Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks578 from public data
- 1,342
- 1,080
- 579
- 467
- 295
- 286
- 282
- Reduced Gene Expression of Vascular Endothelial NO Synthase and Cyclooxygenase-1 in Heart Failure277
The results suggest that at least two endothelial vasodilator gene products are reduced in heart failure, as opposed to a selective defect in NO synthase gene expression.
- 264
- UCL-Dehaze: Toward Real-World Image Dehazing via Unsupervised Contrastive Learning245
This paper proposes an effective unsupervised contrastive learning paradigm for image dehazing, dubbed UCL-Dehaze, which does not require paired data during training and utilizes unpaired positive/negative data to better enhance the dehazing performance.
- Color Image Watermarking Using Multidimensional Fourier Transforms237
This paper presents two vector watermarking schemes that are based on the use of complex and quaternion Fourier transforms and demonstrates, for the first time, how to embed watermarks into the frequency domain that is consistent with the human visual system.
- 217
- 205
- Comments on "An SVD-based watermarking scheme for protecting rightful Ownership"190
This comment demonstrates that this watermarking algorithm is fundamentally flawed in that the extracted watermark is not the embedded watermark but determined by the reference watermark, which biases the false positive detection rate.
- Thresholding neural network for adaptive noise reduction185
Numerical results show that the TNN is very effective in finding the optimal solutions of thresholding methods in an MSE sense and usually outperforms other noise reduction methods.
- 178
- On the Shift Operator, Graph Frequency, and Optimal Filtering in Graph Signal Processing175
A new shift operator based GSP framework enables the signal analysis along a correlation structure defined by a graph shift manifold as opposed to classical signal processing operating on the assumption of the correlation structure with a linear time shift manifold.
- Dual Vision Transformer174
This paper proposes a novel Transformer architecture that elegantly exploits the global semantics for self-attention learning, namely Dual Vision Transformer (Dual-ViT).
- The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances165
This survey article presents a comprehensive review about the recent advance of each element of the end-to-end deep face recognition, since the thriving deep learning techniques have greatly improved their capability of them.
- 159
- Performance Limits and Geometric Properties of Array Localization148
This paper determines the localization accuracy of an agent, which is equipped with an antenna array and localizes itself using wireless measurements with anchor nodes, in a far-field environment with typical anchor deployments and antenna arrays.
- Performance Limits and Geometric Properties of Narrowband Array Localization148
This paper determines the localization accuracy of an agent, which is equipped with an antenna array and localizes itself using wireless measurements with anchor nodes, in a far-field environment with typical anchor deployments and antenna arrays.
- Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI143
A Bayesian nonparametric model for reconstructing magnetic resonance images (MRIs) from highly undersampled \(k \) -space data is developed, and the proposed regularization framework can improve reconstruction accuracy over other methods.
- Transclaw U-Net: Claw U-Net With Transformers for Medical Image Segmentation140
The TransClaw U-Net network structure is proposed, which adds the bottom upsampling part to retain the deepest feature information for detail segmentation and the modified three-channel global attention mechanism to blend the outputs of three channels.
- 132
- A Survey on Speech Deepfake Detection124
This survey systematically analyze more than 200 papers published up to March 2024 and identifies the current state of the art to establish strong baselines for future experiments and offers clear guidance for researchers aiming to enhance speech Deepfake detection systems.
- 119
- 103
- Change Detection in Heterogeneous Optical and SAR Remote Sensing Images Via Deep Homogeneous Feature Fusion99
A new homogeneous transformation model termed deep homogeneous feature fusion (DHFF) based on image style transfer (IST) is presented, where the cost function in each IST iteration measures and thus maximizes the feature homogeneity in additional new feature subspaces for change detection.
- 89
- 83
- 83
- 78
- Visual–Tactile Fusion for Transparent Object Grasping in Complex Backgrounds76
A visual–tactile fusion framework for transparent object grasping in complex backgrounds is proposed, which synergizes the advantages of vision and touch, and greatly improves the grasping efficiency of transparent objects.
- An intrusion detection method for internet of things based on suppressed fuzzy clustering75
An intrusion detection method of the Internet of Things is proposed by suppressed fuzzy clustering (SFC) algorithm and principal component analysis (PCA) algorithm that has better adaptability than traditional method.
- 75
- 74
- 73
- Pi-ViMo: Physiology-inspired Robust Vital Sign Monitoring using mmWave Radars70
Pi-ViMo is presented, a non-contact Physiology-inspired Robust Vital Sign Monitoring system, using mmWave radars that is capable to separate respiration and heartbeat in the presence of micro-level random body movements (RBM) when a subject is at any location within the field of view of a radar.
- 70
- cAMP Signal Transduction Cascade, a Novel Pathway for the Regulation of Endothelial Nitric Oxide Production in Coronary Blood Vessels70
It is demonstrated that stimulation of cAMP signal transduction can substantially increase coronary NO production, indicating that there is a cAMP-mediated, endothelial NO–forming system in coronary blood vessels.
- 69
- An optimal method for prediction and adjustment on byproduct gas holder in steel industry69
The results demonstrate that the proposed approach can precisely predict and adjust gasholders and provide a remarkable guidance for reasonable scheduling of byproduct gases.
- When Vision Meets Touch: A Contemporary Review for Visuotactile Sensors From the Signal Processing Perspective68
This paper provides a comprehensive review of visuotactile sensors from the perspective of signal processing methods and outlooks possible future research directions for visuotactile sensors.
- 67
- Image Quality Assessment: From Mean Opinion Score to Opinion Score Distribution63
A convolutional neural network based on fuzzy theory is proposed to predict the opinion score distribution of image quality by learning the mapping from epistemic uncertainty to the uncertainty existing in the image quality ratings.
- 62
- Explainable Person Re-Identification with Attribute-guided Metric Distillation62
This paper proposes a post-hoc method, named Attribute-guided Metric Distillation (AMD), to explain existing ReID models, and proposes an attribute prior loss to make the interpreter generate attribute-guided attention maps and to eliminate biases caused by the imbalanced distribution of attributes.
- 61
- 61
- 61
- Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds58
Qualitative and quantitative evaluations demonstrate the clear superiority of Refine-Net over the state-of-the-arts on both synthetic and real-scanned datasets.
- Abnormal event detection in surveillance videos based on low-rank and compact coefficient dictionary learning58
A novel approach to abnormal event detection in crowded scenes is presented based on a new low-rank and compact coefficient dictionary learning (LRCCDL) algorithm based on the background subtraction and binarization of surveillance videos.
- 57
- Activation of extracellular signal regulated protein kinase by neuropeptide Y and pancreatic polypeptide in CHO cells expressing the NPY Y1, Y2, Y4 and Y5 receptor subtypes57
It is demonstrated that in CHO cells, the Y(5) receptor and the Y (1), Y(2) and Y(4) receptors utilize different pathways to activate ERK.
- 56
- Palladium-Catalyzed C–N Cross Coupling of Sulfinamides and Aryl Halides56
The palladium-catalyzed C-N cross coupling of sulfinamides and aryl halides is reported to give N-aryl tert-butanesulfinamide without racemization, and the coupling of racemic p-toluenesulf inamide smoothly afforded N- Daryl p- tolueneenesulfinamide.
- 55
- Robust image matching via local graph structure consensus53
This paper designs a local graph structure for preserving geometric topology, which contains a local indicator vector and a local affinity vector for each correspondence and derives a closed-form solution with linearithmic time and linear space complexity.
