Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Chun ChenSuggested from co-authorship
- Xuelong LiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works235 from public data
- 297
- Fortune Teller: Predicting Your Career Path258
This work scientifically and systematically study the feasibility of career path prediction from social network data and seamlessly fuse information from multiple social networks to comprehensively describe a user and characterize progressive properties of his or her career path.
- Representative Discovery of Structure Cues for Weakly-Supervised Image Segmentation240
Experimental results show that the proposed approach outperforms state-of-the-art weakly-supervised image segmentation methods, on five popular segmentation data sets and performs competitively to the fully- supervised segmentation models.
- 233
- 206
- 196
- 181
- Fusion of Multichannel Local and Global Structural Cues for Photo Aesthetics Evaluation172
A new photo aesthetics evaluation framework is proposed, focusing on learning the image descriptors that characterize local and global structural aesthetics from multiple visual channels, which significantly outperforms state-of-the-art algorithms in photo aesthetics prediction.
- GMove162
This work proposes GMove, a group-level mobility modeling method using GeoSM data that alternates between user grouping and mobility modeling, and generates an ensemble of Hidden Markov Models (HMMs) to characterize group- level movement regularity.
- 159
- The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers150
This survey focuses on algebraic word problems, summarize their extracted features and proposed techniques to bridge the semantic gap, and compare their performance in the publicly accessible datasets.
- A Probabilistic Associative Model for Segmenting Weakly Supervised Images146
This paper proposes a new weakly supervised image segmentation model, focusing on learning the semantic associations between superpixel sets (graphlets in this paper), and presents a hierarchical Bayesian network to capture the semantic association between postembedding graphlets.
- 145
- A Fine-Grained Image Categorization System by Cellet-Encoded Spatial Pyramid Modeling144
A new fine-grained image categorization system that improves spatial pyramid matching is developed that outperforms the state of the art and can be conducted with a trained linear support vector machine.
- Exploring global diverse attention via pairwise temporal relation for video summarization135
An efficient convolutional neural network architecture for video SUMmarization via Global Diverse Attention called SUM-GDA, which adapts attention mechanism in a global perspective to consider pairwise temporal relations of video frames, is proposed.
- 127
- Beyond Doctors121
An adaptive multimodal multi-task learning model is proposed to co-regularize the modality agreement, temporal progression and discriminative capabilities of different modalities of Alzheimer's disease and is theoretically show that it is a linear system.
- 119
- Multiple Social Network Learning and Its Application in Volunteerism Tendency Prediction103
A novel model for data missing completion is proposed that is applicable to many other domains, such as demographic inference and interest prediction, and a robust multiple social network learning model is developed and applied to the application of volunteerism tendency prediction.
- Modeling Disease Progression via Multisource Multitask Learners: A Case Study With Alzheimer’s Disease99
A novel and unified scheme to coregularize the prior knowledge of source consistency and temporal smoothness of chronic disease progression is proposed and theoretically proves that the proposed model is a linear model.
- Prediction of prognosis in elderly patients with sepsis based on machine learning (random survival forest)98
A prognostic model to predict a 30-day mortality risk in elderly patients with sepsis based on machine learning (RSF algorithm), and it proved superior to the traditional scoring systems.
- 98
- Actively Learning Human Gaze Shifting Paths for Semantics-Aware Photo Cropping96
Semantics-aware photo cropping is proposed, which crops a photo by simulating the process of humans sequentially perceiving semantically important regions of a photo, and the cropped photos produced by the approach outperform its competitors in both qualitative and quantitative comparisons.
- A mix-pooling CNN architecture with FCRF for brain tumor segmentation94
A two-pathway model with average and max pooling layers in different paths is designed and combined with fully connected CRF(FCRF) as a mixture model to introduce the global context information to optimize prediction results.
