Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks152 from public data
- Convolutional Sequence to Sequence Model for Human Dynamics376
This work presents a novel approach to human motion modeling based on convolutional neural networks (CNN), which is able to capture both invariant and dynamic information of human motion, which results in more accurate predictions.
- 371
- RadixPuerariae: An overview of Its Chemistry, Pharmacology, Pharmacokinetics, and Clinical Use217
The current review is proposed to cover its traditional applications, pharmacological activities, pharmacokinetics, clinical efficacy, and potential herb–drug interactions aiming to fill in the information gaps of this herb for frontline practitioners.
- Improved key-rate bounds for practical decoy-state quantum-key-distribution systems148
A tighter bound is developed for the decoy-state method, which yields a smaller failure probability and results in a higher key rate and increases the maximum distance over which secure key exchange is possible.
- Learning Deep Gradient Descent Optimization for Image Deconvolution120
A recurrent gradient descent network (RGDN) is proposed by systematically incorporating deep neural networks into a fully parameterized gradient descent scheme and learns an implicit image prior and a universal update rule through recursive supervision.
- Matching user accounts based on user generated content across social networks86
This work first formulate the problem of user identification based on UGCs and then proposes a UGC-based user identification model, and presents the possibility of matching user accounts with high accessible online data.
- 85
- 75
- 62
- Factor Graph Neural Networks55
This work derives an efficient approximate Sum-Product loopy belief propagation inference algorithm for discrete higher-order PGMs, and neuralizes the novel message passing scheme into a Factor Graph Neural Network (FGNN) module by allowing richer representations of the message update rules, which facilitates both efficient inference and powerful end-to-end learning.
- 51
- 50
- 49
- NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results45
This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022, and the competition set-up, datasets, proposed methods and their results.
- 43
- Random Sampling SVM Based Soft Query Expansion for Image Retrieval43
The experiments show that the wrinkle generated by this method not only has the advantage of verisimilitude as a photograph, but also has the feature of natural ripple which is deeper in middle than in both sides.
- A bidirectional graph neural network for traveling salesman problems on arbitrary symmetric graphs40
A bidirectional graph neural network (BGNN) for the arbitrary symmetric TSP that learns to produce the next city to visit sequentially by imitation learning and is able to be combined with informed search to further improve performance.
- 39
- Pharmacokinetic and pharmacodynamic interaction of Danshen–Gegen extract with warfarin and aspirin38
It is indicated that co-administration of DG with warfarin/aspirin can cause significant pharmacokinetic and pharmacodynamic herb-drug interactions in rat, and danshensu were not significantly affected by aspirin.
- 37
- 36
- Applications of Zeroing Neural Networks: A Survey32
This review article explores the practical applications of ZNN across various domains in the past two decades, specifically focusing on robot manipulator path tracking, motion planning, and chaotic systems.
- 28
- Identifiable Latent Polynomial Causal Models Through the Lens of Change27
The scope of latent causal models is extended to involve nonlinear causal relationships, represented by polynomial models, and general noise distributions conforming to the exponential family, and a novel empirical estimation method is proposed, grounded in the theoretical finding, that enables learning consistent latent causal representations.
- A new swarm-SVM-based fault diagnosis approach for switched current circuit by using kurtosis and entropy as a preprocessor27
A particle swarm optimization is proposed to optimize the SVM to diagnose switched current circuits and shows that the method performs well in the part of fault diagnostic accuracy.
- 26
- 25
- 21
- Learning an Optimizer for Image Deconvolution.20
A Recurrent Gradient Descent Network (RGDN) is proposed by systematically incorporating deep neural networks into a fully parameterized gradient descent scheme and learns an implicit image prior and a universal update rule through recursive supervision.
- Advanced Sentiment Classification of Tibetan Microblogs on Smart Campuses Based on Multi-Feature Fusion20
A sentiment classification method for Tibetan microblogs based on multi-feature fusion, which demonstrated that the sentiment classification algorithm based on feature fusion improved the accuracy of microblog sentiment classification.
- CLAP: Isolating Content from Style Through Contrastive Learning with Augmented Prompts19
A causal generative perspective for multimodal data is adopted and contrastive learning with data augmentation to disentangle content features from the original representations is proposed to disentangle content features from the original representations.