- 53
- Label propagation based supervised locality projection analysis for plant leaf classification53
This paper uses the label propagation to propose a new weight measure, and presents a supervised locality projection analysis (SLPA) method for plant leaf classification that is quite effective and feasible.
- 51
- 51
- Re-Synchronization Using the Hand Preceding Model for Multi-Modal Fusion in Automatic Continuous Cued Speech Recognition51
This work proposes a novel re-synchronization procedure for multi-modal fusion, which aligns the hand features with lips feature and is incorporated into a practical continuous CS recognition system that combines convolutional neural network with multi-stream hidden markov model.
- 50
- Optimal Two-Way TOA Localization and Synchronization for Moving User Devices With Clock Drift50
This article proposes an optimal maximum likelihood (ML) based two-way TOA localization and synchronization method, namely TWLAS, which takes the UD motion into account to compensate the error caused by the UD movement and analyzes its estimation error and derives the Cramer-Rao lower bound.
- Virtual Reality Gaming on the Cloud: A Reality Check50
This paper presents two statistical models that capture the behaviour of VR gaming video traffic and Quality of Service when VR rendering is conducted remotely in the cloud and develops an interval threshold based identification method for video frames.
- 50
- Increased apoptosis and myocyte enlargement with decreased cardiac mass; distinctive features of the aging male, but not female, monkey heart50
Gender-specific changes in aging cardiomyopathy in a primate model, Macaca fascicularis, free of the major human diseases, indicate distinct differences in which male and female monkeys maintain functional heart mass during aging.
- 49
- Design of a High-Order Dual-Band Superconducting Filter With Controllable Frequencies and Bandwidths49
- 48
- 48
- 47
- 46
- 46
- In vitro panning of a targeting peptide to hepatocarcinoma from a phage display peptide library46
The peptide WP05 was proved to be a targeting peptide to several common hepatocellular carcinoma cell lines and was demonstrated to be the most effective peptide in targeting four kinds of liver cancer cell lines.
- 45
- 44
- 44
- A New Approach to Construct Virtual Array With Increased Degrees of Freedom for Moving Sparse Arrays43
- Open3D-VQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space41
This work pro-poses a novel benchmark, Open3DVQA, to comprehensively evaluate the spatial reasoning capacities of current state-of-the-art (SOTA) foundation models in open 3D space and reveals that MLLMs perform better at answering questions regarding relative spatial relationships than absolute spatial relationships.
- A Comparative Study on Physical and Perceptual Features for Deepfake Audio Detection40
This paper provides a comprehensive study on 16 physical and perceptual features and evaluates their effectiveness in both Track 1 and Track 2 of the ADD Challenge to provide a potential direction in selecting appropriate feature extraction methods for the future implementation of detection models.
- 40
- 39
- Improving a digital elevation model by reducing source data errors and optimising interpolation algorithm parameters: An example in the Loess Plateau, China39
Large improvement in DEM quality was gained by using ANUDEM instead of TIN, with smaller improvement gained by fixing source data errors, and optimising ANUD EM parameters.
- 38
- 38
- 37
- 37
- Recent Progress of Optical Imaging Approaches for Noncontact Physiological Signal Measurement: A Review37
This is a comprehensive overview of the noncontact physiological signal measurement of optical imaging approaches, including principles of various optical imaging techniques, processing methods for data analysis, discussion on advantages and disadvantages, application summary, and future prospects.
- 36
- TransformLoc: Transforming MAVs into Mobile Localization Infrastructures in Heterogeneous Swarms36
This study proposes TransformLoc, a new framework that transforms AMAVs into mobile localization infrastructures, specifically designed for low-cost and resource- constrained BMAVs, and achieves a collaborative, adaptive, and cost-effective localization system suitable for large-scale heterogeneous MAV swarms.
- SAFARI: Sparsity-Enabled Federated Learning With Limited and Unreliable Communications36
A sparsity-enabled FL framework with both improved communication efficiency and bias reduction, termed as SAFARI, that makes use of similarity among client models to rectify and compensate for bias that results from unreliable communications is proposed.
- 35
- 35
- 34
- Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer34
The proposed Tem-adapter enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner that first designs a template to fuse question and answer pairs as event descriptions and then learns a Transformer decoder with the whole video sequence as guidance for refinement.
- 34
- 34
- 34
- 34
- 34
- From the wavelet series to the discrete wavelet transform-the initialization34
In this correspondence, the problem is analyzed, and two simple algorithms for the initialization are introduced, and numerical examples are presented to show that these algorithms are more effective than others.
- 33
- Scheduling UAV Swarm with Attention-based Graph Reinforcement Learning for Ground-to-air Heterogeneous Data Communication32
AGUZero, an attention-based graph reinforcement learning (RL) framework designed to handle dynamic and uncontrollable environments based on Monte Carlo Tree Search (MCTS), outperforms other baseline models consistently when either the number of UAVs or theNumber of sensors is varying.
- DOA Estimation for Heterogeneous Wideband Sources Based on Adaptive Space-Frequency Joint Processing32
- 32
- Open3D-VQA: A Benchmark for Embodied Spatial Concept Reasoning with Multimodal Large Language Model in Open Space31
Evaluation on 13 popular MLLMs reveals that: 1) Models are generally better at answering questions about relative spatial relations than absolute distances, 2) 3D LLMs fail to demonstrate significant advantages over 2D LLMs, and 3) Fine-tuning solely on the simulated dataset can significantly improve the model's spatial reasoning performance in real-world scenarios.
- Dilated projection correction network based on autoencoder for hyperspectral image super-resolution31
This paper transforms the HSI SR problem from the image domain into the abundance domain by the dilated projection correction network with an autoencoder, termed as aeDPCN, and preserves the spectral information in the decoder network, which could largely reduce the computational complexity.
- 31
- 31
- 31
- 31
- 31
- New Closed-Form Joint Localization and Synchronization Using Sequential One-Way TOAs30
This paper proposes a new closed-form JLAS approach, namely CFJLAS, which achieves the asymptotically optimal solution in one shot without initialization when the noise is small, and has a low computational complexity.
- 30
- Short-term Exercise Training Enhances Reflex Cholinergic Nitric Oxide–Dependent Coronary Vasodilation in Conscious Dogs30
The results indicate that the coronary vasodilation following activation of the Bezold-Jarisch reflex is enhanced in conscious dogs after exercise training, most likely due to the increased release of NO from the endothelial cells.
- Closed-Form Two-Way TOA Localization and Synchronization for User Devices With Motion and Clock Drift29
The theoretical analysis and numerical results verify the theoretical analysis that the estimation accuracy of the new CFTWLAS method reaches CRLB in the presented experiments when the number of ANs is large, the geometry is appropriate, and the noise is small.
- MobiAir: Unleashing Sensor Mobility for City-scale and Fine-grained Air-Quality Monitoring with AirBERT28
This work proposes MobiAir, a novel city-scale fine-grained air quality estimation system to deliver accurate mobile air quality data, and designs AirBERT, a representation learning model to discern mixed gas concentrations.
- Audio texture and age-wise analysis of disordered speech in children having specific language impairment28
Experimental results indicate that with the proposed system the classification accuracy rate of the system has been improved up to 13.1% if the LBP features are fused along with the traditional features with a highest average accuracy rates of 97.36% when a 5-fold cross validation is done.
