% ∼ 48% with comparable or even better SR performance.
- 17
- 17
- A Study of Implicit Ranking Unfairness in Large Language Models16
The need for the community to identify and mitigate the implicit unfairness in Large Language Models, aiming to avert the potential deterioration in the reinforced human-LLMs ecosystem deterioration, is emphasized.
- Application of a Brain–Computer Interface System with Visual and Motor Feedback in Limb and Brain Functional Rehabilitation after Stroke: Case Report15
The BCI system with visual and motor feedback is applicable in active rehabilitation training of stroke patients with hemiplegia, and the pilot results show potential multidimensional benefits after a short course of treatment.
- 14
- MetaKernel: Learning Variational Random Features With Limited Labels14
This paper proposes meta-learning kernels with random Fourier features for few-shot learning by leveraging the shared knowledge provided by related tasks in a meta-learning setting and treats the random feature basis as the latent variable, which is estimated by variational inference.
- Adaptive video-blocking artifact removal in discrete Hadamard transform domain13
A novel postprocessing algorithm for blocking artifact removal in the discrete Hadamard transform (DHT) domain, which does not require prior knowledge of quantization parameters and features low computational complexity is presented.
- Radiation reduction for interventional radiology imaging: a video frame interpolation solution11
The deep learning model, which interpolates low-frame-rate IR sequences, has shown the capability to produce high-quality IR images and exhibits potential for reducing the frame rate during IR image acquisition, consequently mitigating radiation exposure.
- 10
- 10
- [A Novel Spatial-Spectral Sparse Representation for Hyperspectral Image Classification Based on Neighborhood Segmentation].10
A spatial-spectral joint sparse representation classification algorithm based on neighborhood segmentation is presented, which concludes that neighborhood segmentations is necessary for joint sparse Representation classification.
- 9
- 9
- 8
- Grapheme-to-phoneme conversion for Chinese text-to-speech8
A complete G2P framework is presented, which includes a two-stage statistical word segmentation module, a hidden Markov model (HMM) based part-of-speech (POS) tagging module and a word-to-pinyin conversion module, which involves augmented word grapheme is augmented by its POS tag in an effort to resolve the pronunciation disambiguation in G1P.
- 7
- A Fuzzy Spatial Region Extraction Model for Object’s Vague Location Description from Observer Perspective7
A Fuzzy Spatial Region Extraction Model for Object’s Vague Location Description from Observer Perspective (FSREM-OP) is proposed, capable of extracting the spatial information and presenting location descriptions in the GIS, despite the vagueness and subjective spatial relation expressions in the descriptions.
- 7
- 7
- 6
- Group-of-pictures-based unequal error protection for scalable video coding extension of H.264/AVC6
Experimental results demonstrate the proposed UEP scheme provides significant error resilience and a simple heuristic algorithm is proposed to quickly derive the protection pattern.
- 5
- 5
- MARformer: An Efficient Metal Artifact Reduction Transformer for Dental CBCT Images4
The proposed MAR Transformer (MARformer) reduces computation complexity in the multihead self-attention by a new Dimension-Reduced Self-Attention (DRSA) module, based on that the CBCT images have globally similar structure.
- Virtual Reality-Based Fuzzy Spatial Relation Knowledge Extraction Method for Observer-Centered Vague Location Descriptions4
Experiments show that, on the basis of interactive scenes provided through VR, VR-FSRKE can efficiently extract spatial relation knowledge from many individuals and is not restricted by requirements of a certain place or time; furthermore, the knowledge obtained by VR- FSRKE is close to theknowledge obtained from a real scene.
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- Finger mouse system based on computer vision in complex backgrounds3
A human-computer interaction system that emulates the dragging and selecting functions of a mouse by recognizing bare hands, hence the control style is simple and intuitive and has advantages of good real-time performance, easy integration and energy conservation.
- 3
- 3
- 2
- ACformer: A unified transformer for arbitrary-frame image exposure correction2
An Arbitrary-Frame Exposure Correction Transformer (ACformer) is developed as an integrated model to tackle the AF-EC task, and achieves mutually boosted performance on both the SEC and MEF tasks.
- PSAIP: Prior Structure-Assisted Identity-Preserving Network for Face Animation2
A Prior Structure-Assisted Identity-Preserving (PSAIP) network for face animation is proposed, which introduces the additional priors of portrait segmentation images and face landmarks, which provide rich face geometric information while masking background interference to generate more realistic face images.
- 2
- 2
- 2
- Information Extraction from High-Resolution Remote Sensing Images Based on Multi-Scale Segmentation and Case-Based Reasoning2
A new method for extracting high-resolution remote sensing image information by fully using the image and nonimage features of the case object is proposed, and feature selection and weight learning are used to construct a multi-level and multi-layer case library model of surface cover classification reasoning.