- Rationally designed upconversion nanoparticles for NIR light-controlled lysosomal escape and nucleus-based photodynamic therapy19
The rationally designed UCNP/RB@mSiO2-NH2 NPs showed excellent anticancer performance in both two-dimensional and three-dimensional cell models using the “one treatment, multiple irradiations” strategy.
- 19
- 16
- 16
- Understanding human activities in videos: A joint action and interaction learning approach16
Both the features learned via deep nets and human interaction context are leveraged to encode the correlations among actions and pairwise interactions in a structured model, and all model parameters are trained via a large-margin framework.
- Potentials-Attract or Likes-Attract in Human Mate Choice in China16
The main results show that not only the relationship between individuals’ own attributes and their self-stated mate preference are more consistent with the likes-attract hypothesis, i.e., people tend to choose mates who are similar to themselves in a variety of attributes.
- Social Network Size and Subjective Well-Being: The Mediating Role of Future Time Perspective Among Community-Dwelling Retirees15
Examination of the association between social network size and SWB and the mediating role of future time perspective (FTP) among Chinese retirees confirms relevance of social networks in the SWB of retirees, and provides a new insight into the role of FTP as an explanatory mechanism.
- 12
- Grammatically Derived Factual Relation Augmented Neural Machine Translation10
A novel approach named Factual Relation Augmented (FRA) is proposed to guide the decoder in Transformer-based NMT and positive results obtained in several different translation tasks indicate the effectiveness of the proposed approach.
- Optimization of Emergency Braking Pedestrian Collision Avoidance for Autonomous Vehicle Fusing the Fuzzy Neural Network with the Genetic Algorithm10
A backpropagation (BP) feed-forward FNN-GA model for the AEB-P system based on the fuzzy neural network (FNN) and genetic algorithm (GA) theory is constructed to solve the problem that initial training parameters of the FNN model generate randomly.
- 10
- Annotating semantic tags of locations in location-based social networks10
A new location feature, called the similar user pattern (SUP), is first extracted by capturing the similarities among the different users’ check-in activities, and a multi-label semantic annotation with an extreme learning machine (ELM) is proposed, called MSA-ELM.
- Variable kernel density estimation based robust regression and its applications10
The authors build up a robust estimator based on Variable Kernel Density Estimation (VKDE), which has higher precision than two most widely used robust estimators, Random Sampling Consensus and Least Median Square.
- 10
- 10
- 10
- Structure enhanced prototypical alignment for unsupervised cross-domain node classification9
This paper proposes a novel unsupervised graph domain adaptation framework called Structure Enhanced Prototypical Alignment (SEPA), which aims to learn domain-invariant representations on non-IID (non-independent and identically distributed) data.
- 9
- Structural and Morphological Quantitative 3D Characterisation of Ammonium Nitrate Prills by X-Ray Computed Tomography9
This study presents how X-ray computed tomography (XCT), and the associated advanced data processing workflow, can be used to fully characterise the structure and morphology of AN prills, and shows that structural parameters such as volume fraction of the different phases and morphological parameters can be reliably extracted from the XCT data.
- Visual Relationship Detection with Low Rank Non-Negative Tensor Decomposition9
A novel technique of learning conditional triplet distributions in the form of their normalized low rank non-negative tensor decompositions is introduced to efficiently learn higher order discrete multimodal distributions and at the same time keep the parameter size manageable.
- 8
- Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning7
This work introduces a unified causal model specifically designed for multimodal data, and shows that multimodal contrastive representation learning excels at identifying latent coupled variables within the proposed unified model, up to linear or permutation transformations resulting from different assumptions.
- 7
- Panoramic annular image restoration algorithm by prediction based on the lens design characteristics7
- Improving waveform inversion using modified interferometric imaging condition7
A new random boundary designed to regenerate random velocity anomalies in the boundary region for each shot of each iteration is followed, which enhances the continuity of the imaging path and reduces noise interference and significantly enhances waveform inversion performance.
- Dynamic Programming Bipartite Belief Propagation For Hyper Graph Matching7
This paper formulate hyper graph matching problems as constrained MAP inference problems in graphical models as constrained MAP inference problems in graphical models, and introduces only one global correspondence vector, but several local correspondence vectors.
- 7
- 7
- Belief in Reciprocity in a Chinese Sample7
The results indicated that belief in reciprocity was a partially negative, but not neutral, reciprocity norm for Chinese people and forgiveness largely mediated the effect of belief in reciprocal belief on altruism.