- Proposal-Copula-Based Fusion of Spaceborne and Airborne SAR Images for Ship Target Detection⁎⁎28
Experimental results show that the proposed TPCT fusion method leads to higher TCRs of composite images and better performance in the ship detection task than other commonly used image fusion methods.
- 28
- 28
- Noise Invalidation Denoising28
Experimental results show that the proposed method, called noise invalidationDenoising (NIDe), outperforms existing denoising approaches in terms of mean square error (MSE).
- Brain-derived neurotrophic factor and electrophysiological properties of voltage-gated ion channels during neuronal stem cell development28
It is found that chronic stimulation of neural stem cells with bath application of 40 ng/ml BDNF during differentiation promoted the functional development of passive membrane, evoked biphasic changes in Na(+) currents, regulated the expression of K(+ channels and the outward K(+) especially at the early developmental stage.
- 27
- AQUILA: Communication Efficient Federated Learning With Adaptive Quantization in Device Selection Strategy27
This paper introduces AQUILA (adaptive quantization in device selection strategy), a novel adaptive framework devised to effectively handle overheads and biases in Federated Learning, enhancing the efficiency and robustness of FL.
- 27
- Role of nitric oxide in the coupling of myocardial oxygen consumption and coronary vascular dynamics during pregnancy in the dog27
Increases in eNOS and SOD-1 promote the coupling of oxygen delivery and efficiency in the heart during pregnancy, and this increase is associated with enhanced nitric oxide-dependant control of MVO(2).
- 26
- A Closed-Form Localization Method Utilizing Pseudorange Measurements From Two Nonsynchronized Positioning Systems26
A new closed-form dual-system localization (CDL) approach that has low complexity and optimal localization accuracy, and does not require initialization and has lower computational complexity with comparable positioning accuracy is proposed.
- Nonparametric discriminant multi-manifold learning for dimensionality reduction26
A dimensionality reduction method titled nonparametric discirminant multi-manifold learning (NDML) is put forward and involved in different manifolds recognition and experimental results validate that the proposed NDML can obtain better performance than other methods.
- 26
- 26
- Multi-Task Learning Model Based on BERT and Knowledge Graph for Aspect-Based Sentiment Analysis25
A multi-task sentiment analysis model based on Bidirectional Encoder Representation from Transformers and a Knowledge Graph (SABKG) and the experimental results show that the proposed model can achieve the most advanced performance compared with previous models.
- 25
- 25
- 25
- 25
- 24
- 24
- 24
- 23
- 23
- 23
- 23
- 23
- M2Restore: Mixture-of-Experts-Based Mamba-CNN Fusion Framework for All-in-One Image Restoration22
This work proposes M2Restore, a novel Mixture-of-Experts (MoE)-based Mamba-CNN fusion framework for efficient and robust all-in-one image restoration, and introduces an edge-aware dynamic gating mechanism that adaptively balances global modeling and local enhancement by reallocating computational attention to degradation-sensitive regions.
- Sequential Doppler-Shift-Based Optimal Localization and Synchronization With TOA22
A new optimal LAS method in the TDBS, namely, LAS-SDT, is developed by taking advantage of the sequential Doppler shift and TOA measurements, which achieves higher accuracy compared with the conventional TOA-only method for user devices (UDs) with motion and clock drift.
- 22
- 22
- 22
- A MKL based on-line prediction for gasholder level in steel industry22
This study extended the least squares support vector regression to multiple kernel learning (MKL) based on reduced gradient method, using the optimal linear combination of kernels, and improves the generalization of the model and reduces the training time.
- Quaternion image watermarking using the spatio-chromatic fourier coefficients analysis22
A new color watermarking algorithm that uses the quaternion fourier transform (QFT) to mark the La*b* components of color images is presented and an interpretation of the QFT coefficients using the Spatio-Chromatic Fourier analysis is proposed.
- Automatic identification of digital video based on shot-level sequence matching22
A novel technique based on dynamic programming that fully uses the temporal dimension to measure the similarity between two video sequences is presented, and two new normalized distance measures are presented for video sequence matching.
- 22
- WDMamba: When Wavelet Degradation Prior Meets Vision Mamba for Image Dehazing21
A novel dehazing framework, WDMamba, which decomposes the image dehazing task into two sequential stages: low-frequency restoration followed by detail enhancement, and introduces a self-guided contrastive regularization during network training to enhance detail retention and achieve more natural dehazing.
- 21
- 21
- A Survey of Single Image Rain Removal Based on Deep Learning20
This paper presents a comprehensive review of single image deraining based on deep learning over the past ten years and quantitatively investigates the performances of the existing state-of-the-art methods on both publicly synthetic and real datasets.
- 20
- 20
- Electro-optical phenomena based on ionic liquids in an optofluidic waveguide20
The electro-optical phenomenon of ILs is probably caused mainly by the change in carrier concentration (ion redistribution near charged electrodes), which induces the enhancement and suppression of NIR optical absorption (contributed by C-H and N-H groups) in the vicinity of the negative electrode and positive electrode, respectively.
- Feature extraction using maximum nonparametric margin projection20
A maximum nonparametric margin projection (MNMP) method is put forward to extract features from original high dimensional data to remove the disadvantage that linear discriminant analysis (LDA) can not be well-performed in the cases of non-Gaussian distribution data.
- 20
- 20
- 20
- cAMP Signal Transduction, A Potential Compensatory Pathway for Coronary Endothelial NO Production After Heart Failure20
It is indicated that cAMP signal transduction may be an important potential compensatory pathway to increase myocardial microvascular NO production after HF when eNOS is downregulated.
- Quantification of eNOS mRNA in the canine cardiac vasculature by competitive PCR20
The ability to quantify changes in eNOS mRNA levels throughout the canine vasculature should provide greater insight into the molecular mechanisms of how this gene is regulated in physiological and pathophysiological states.
- 19
- 19
- TraND: Transferable Neighborhood Discovery for Unsupervised Cross-Domain Gait Recognition19
This paper proposes a Transferable Neighborhood Discovery (TraND) framework to bridge the domain gap for unsupervised cross-domain gait recognition, and explores a high- entropy-first neighbor selection strategy, which can effectively transfer prior knowledge to the target domain.
- DOVE: Doodled vessel enhancement for photoacoustic angiography super resolution18
An approach doodled vessel enhancement (DOVE) that utilizes hand-drawn doodles to train a PAA super-resolution model and overcomes the limitation of insufficient training samples and unlocks the clinic application potential of super-resolution-based biomedical imaging.
- 18
- 18
- Role of Oxidative Stress in the Occurrence and Development of Cognitive Dysfunction in Patients with Obstructive Sleep Apnea Syndrome18
Analysis on the relationship between oxidative stress and cognitive dysfunction in patients with OSAS will help to clarify the etiology and discover new treatment options, which will be of great significance for early clinical intervention.
- Exploiting Relationship for Complex-scene Image Generation18
This work explores relationship-aware complex-scene image generation, where multiple objects are inter-related as a scene graph and proposes three major updates in the generation framework, which significantly outperforms prior arts in terms of IS and FID metrics.
- Automatic Detection of the Temporal Segmentation of Hand Movements in British English Cued Speech18
This work proposes a novel diphthong-hand preceding model (D-HPM) and presents a hybrid temporal segmentation detection algorithm (HTSDA) for the hand movement in CS, the first work to study the temporal organization of hand movements in British English CS.