- A Fully Automatic AI-based CT Image Analysis System for Accurate Detection, Diagnosis, and Quantitative Severity Evaluation of Pulmonary Tuberculosis2
This end-to-end AI system based on chest CT can achieve human-level diagnostic performance, and holds great potential for early management and medical resource optimization of patients with pulmonary TB in clinical practice.
- 2
- Prior Consistent CNN with Multi-Task Learning for Colon Image Classification2
This model is based on the clinical-pathological diagnostic criteria of adenocarcinoma, which provides more ideas on how to make deep learning methods in the field of digital pathology more interpretable.
- 2
- 2
- 2
- Multimodal learning audio-visual detection for obtaining object-level sound sources in Japanese-language teaching room1
This study proposes a novel deep learning-based approach for audio-visual detection (AVD) in Japanese-language teaching rooms, combining audio and visual information to detect sound sources at the object level.
- 1
- 1
- Parameter Optimization of the SVM Kernel Function Based on the ACO Algorithm1
C-CACO-DE solves the problem that the continuous ACO algorithm (C-ACO) must be pretreated;olves the precision shortcomings of the C- ACO based on a grid search strategy.
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- Patch Triplet Similarity Purification for Guided Real-World Low-Dose CT Image Denoising–
A new Patch Triplet Similarity Purification (PTSP) strategy is designed to select highly similar patch (instead of image) triplets of LDCT, NDCT, and NCCT images for network training to alleviate the issue of spatial misalignment in training data.
- LHT: Statistically-Driven Oblique Decision Trees for Interpretable Classification–
The Learning Hyperplane Tree is introduced, a novel oblique decision tree model designed for expressive and interpretable classification that fundamentally distinguishes itself through a non-iterative, statistically-driven approach to constructing splitting hyperplanes.
- Tri‐Plane Dynamic Neural Radiance Fields for High‐Fidelity Talking Portrait Synthesis–
A novel tri‐plane dynamic neural radiation field (Tri‐NeRF) that employs an implicit radiation field to study the impacts of audio on facial movements is proposed and a new gated attention fusion module (GAF) is proposed to dynamically fuse features based on strong and weak correlation of cross‐modal features.
- Learning Hyperplane Tree: A Piecewise Linear and Fully Interpretable Decision-making Framework–
A novel tree-based model, Learning Hyperplane Tree (LHT), which outperforms state-of-the-art (SOTA) tree models for classification tasks on several public datasets and is highly transparent and interpretable.
- –
- –
- –
- Lightweight improved residual network for efficient inverse tone mapping–
A new Improved Residual Block (IRB) is proposed to extract and fuse multi-layer features for fine-grained HDR image reconstruction to enhance the power of popular residual block for efficient ITM.
- Optimization of Reinforcement Learning Algorithms for Addressing the Linear Function Fitting Challenge in the Electric Power Internet of Things–
This research proposes an improved reinforcement learning framework that enhances the accuracy and efficiency of the algorithm in handling large-scale, high-dimensional data by optimizing the linear function fitting process.
- –
- –
- –
- –
- Research on Experimental Teaching of Communication Majors–
To solve problems in the experiment teaching of communication majors, the authors have taken some measures from training scheme, teaching method, standards of performance and so on, which have achieved well results.
- –
- –
- –
- –
- –
- –
- Design and Analysis of Built-in Test for Torpedo Homing System–
Analysis and calculation results show that the BIT technique meets design requirements with higher falult detection rate(FDR) and several ways to reduce effectively false alarm rate (FAR) of the BIT.
- The developing trend of the Computer network management system–
This paper introduces the basic knowledge of the computer network management system and analyzes the current situation and the problems of the application to raise the development trend in the future of the system.
- ASON network strategy for the protection of relativity–
The algorithm excavated the important nodes and edges of ASON network by making use of the PageRank algorithm, giving them priority protection in order to taking advantage of the wavelength resource efficiently in the ASon network.
- –
- –
- –
- Secondly-development of Garment CAD based on AutoCAD2004、VFP–
The joint method of AutoCAD and database is introduced, which created slide library, pattern block library, accessory library and all kinds of forms in database in order to be transferred at any moment by fashion designer.
- –
- –
- –
- –
- –
- The safe config of Cisco Router–
Some common network safety control methods based on Cisco Router3661 are provided and their applications are discussed.
- The Choice in Translation–
The author argues that the choice in translation runs through the whole process of translating, and such choice is not merely a personal decision of the translator.
- –
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.