- Active Learning-Based Prediction of Drug Combination Efficacy6
This study presents a computational intelligence method combining active learning and fine-grid optimization to predict the efficacy of drug combinations, focusing on dual-drug-loaded polymeric nanoparticles for cancer therapy.
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- Preoperative Analysis for Clinical Features of Unsuspected Gallbladder Cancer Based on Random Forest6
- An easy-implemented confidence filter for signal processing in the complex electromagnetic environment6
A novel easy-implemented nonlinear confidence filter to record data accurately and reliably extract in the case of the complex electromagnetic environment, which can retains the convictive signal characteristics, and eliminates the noises.
- Feature points extraction of different structure for industrial computed tomography image contour6
For the regular structures, by using a positive–negative factor, the curvature estimation method was improved, and this method was designed and verified for the actual part, and has an improved accuracy in the feature points extraction.
- Physics-informed data-driven unsteady Reynolds-averaged Navier–Stokes turbulence modeling for particle-laden jet flows5
The proposed DL–URANS model was found to provide enhanced accuracy for predicting both flow and particle quantities when compared with the baseline URANS simulation.
- Identifying Weight-Variant Latent Causal Models5
This work analysis three intrinsic properties in latent space, including transitivity, permutation and scaling, and proposes a novel method, termed Structural caUsAl Variational autoEncoder (SuaVE), which directly learns latent causal variables, together with the mapping from the latent causal variable to the observed ones.
- 5
- On the construction of systematic tEC/AUED codes5
A new approach for the construction of systematic tEC/AUED codes is presented, which improve many values of the upper bound on the redundancy of the code for t=1 and 2.
- Improving insulator fault detection with effective-YOLOv7 network4
An improved YOLOv7 transmission line insulator defect recognition algorithm has been introduced, and the SiLU activation function has been replaced with meta-ACON to enhance the adaptive feature capability of the YOLOv7 network.
- Research on Prediction Model of Fracture Width in Loss Formation Based on Artificial Neural Network4
The established model of fracture width based on artificial neural network had high accuracy, which can provide a basis for early and accurate prediction of well loss risk on site and for guiding optimization of engineering parameters to prevent well loss.
- Hard Real Time and Mixed Time Criticality on Off-The-Shelf Embedded Multi-Cores4
A simple timing isolation protocol allowing computational tasks to communicate with hard real-time ones is proposed, designed to enable full system certification at the highest safety standards, such as SIL 4 in IEC 61508 or DAL A in DO-178B.
- Controlling knowledge-based image segmentation using an iterative spacial data structure construction algorithm4
A control algorithm for knowledge-based segmentation of multidimensional image data based on the iterative expansion of spatial data structures provides a controlled environment during segmentation for accessing and manipulating image data at different spatial resolution scales.
- 3
- Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation3
It is shown that although (completely) identifying the proposed latent causal model is challenging, the latent content variable can be identified up to scaling by using its dependence with labels from source domains, together with the identifiability conditions of nonlinear ICA.
- Application of Image Processing and Identification Technology for Digital Archive Information Management3
This paper explores the application of image processing and identification technology for digital archive information management, trying to provide convenient and swift services to archive mangers and archive information requestors, and to strengthen the standardized management of archive information.
- 3
- 3
- 3
- 3
- 3
- 3
- Construction and validation of a risk prediction model for oral frailty in rural hypertensive patients2
The oral frailty risk prediction model constructed based on these influencing factors has high predictive and discriminative power and can be used as a screening tool for the risk of oral frailty in rural older adults hypertensive patients.
- State Analysis of Grouped Smart Meters Driven by Interpretable Random Forest2
This study proposes a novel method for analyzing the status of smart meter groups using an interpretable random forest model that incorporates an expert-knowledge-guided grouping assessment strategy, develops a multi-source heterogeneous feature set with strong correlations to meter status, and enhances the random forest model with the SHAP (SHapley Additive exPlanations) interpretability framework.
- A three-dimensional advancing front technique to generate grids based on the neural networks2
This paper introduces two neural networks trained on the backpropagation (BP) algorithms, Line-ANN and Plane-ANN, specifically designed for integration with AFT, and proposes preliminary solutions to enhance algorithm robustness while reducing intersection judgments.
- 2
- 2
- 2
- Design and Implementation of Blind Source Separation Based on BP Neural Network in Space-Based AIS2
A method that combines the problem of blind source separation with BP neural network is proposed, using the generated suitable data set to train the neural network, thereby automatically generating a traditional blind signal separation algorithm with a more stable separation effect.