- FactorMiner: A Self-Evolving Agent with Skills and Experience Memory for Financial Alpha Discovery17
FactorMiner provides a practical approach to scalable discovery of interpretable formulaic alpha factors under the ''Correlation Red Sea'' constraint and constructs a diverse library of high-quality factors with competitive performance, while maintaining low redundancy among factors as the library scales.
- 17
- 17
- 17
- 17
- 17
- 17
- 17
- 17
- 17
- 17
- Endocardial endothelium in the avascular frog heart: role for diffusion of NO in control of cardiac O2 consumption17
It appears that the EE of the frog heart is the sole source of NO to regulate myocyte O(2) consumption, and produces enough NO, which diffuses from the EE to cardiac myocytes, to regulate the myocardial O( 2) consumption.
- Steganography for medical record image16
The experimental results show that the designed distortion network and the FISM loss function term can be well suited for the steganographic task of medical record images from the perspective of decoding accuracy and image quality.
- 16
- 16
- 16
- 16
- An Automated Video Object Extraction System Based on Spatiotemporal Independent Component Analysis and Multiscale Segmentation16
A novel technique is developed to extract objects from video sequences based on spatiotemporal independent component analysis (stICA) and multiscale analysis and an automated video object extraction system is developed based on these new techniques.
- Semidefinite Programming Two-Way TOA Localization for User Devices With Motion and Clock Drift15
This letter converts the original estimator into a convex problem by relaxation, and develops a new semidefinite programming (SDP) based localization method for moving UDs, namely SDP-M, which significantly reduces the localization error and outperforms the conventional method for stationary UDs.
- 15
- 15
- 15
- Dual-modal Tactile E-skin: Enabling Bidirectional Human-Robot Interaction via Integrated Tactile Perception and Feedback14
A dual-modal electronic skin that integrates magnetic tactile sensing and vibration feedback for enhanced HRI and is capable of transmitting tactile information bidirectionally, enabling object recognition and fine-weighing operations is proposed.
- Interpretable Temporal Class Activation Representation for Audio Spoofing Detection14
This paper proposes a class activation representation to localize the discriminative frames contributing to detection and demonstrates that multi-label training based on spoofing types, rather than binary labels as bonafide and spoofed, enables the model to learn distinct characteristics of different attacks, significantly improving detection performance.
- Angel’s Girl for Blind Painters: An Efficient Painting Navigation System Validated by Multimodal Evaluation Approach14
This work designs a simple yet efficient position information coding rule to remind the user of the current brush tip position and designs a criterion to efficiently judge whether the brush reaches the target or not, and demonstrates that it is practicable for the blind people to feel the world through the brush in their hands.
- 14
- 14
- Non-local channel aggregation network for single image rain removal14
A non-local channel aggregation network (NCANet) to address the SIRR problem by recurrently aggregating information from all three directions enables the model to capture the long-range dependencies in both channels and spaitials locations.
- Computer-Aided Diagnosis of Children with Cerebral Palsy under Deep Learning Convolutional Neural Network Image Segmentation Model Combined with Three-Dimensional Cranial Magnetic Resonance Imaging14
According to the research results, in the diagnosis of cerebral palsy in children, the image segmentation of brain 3D model based on CNN to obtain the MRI image of segmented brain tissue can effectively improve the detection accuracy.
- Rain Detection and Removal via Shrinkage-based Sparse Coding and Learned Rain Dictionary14
Experimental results verified that the proposed shrinkage-based sparse coding model could remove rain structures and preserve objects’ details due to the REC- or DCNN-based rain detection using the scribbled rain image set and confirmed that the method is more effective at removing rain structures from similar objects' structures than conventional methods.
- A Novel Classification Method for Syndrome Differentiation of Patients with AIDS14
The minimum reference set-based multiple instance learning (MRS-MIL) method, which identifies a list of representative symptoms for each syndrome and builds a Gaussian mixture model based on them, can produce reliable and high quality classification rules even on datasets with small sample size.
- 14
- Content-based image retrieval using a Gaussian mixture model in the wavelet domain14
The experimental results indicate that the new statistical-model based technique for analyzing and extracting image features in the wavelet domain is very effective in representing image characteristics and provides a high retrieval rate in the CBIR system.
- 13
- Multistate Constraint Multipath-Assisted Positioning and Mismatch Alleviation13
A novel real-time and low computation complexity multipath-assisted ToA positioning method, namely, multistate constraint (MSC)-MAP, which can substantially improve positioning performance while adding minimal computation time in the presence of measurement mismatches and can also efficiently handle signals with non-Gaussian impairments.
- 13
- Multi-class change detection of remote sensing images based on class rebalancing13
This paper is the first time to introduce the image class balancing method in the multi-class change detection task, so a control experiment is designed to verify the effectiveness and superiority of this method for the unbalanced data.
- 13
- 13
- 13
- 13
- Identification and characterization of pseudoirreversible nonpeptide antagonists of the neuropeptide Y Y5 receptor and development of a novel Y5-selective radioligand13
Data indicate that the apparent insurmountable antagonism of these NPY Y(5) receptor antagonists is attributable both to slow receptor dissociation rates and to binding at a site distinct from NPY.
- 12
- Adaptive Super-Resolution Networks for Single-Pixel Imaging at Ultra-Low Sampling Rates12
By merging sophisticated network design with strategic integration of physical sampling rates, this model provides a refined solution for high-quality, high-resolution SPI at minimal sampling rates, facilitating progress in ultra-fast imaging applications.
- 12
- Speckle-free holography with a diffraction-aware global perceptual model12
This work proposes a CGH model called Holomer, which has a single-layer perceptual field 43 times larger than that of a widely used 3 × 3 convolutional kernel, thanks to the embedding-based feature dimensionality reduction and multi-head sliding-window self-attention mechanisms.
- 12
- A multi‐modal clustering method for traditional Chinese medicine clinical data via media convergence12
- 12
- 12
- 12
- Space-Time Adaptive Processing by Employing Structure-Aware Two-Level Block Sparsity12
This article proposes a new STAP approach exploiting structure-aware two-level block sparsity (STBS) of radar echoes, namely STBS-STAP, which enhances the performance on clutter suppression and target detection with limited training snapshots.
- 12
- 12
- 12
- 12
- 11
- SmoothLander: A Quadrotor Landing Control System with Smooth Trajectory Guarantee Based on Reinforcement Learning11
The results show that the SmoothLander control system, an aerodynamics and reinforcement learning-based control system to stabilize the quadrotors under the influence of the ground effect and control noise, can enable thequadrotor to land more smoothly and stably against control noise than the baseline.
- A new mechanism of rule acquisition based on covering rough sets11
The action parameters are first introduced to establish a more realistic granule associativity rule in covering information system and the rule-based data potential to address the measurement problem is presented.
- Phenonizer: A Fine‐Grained Phenotypic Named Entity Recognizer for Chinese Clinical Texts11
The proposed phenotypic named entity recognizer, Phenonizer, which utilized BERT to capture character‐level global contextual representation, extracted local contextual features combined with bidirectional long short‐term memory, and finally obtained the optimal label sequences through conditional random field is developed.
- Effects of different regimes of low temperature on egg hatching of Dactylogyrus vastator (Monogenea: Dactylogyridae)11
It is suggested that egg incubation for more than 1 week at 5 °C had significant impacts on hatching success of D. vastator, and low temperature had no effect on hatch success when eggs were firstly exposed to room temperature for one day.
- 11
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- Locally linear representation Fisher criterion based tumor gene expressive data classification10
A discriminant manifold learning method, named locally linear representation Fisher criterion (LLRFC), is applied to extract features from tumor gene expressive data to explore a low dimensional subspace where the reconstruction errors in the inter-class graph can be maximized and the reconstructionerrors in the intra-classgraph can be minimized, simultaneously.
- WEIGHTED NEIGHBORHOOD CLASSIFIER FOR THE CLASSIFICATION OF IMBALANCED TUMOR DATASET10
A subclass-weighted neighborhood classifier to address the imbalanced sample set problem and a novel neighborhood rough set model to select informative genes for classification performance improvement are proposed.
- 10
- 10
- 10
- 9
- Translating Motion to Notation: Hand Labanotation for Intuitive and Comprehensive Hand Movement Documentation9
A novel notation system, named Hand Labanotation (HL), for hand movement documentation, and a novel multi-view transformer architecture for automatically translating hand movements to HL, which makes the method a general tool for hand movement documentation.
- Joint Beamforming for Backscatter Integrated Sensing and Communication9
A novel backscatter-ISAC (B-ISAC) system is proposed and a joint beamforming scheme aiming to optimize the communication rate under sensing constraint and power budget and an iterative algorithm is developed for solving the complicated non-convex optimization problem.
- Demo: SolarSense: A Self-powered Ubiquitous Gesture Recognition System for Industrial Human-Computer Interaction9
SolarSense is a self-powered sensing system for gesture recognition using solar cell arrays, thereby offering a sustainable approach to human-computer interaction (HCI) within industrial settings and suitable for Internet of things (IoT) scenarios.
- Audio-Visual Quality Assessment for User Generated Content: Database and Method9
The first UGC AVQA database named the SJTU-UAV database is constructed, which includes 520 in-the-wild UGC audio and video (A/V) sequences, and the experimental results show that with the help of audio signals, the VQA models can evaluate the perceptual quality more accurately.
- 9
- 9
- 9
- 9
- Boosting Video Representation Learning with Multi-Faceted Integration9
A new learning framework to aggregate facets from different datasets for learning a representation that could reflect the full spectrum of video content, which explicitly maps video representation into a rich semantic embedding space, and jointly optimizes video representation from two perspectives.
- Identification of Deep Breath While Moving Forward Based on Multiple Body Regions and Graph Signal Analysis9
This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera, and can be extended to public places to provide timely and ubiquitous help for those who may have or are going through physical or mental trouble.
- A Segmentation Map Difference-Based Domain Adaptive Change Detection Method9
A domain adaptive CD method based on segmentation map difference is proposed, which has strong domain adaptability and can greatly reduce the influence of the difference in feature distributions of the CD results.
- Time-Distributed Feature Learning in Network Traffic Classification for Internet of Things9
A novel network data representation is proposed, treating the traffic data as a series of images to employ time-distributed (TD) feature learning, and shows that the TD feature learning elevates the network classification performance by 10%.
- Using Mobile Phone Data to Examine Point-of-Interest Urban Mobility9
An appearance probability estimation algorithm is proposed to detect individual frequent locations for each user, and thereafter mobile users are classified into POI-related categories for further analysis of group-level mobility behavior.
- A novel aliasing-free subband information fusion approach for wideband sparse spectral estimation9
This paper reformulated the MD/MM problem is reformulated as a single sparse indicative vector (SIV) recovery problem at the cost of introducing an additional system error, and the number of unknowns is reduced greatly.
- 9
- Interest-suppression-based NDN live video broadcasting over wireless LAN9
A new NDN-based cross-layer approach called NLB for efficient and scalable live video streaming over wireless LAN, using WiFi’s broadcast channel to deliver content from the access point to the users, a leader-based mechanism to suppress duplicate requests from users, and receiver-driven rate control and loss recovery.
- 9
- 9
- 9
- 9
- 9
- Performances of Amplify-and-Forward Cooperative Relay Networks with Different Topologies9
An aggregated channel mode is proposed, which combines the power gain obtained from the reduction of path loss through the deployment of relays, and the flat fading caused by multi-path propagation, as well as the outage probabilities of the MISO systems.
- 9
- 9
- A web-enabled video indexing system9
A new web-enabled video indexing system that integrates Synchronized Multimedia Integration Language (SMIL) standard is presented that can effectively detect shot boundaries and methods for eliminating false positives are described.
- SniffySquad: Patchiness-Aware Gas Source Localization with Multi-Robot Collaboration8
SniffySquad is introduced, a multi-robot olfaction-based system designed to address the inherent patchiness in gas source localization that achieves an increase in the success rate and improvement in path efficiency, outperforming state-of-the-art gas source localization solutions.
- Aerial Shepherds: Enabling Hierarchical Localization in Heterogeneous MAV Swarms8
This work introduces TransformLoc, a new framework that transforms AMAVs into mobile localization infrastructures, specifically designed for low-cost and resource-constrained BMAVs, and designs an error-aware joint location estimation model to perform intermittent joint estimation for BMAVs.
- 8
- Foes or Friends: Embracing Ground Effect for Edge Detection on Lightweight Drones8
AirTouch is proposed, a system that transforms the ground effect from a stability "foe" in traditional flight control views, into a "friend" for accurate and efficient edge detection, thereby achieving accurate and efficient scene edge detection.
- 8
- 8
- 8
- Sea surface target detection based on complex ARMA-GARCH processes8
A complex-valued ARMA-GARCH model for the sea clutter modeling application is developed and it is shown that the proposed sea surface target detector offers a noticeable improvement for the probability of detection, comparing with the state-of-the-art AR-Garch detector.
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- FL-TAC: Enhanced Fine-Tuning in Federated Learning via Low-Rank, Task-Specific Adapter Clustering7
This paper addresses the high communication cost for fine-tuning large pre-trained models within FL frameworks through low-rank fine-tuning and proposes the proposed low-rank task-specific adapter clustering (TAC) method.
- 7
- 7
- Time-Distributed Feature Learning for Internet of Things Network Traffic Classification7
The proposed holistic-temporal time-distributed feature extraction method is efficient in learning holistic-temporal features and proves that pseudo-temporal and spatial-temporal features can significantly improve the robustness and performance of any NTC.
- 7
- 7
- 7
- 7
- 7
- 7
- Segmented Learning for Class-of-Service Network Traffic Classification7
The solution is the first to propose segmentation learning NTC that uses fewer features to classify most CoS traffic with an accuracy of 99 % and is validated on multiple datasets for various CoS services, including virtual reality (VR).
- Tao-Hong-Si-Wu decoction improves depressive symptoms in model rats via amelioration of BDNF-CREB-arginase I axis disorders7
Traditional Chinese medicine formula Tao-Hong-Si-Wu decoction (TSD), used for treating ischaemic stroke, has the potential to treat depressive disorder (DD).
- 7
- 7
- 7
- Point Cloud Denoising Based on Tensor Tucker Decomposition7
A new algorithm for point cloud de-noising based on the tensor Tucker decomposition, which outperforms the state-of-the-art graph Laplacian regularized (GLR) algorithm when the Gaussian noise is high, and the GLR algorithm is better in lower noise cases.