- 2
- The Indoor Localization Algorithm for Combination of Signal Strength and Anti-disturbance2
An anti-interference indoor localization algorithm that improves the location accuracy and has a certain anti-disturbance ability is proposed in this paper.
- Solving Constrained Combinatorial Optimisation Problems via MAP Inference without High-Order Penalties2
This work proposes an approach which is able to solve constrained combinatorial problems using belief propagation without increasing the order, and shows several situations in which this approach outperforms commercial solvers like CPLEX and others designed for specific constrained MAP inference problems.
- 2
- 2
- 2
- The Application of the Snake Model in Carcinoma Cell Image Segment2
The novel cell nucleus segmentation method has been tested on a number of cell images obtained from esophageal smear slide and the results are encouraging, showing that the presented method performs well on both well-separated nuclei and some overlapped nuclei.
- 1
- 1
- 1
- A Video Coding Method Based on Neural Network for CLIC20241
This paper presents a video coding scheme that combines traditional optimization methods with deep learning methods based on the Enhanced Compression Model (ECM), and achieves remarkable higher compression quality than the conventional ECM 3.0 in terms of PSNR and subjective evaluation.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- An Iris Recognition Algorithm of Multiple Features Extraction and Fusion1
In this paper, an iris recognition algorithm of multiple features extraction and fusion was proposed, which was different from the classical irIS recognition algorithm that focused on a single texture feature.
- Developing Analytical Inspection Criteria for Health IT Personnel with Minimum Training in Cognitive Ergonomics: A Practical Solution to EHR Improving EHR Usability.1
A preliminary study of a metric for cognitive transparency and an exploratory experiment testing its validity in predicting the effectiveness of action-effect mapping found high sensitivity and specificity of the metric and higher response accuracy within a shorter time for users to determine action- effect mappings in transparent user interface controls.
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- InvariantStock: Learning Invariant Features for Mastering the Shifting Market–
This study presents InvariantStock, a designed learning framework comprising two key modules: an environment-aware prediction module and an environment-agnostic module that can learn invariant features across different environments in a straightforward manner, thereby enhancing robustness against distribution shifts.
- –
- Uncanny Valley Game in Virtual Environments–
The article will be depicting the process of researching the Uncanny Valley theory's demonstration in the virtual environment, which can show that the Uncannable Valley theory might suit more scales than the authors think.
- –
- –
- –
- –
- An Improved Approximation Algorithm for the Prize-Collecting Red-Blue Median Problem–
A layered structure of the swap pairs is constructed, which yields a \((9+\epsilon )\)-approximation for the prize-collecting red-blue median problem, where the noisy data can be removed by paying a penalty cost.
- Kernel Methods for Graph-structured Data Analysis–
This dissertation focuses on three important topics in graph-structured data analysis: graph comparison, graph embeddings, and graph matching, and proposes effective algorithms by making use of kernel functions and the corresponding reproducing kernel Hilbert spaces, which significantly outperform state-of-the-art approaches in both accuracy and computational efficiency.
- –
- –
- –
- –
- –
- –
- Spoken Term Detection Based on Improved Index Structure–
This paper presents two algorithm: the first one called unconstraint word graph expansion (UWGE) and the other called dynamic position specific posterior lattice(D-PSPL), to eliminate the N-gram language model state limitation of lattice and reconstruct lattice to unconstrained word graph.
- Generalized Kernel Density Estimation Based Robust Estimator and Its Application–
Compared to ASKC, pbM and other Kernel Density Estimation based robust estimators which do not have locality, GKDE has higher resolution for inliers, and experiments show that it has higher precision than traditional robust estimator such as RANSAC, LMeds.
- Smear radiometric correction algorithm in star images based on kernel density estimation–
Experimental results indicate that the algorithm in this paper can remove smear effect in star image efficiently while retaining origin information and an algorithm to do radiometric correction in smear images based on modeling and estimating the probability density function of background noise in star images.
- –
- –
- Design of Infrared Detecting Intelligent Guiding Equipment Based on man-machine Interaction–
The principle and process of detecting method, control function, command definition, program design and debugging improvement of the guiding equipment were introduced, and its application and prospect were discussed.
- –
- –
- –
- –
- –
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 2026-10-15. 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.