- 7
- 7
- 7
- 7
- A smart video player with content-based fast-forward playback7
A video player to allow the users to do fast-forward playback based on the semantic video content by developing a VTDF-based temporal quantization method to find the best quanta and partition in the time domain.
- 7
- SmartSpr: A Physics-Informed Mobile Sprinkler Scheduling System for Reducing Urban Particulate Matter Pollution6
The proposed SmartSpr incorporates a Physics-Informed Neural Network-based model, enriched with Bayesian optimization, to accurately simulate the impact of mobile sprinklers on particulate matter (PM) dispersion, and a selective sprinkling strategy considering the replenish process is proposed.
- 6
- 6
- Federated PAC-Bayesian Learning on Non-IID Data6
This work presents the first non-vacuous federated PAC-Bayesian bound tailored for non-IID local data, which assumes unique prior knowledge for each client and variable aggregation weights.
- 6
- 6
- Leveraging spatial residual attention and temporal Markov networks for video action understanding6
This paper presents a novel two-stream approach that incorporates Spatial Residual Attention and Temporal Markov (SRATM) to learn complementary features to achieve stronger video action understanding performance.
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- Super-resolution compressed sensing imaging algorithm based on sub-pixel shift6
Experimental results revealed that the proposed sub-pixel shift method can effectively improve the resolution of compressed sensing imaging system and obtain super-resolution image information.
- 6
- 6
- A novel video thumbnail extraction method using spatiotemporal vector quantization6
A novel video data modeling tools, video time density function (VTDF) is presented to explore the temporal characteristics of video content to create video thumbnail using a new spatiotemporal vector quantization method.
- A New Hierarchical Key Frame Tree-Based Video Representation Method Using Independent Component Analysis6
A new hierarchical key frame tree-based video representation technique to model the video content hierarchically by projecting video frames from illumination-invariant raw feature space into low dimensional independent component analysis (ICA) subspace.
- 6
- 6
- 6
- Beyond Identity: A Generalizable Approach for Deepfake Audio Detection5
This work proposes an identity-independent audio deepfake detection framework that mitigates identity leakage by encouraging the model to focus on forgery-specific artifacts instead of overfitting to speaker traits, and introduces novel dynamic artifact generation techniques, including frequency domain swaps, time domain manipulations, and background noise augmentation to enforce learning of dataset-invariant features.
- 5
- 5
- 5
- Don't worry about mistakes! Glass Segmentation Network via Mistake Correction5
A novel glass segmentation network to detect transparent glass, dubbed GlassSegNet, designed to simulate the detection procedure of human recognition for identifying transparent glass by global context and edge information.
- 5
- 5
- 5
- 5
- Visuotactile Sensor Enabled Pneumatic Device Towards Compliant Oropharyngeal Swab Sampling5
A sampling method that adopts a compliant control algorithm based on the adaptive virtual force to enhance the safety and compliance of the swab sampling process to address the problems of high cost and poor reliability of traditional multi-axis force sensors.
- Rapidly developing human heat residue model under various conditions based on Fluent and thermal video5
This work has developed a two-dimensional (2D) model for human thermal residue emulation via the Fluent software and demonstrated that the simulation models can effectively imitate the thermal dissipation process in real scenes under different contact materials and contact time.
- 5
- 5
- On the Shift Operator and Optimal Filtering in Graph Signal Processing.5
This work defines a unique set of shift operators that satisfy all properties of the shift operator in the classical signal processing, especially energy preservation property, and elaborate on the best linear predictor graph filters and optimal filters for product graphs.
- 5
- 5
- 5
- Ice hockey shot event modeling with mixture hidden Markov model5
The results prove that the mixture HMM is a suitable model to deal with complex videos with intensive activities and could be a very useful tool for coaches and players to analyze hockey games.
- 5
- When Marine Radar Target Detection Meets Pretrained Large Language Models4
This work proposes a framework that integrates feature preprocessing with large language models (LLMs), which tokenizes radar sequence features, applies a patch selection algorithm to filter out uninformative segments, and projects the selected patches into embeddings compatible with the feature space of pre-trained LLMs.
- 4
- 4
- 4
- Language-Free Compositional Action Generation via Decoupling Refinement4
This study introduces a novel framework to generate compositional actions without language auxiliaries using a conditional generative model, CVAE, and a self-supervised pre-trained model MAE to ensure semantic consistency between sub-actions and compositional actions.
- 4
- 4
- Cooperative Multi-Type Multi-Agent Deep Reinforcement Learning for Resource Management in Space-Air-Ground Integrated Networks4
A comprehensive SAGIN system that encompasses five distinct communication links is developed and an efficient cooperative multi-type multi-agent deep reinforcement learning (CMT-MARL) method is proposed to address the resource management issue.
- 4
- 4
- 4
- 4
- 4
- 4
- Direction-aware Feature-level Frequency Decomposition for Single Image Deraining4
Different from existing algorithms using convolutional filters consistent in all directions, this work proposes a direction-aware filter to capture the direction of rain streaks in order to more effectively and thoroughly purge the input images ofRain streaks.
- 4
- 4
- 4
- Generative adversarial networks for non-negative matrix factorization in temporal psycho-visual modulation4
This paper presents an end-to-end learned model for image-based non-negative matrix factorization, based on conditional GAN and a variational sample disturber that outperforms other CNN based methods on several public datasets.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- Ice hockey shooting event modeling with mixture hidden Markov model4
A new event analysis framework based on mixture hidden Markov model (HMM) for ice hockey videos is presented and it is confirmed that the mixture HMM is a suitable model to deal with videos with intensive activities.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- SCOPE: Skeleton Graph-Based Computation-Efficient Framework for Autonomous UAV Exploration3
Comparative evaluations in simulation demonstrate that SCOPE achieves competitive exploration performance comparable to state-of-the-art global planners, while reducing computational cost by an average of 86.9%.
- 3
- From 2D to 3D Cognition: A Brief Survey of General World Models3
This survey addresses the need for systematic analysis to categorize emerging techniques and clarify their roles in advancing 3D cognitive world models by introducing a conceptual framework, providing a structured and forward-looking review of world models transitioning from 2D perception to 3D cognition.
- Structure-prior Informed Diffusion Model for Graph Source Localization with Limited Data3
SIDSL (Structure-prior Informed Diffusion model for Source Localization), a generative diffusion framework that leverages topology-aware priors to enable robust source localization with limited data, is presented.
- VTire: A Bimodal Visuotactile Tire With High-Resolution Sensing Capability3
This article introduces a bimodal sensing tire, which can simultaneously capture tactile and visual data, and constructs an intelligent mobile platform to validate the system's effectiveness and develop visual and tactile datasets in complex terrains.
- 3
- HiLTV: Hierarchical Multi-Distribution Modeling for Lifetime Value Prediction in Online Games3
HiLTV is proposed, a novel hierarchical framework for LTV prediction in online games that devise hierarchical modules to align with real-world user recharge behaviors, and a Zero-Inflated Mixture-of-Logistic (ZIMoL) loss instead of a unimodal distribution loss is adopted to better model various segments of users.
- Poster: Real-time Material and Texture Recognition Using Visible Light Communication3
This study highlights VLC's potential in enhancing automated recognition systems across various applications, through a comprehensive design integrating hardware and software that achieves 97.7% accuracy in material identification and 93.8% in texture detection.
- 3
- 3
- Finding the Most Transferable Tasks for Brain Image Segmentation3
This paper adapt the state-of-the-art analytical transferability estimation metrics to medical image segmentation tasks and shows that their performance can be significantly boosted by filtering candidate source tasks based on modality and RoI characteristics.
- Parameterized Image Quality Score Distribution Prediction3
This paper proposes a framework and an algorithm to predict the alphastable model based IQSD, where quality features are extracted from each image based on structural information and statistical information, and support vector regressors are trained to predictthe alpha stable model parameters.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- A content-based rapid video playback method using motion-based video time density function and temporal quantization3
Experimental results show that the proposed method is effective to capture the important semantic information of video data during rapid playback and is integrated into a video player for variable-rate rapid video playback that preserves content.
- 3
- 3
- A new room decoration assistance system based on 3D reconstruction and integrated service3
This paper introduces a room decoration assistance system that delivers a new interactive 3D service to mobile customers and takes advantage of the intergraded network such as three screen services to deliver the service.
- 3
- 3
- 3
- 3
- 3
- QUIDS: Quality-Informed Incentive-Driven Multiagent Dispatching System for Mobile Crowdsensing2
The QUIDS system leverages nondedicated vehicles and incorporates a quality-informed, incentive-driven dispatching system to jointly optimize sensing coverage and sensing reliability, which enables low-cost, high-quality, and scalable urban environmental monitoring without the need for dedicated sensing infrastructure.
- Using a machine learning framework for natural language processing to create a high-resolution carbon emission map for urban manufacturing2
A fine-tuned, pre-trained natural language processing model based on Bidirectional Encoder Representations from Transformers is employed to classify points of interest data into manufacturing industry categories and addresses the gap in micro-scale research on the correlation between manufacturing concentration and carbon emissions.
- 2
- Species-specific relationships between net primary productivity and forest age for subtropical China2
- 2
- 2
- UVCG: Leveraging Temporal Consistency for Universal Video Protection2
UVCG embeds the content of another video(target video) within a protected video by introducing continuous, imperceptible perturbations which has the ability to force the encoder of editing models to map continuous inputs to misaligned continuous outputs, thereby inhibiting the generation of videos consistent with the intended textual prompts.
- 2
- 2
- Misaligned Over-The-Air Computation of Multi-Sensor Data with Wiener-Denoiser Network2
The misalignment problem is formulates as a non-blind image deblurring problem as a non-blind image deblurring problem, and the method is capable to exploit the inherent correlations in the signal data via learning, thus outperforms traditional methods in term of accuracy.
- 2
- 2
- 2
- CoCoOpter: Pre-train, prompt, and fine-tune the vision-language model for few-shot image classification2
The proposed CoCoOpter alleviates the overfitting and ensures generalizability in unseen new categories in unseen classes and achieves superior few-shot classification performance with a straightforward design.
- 2
- 2
- A novel three-channel endorectal coil for prostate magnetic resonance imaging at 3T2
A novel three-channel endorectal prostate coil is designed and fabricated and validated its feasibility of high-resolution magnetic resonance imaging (MRI) at 3T and could enable parallel imaging based fast imaging in prostate imaging studies.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Chain routing algorithm of wireless sensor network based on adaptive back-off adjusted medium access control2
The results show that, compared with the traditional chain routing algorithm and progressive best backoff algorithm, the algorithm has great advantages in terms of chaining efficiency, node life cycle and delay.
- Multimodal fusion via a series of transfers for noise removal2
The proposed transfer-based fusion method is superior to conventional fusion methods and guided filtering, and even the state-of-the-art fusion methods based on scale map and layer decomposition in solving the discrepancy problem.
- 2
- 2
- 2
- 2
- 2
- 2
- Nonparametric Discriminant Multi-manifold Learning2
Experiments validate that NDML is of better performance than some other dimensionality reduction methods, such as Unsupervised Discriminant Projection (UDP), Constrained Maximum Variance Mapping (CMVM) and Lineardiscriminant Analysis (LDA).
- Automatic Video Intro and Outro Detection on Internet Television2
This work develops a framework that identifies intro and outro parts of a show using computationally-efficient features such as silence gaps, blank screen transitions and histogram of shot boundaries and test the proposed intro/outro detection methods on a large number of videos.
- 2
- 2
- 2
- 2
- 2
- 2
- [Characters of infiltration and preferential flow of black soil in Northeast China under different tillage patterns].2
NT soil had better development of pore structure and more biological pores, and presented better preferential flow character, which were of importance for water infiltration and soil and water conservation.
- 2
- 2
- 1
- 1
- 1
- Reinforced Domain Selection for Continuous Domain Adaptation1
This work proposes a novel framework that combines reinforcement learning with feature disentanglement to conduct domain path selection in an unsupervised CDA setting and introduces an innovative unsupervised reward mechanism that leverages the distances between latent domain embeddings to facilitate the identification of optimal transfer paths.
- 1
- 1
- Revealing the key modules and potential prognostic markers of gastric cancer transformation based on weighted gene co-expression networks1
FCRL3, EFEMP1, ANKRD29, and STOX2 may serve as potential biomarkers for monitoring the transition from precancerous lesions to gastric cancer, offering insights into the mechanisms of gastric carcinogenesis and supporting early diagnosis and intervention strategies.
- PhysFire-WM: A Physics-Informed World Model for Emulating Fire Spread Dynamics1
PhysFire-WM is introduced, a Physics-informed World Model for emulating Fire spread dynamics that internalizes combustion dynamics by encoding structured priors from a Physical Simulator to rectify physical discrepancies, coupled with a Cross-task Collaborative Training strategy (CC-Train) that alleviates the issue of limited information in mask-based modeling.
- A Face Quality Assessment System for Unattended Face Recognition: Design and Implementation1
A face quality assessment approach that selects the highest‐quality face image using a two‐stage process from video streaming and the effectiveness of the FSA‐Shared_Nadam head pose estimation algorithm and the proposed face quality assessment approach is demonstrated.
- WTEC: a wavelet transform–based image exposure correction method1
A wavelet transform–based image exposure correction method that processes images in the frequency domain instead of the spatial domain and corrects underexposed and overexposed images simultaneously.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Dexamethasone and MicroRNA-204 Inhibit Corneal Neovascularization1
The role of Dex in attenuating CNV may be partly attributed to miR-204, a potential therapeutic target in alkali burn-induced CNV, which was investigated in human mammary epithelial cells in vitro and in HMECs in vitro.
- 1
- 1
- 1
- 1
- 1
- Determination of the Data Model for Heterogeneous Data Processing Based on Cost Estimation1
A model determination method based on cost estimation evaluates the execution cost of query tasks on different data models, which taken as the criterion to measure the data model, and chooses a data model with the least cost as the intermediate representation during data processing.
- 1
- 1
- 1
- 1
- 1
- 1
- MR Image Reconstruction from Undersampled k-Space with Bayesian Dictionary Learning1
An algorithm for reconstructing magnetic resona nce images (MRI) from highly undersampledk-space data is developed and the beta-Bernoulli process is used as a Bayesian prior for dictionary learning, which adaptively infers the dictionary size, the sparsity of each patch and the noise parameters.
- 1
- The Application of Magnetic Sensors in Self-Contained Local Positioning1
GPS relies on complicated infrastructure and cannot provide sufficient accuracy, stability and coverage for environments such as indoors and highly urbanized areas (known as “urban canyon”) due to the lack of lineof-sight (LOS) to the satellites of GPS.
- 1
- Application of modulation transfer function in high-resolution image fusion1
The results show that fusion images derived from the improved high frequency modulation based on MTF method have spatial resolution close to non-degraded pan images.
- Preface to the special issue on new achievements in pervasive and interactive multimedia systems and applications1
One of the key issues is how to structure this universe of devices and applications, without bothering users with an explicit awareness of the underlying communications and computing technologies, while guaranteeing to them a full control on the results.
- 1
- A New LUT Watermarking Scheme with Near Minimum Distortion Based on the Statistical Modeling in the Wavelet Domain1
A new wavelet domain look-up table (LUT) watermarking algorithm that leads to the sub-optimal embedding of watermarks in the sense of minimizing distortion and provides a joint distortion-robustness design of the LUT based watermark.
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- Sample-Efficient Diffusion-based Control of Complex Physics Systems–
This paper presents SEDC (Sample-Efficient Diffusion-based Control), a novel diffusion-based control framework addressing three core challenges: high-dimensional state-action spaces, nonlinear system dynamics, and the gap between non-optimal training data and near-optimal control solutions.
- –
- –
- –
- Harnessing Tullock Contests and Signaling Games: A Novel Weight Assignment Strategy for Ethereum 2.0–
An innovative mechanism that combines Tullock contests and signaling games to optimize weight assignments based on security deposits from heterogeneous nodes is introduced, which significantly outperforms existing methods and yields marked improvements in user participation rates and service coverage.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- The First and Second-Order Asymptotics of Covert Communication over AWGN Channels–
The optimality of Gaussian distribution for minimizing KL divergence under the second order moment constraint is extended from dimension $1$ to dimension $n$, which further leads to the direct converse bound in terms of covert metric.
- –
- –
- –
- –
- Granulation multi-label decision tables and three-level granulation attribute reductions of multi-label decision tables–
The reasonability, feasibility and effectiveness of the granulation attribute reduction are demonstrated and it is shown that a complementary decision reduction of a multi-label decision table can be seen as a macroscopic-level granulations attribute reduction and thus it can be interpreted as a positive region reduction.
- –
- Tao-Hong-Si-Wu Decoction improves depressive symptoms in model rats via restorations of neural transmitters and ameliorations of BDNF-CREB-arginase I axis disorders–
TSD improves depression-like symptoms in CUMS rats, which may be primarily related to its effect both on enhancing the release of neural transmitters such as glycine and serotonin and on the improvement of disorders of the BNDF-CREB-Arg I axis.
- New Closed-form Joint Localization and Synchronization using Sequential TOAs in a Multi-agent System–
- –
- Analysis of clinical prognostic factors in bladder cancer-associated double primary cancer–
The incidence of DPC associated with bladder cancer is positively correlated with the history of smoking, radiotherapy, and intravenous chemotherapy, and dynamic monitoring of changes in SII, NLR, PLR and PNI after treatment of the first primary cancer is helpful to evaluate the risk of D PC in patients.
- –
- Research of an Autonomous Path Planning Algorithm in the Dynamic Target Tracking–
The algorithm is redesigned according to operant conditioning principle, and the rationality of the algorithm in dynamic target tracking is proved.
- –
- Monocular Visual-Inertial State Initialization for Micro Aerial Vehicles–
A robust initialization algorithm to provide high-quality initial guess for the monocular visual-inertial system (VINS) and takes the up-to-scale camera poses estimated by monocular vision-only SLAM and the IMU sensor measuements as input.
- Monocular Visual-Inertial State Estimation for Micro Aerial Vehicles–
A monocular visual-inertial algorithm for estimating the state of a MAV using the Semi-Direct Visual Odometry algorithm and an Error-state Kalman Filter was designed so that it can fuse the output of the SVO and IMU data to estimate the full state of the MAVs.
- Problems of snoring collection and nursing strategies of patiens with obstructive sleep apnea hypopnea syndrome–
To improve the efficiency of snoring collection, nursing intervention can be used to excluded objective factors and avoid subjective ones.
- –
- Correlation of Tibetan Plateau residents’ non-proliferative diabetic retinopathy, central retinal thickness and function–
The effects of central retinal thickness of function among high altitude Tibetan residents with non-proliferative diabetic retinopathy was observed and correlation between these were observed and analyzed.
- –
- –
- Constructional Coercion in the Evolution of Contemporary Chinese Morphemes—Taking “Fen”(粉) as an Example–
This paper takes the new Chinese morpheme “fen(粉)” as an example in order to analysis and explain the reason of its evolution using the theory of constructional coercion on the bases of a clear semantical evolutional trace.
- –
- –
- –
- –
- –
- Large Displacement Optical Flow with Adaptive Feature Match–
This paper presents an accurate large displacement optical flow estimation approach by adaptively integrate the local feature match and shows that the adaptive approach substantially decreases the computational cost by remove uncertain features and leads to more robust performance by excluding unreliable matches.
- Research on a New Path Planning Method for Mobile Robot–
A new hybrid learning method is proposed, which is based on the fuzzy inference system and assisted by the combination of supervised learning and bionic automata, that avoids the expert knowledge’s disadvantage of inaccurate estimation to the actual model.
- 1D Infrared Camera Distortion Based on Polynomial Model–
A novel method is proposed for 1D infrared camera distortion based on polynomial model that derives a 1D camera calibration algorithm and then estimates the distortion parameters by means of minimum calibration error.
- Pre-clinical evaluation of a new indirectly labeled ⁹⁹mTc-6-hydrazinopyridine-3-carboxylic acid (HYNIC)-depreotide with HYNIC as bifunctional chelator.–
The findings suggested that the new (99m)Tc-HYNIC-depreotide might be a promising candidate radiopharmaceutical for imaging somatostatin receptor positive lung cancer.
- A Fast Sub-Volume Search Method for Human Action Detection–
A new graph based representation for the search space in a video is introduced and a novel sub-volume search method by Minimum Cycle detection is proposed, which has a low computation complexity while maintaining a high action detection accuracy.
- –
- –
- Graphical probabilistic modeling and applications in multimedia content analysis–
This half-day tutorial introduces the fundamentals of graphical probabilistic modeling, including Bayesian networks, Markov random fields, hidden conditional Random field, etc.
- Improving the Accuracy and Efficiency of CBA Algorithm–
The improved CBA algorithm applies rough set theory to reduce attributes, and prune candidate rules with PEP method, and it has higher accuracy than CBA and C4.5.
- –
- –
- –
- –
- –
- VIDEOEVENT DETECTION USINGICAMIXTURE HIDDEN MARKOV MODELS JianZhou–
The proposed method caneffectively detect semantic video events and exploit the spatial and temporal characteristics of the training data.
- –
- –
- –
- Object extraction in video sequences based on the spatio-temporal independent component analysis–
A novel technique is developed to extract objects from video sequences based on spatiotemporal independent component analysis (stICA) and multiscale analysis and preliminary results demonstrate great potential for stICA based object extraction technique in content-based video processing applications.
- –
- Soft Search and Stepwise Selection: A New Strategy for LOINC Mapping.–
The soft search and stepwise selection strategy used for Loinc mapping is described and the rationale for this strategy is explained.
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.