- Risk factor analysis and nomogram for predicting in-hospital mortality in ICU patients with sepsis and lung infection89
A nomogram prediction model was constructed to accurately evaluate the prognosis of and provide treatment advice for patients with sepsis and lung infection and revealed that it provided net benefits for clinical use over using the SOFA score and SAPSII in both sets.
- Recognizing architecture styles by hierarchical sparse coding of blocklets85
This work decomposes a building image into a collection of blocks, each representing a basic architecture component such as a stone pillar, and introduces blocklets that capture the morphological characteristics of buildings to form architecture style recognition as matching between blocklets extracted from different buildings.
- 84
- Spatial-Aware Object-Level Saliency Prediction by Learning Graphlet Hierarchies83
Experimental results demonstrate that the proposed oGLs and sGLs well capture object-level and spatial-level cues relating to saliency, and the resulting saliency model performs competitively compared with the state-of-the-art.
- 82
- 81
- Fast multi-view segment graph kernel for object classification75
Fast multi-view segment graph kernel (FMSGK) is proposed, which segments each object in terms of its color intensity distribution and computed the kernel between objects by accumulating all matchings' of walk structures between their corresponding multi- view segment graphs.
- Image Categorization by Learning a Propagated Graphlet Path74
This paper proposes to learn object-shaped and directional receptive fields for image categorization, and derives a manifold propagation to calculate the postembedding graphlets by leveraging visual saliency maps.
- Detecting Densely Distributed Graph Patterns for Fine-Grained Image Categorization70
A dense graph mining algorithm is developed to discover graphlets representative to each super-/sub-category, and the discovered graphlets from each sub-category accurately capture those tiny discriminative object components, e.g., bird claws, heads, and bodies.
- Adaptive Multimedia Data Forwarding for Privacy Preservation in Vehicular Ad-Hoc Networks69
Experimental results thoroughly demonstrate that the proposed CP-ABE delegation scheme is effective and efficient for multimedia data forwarding in vehicular ad-hoc networks with privacy preservation.
- 67
- 63
- Interest inference via structure-constrained multi-source multi-task learning61
A structure-constrained multi-source multitask learning scheme to co-regularize the source consistency and the tree-guided task relatedness and it is able to jointly learn the task-sharing and task-specific features.
- Accurate seat belt detection in road surveillance images based on CNN and SVM55
This work proposes a seat belt detection algorithm for complex road backgrounds based on multi-scale feature extraction using deep learning and performs well when applied to a database of images collected by road surveillance cameras.
- 51
- Robust Web Image Annotation via Exploring Multi-Facet and Structural Knowledge51
This paper proposes an effective and robust scheme, termed robust multi-view semi-supervised learning (RMSL), for facilitating image annotation task, and exploits both labeled images and unlabeled images to uncover the intrinsic data structural information.
- Developing an ensemble machine learning model for early prediction of sepsis-associated acute kidney injury47
An ensemble model for early prediction of S-AKI onset was developed and it demonstrated good performance in multicenter external datasets.
- Deep Active Learning with Contaminated Tags for Image Aesthetics Assessment47
A novel semi-supervised deep active learning (SDAL) algorithm is proposed, which discovers how humans perceive semantically important regions from a large quantity of images partially assigned with contaminated tags, and a probabilistic model is developed for image aesthetics assessment.
- Feature selection for fast speech emotion recognition46
A novel feature selection (FSalgorithm) to filter out the low efficiency features towards fast speech emotion recognition by mapping the original feature space into a nonlinear one to select nonlinear features, which can exploit the underlying relationship among the original features.
- 45
- Developing an explainable machine learning model to predict the mechanical ventilation duration of patients with ARDS in intensive care units44
ML models with features at MV initiation can accurate predict mechanical ventilation duration in patients with ARDS in ICUs using the machine learning (ML) approach.
- 44
- Weakly Supervised Human Fixations Prediction43
This paper proposes weakly supervisedfixations prediction, which leverages image labels to improve accuracy of human fixations prediction and proposes spatial-level graphlets (sGLs) to model the relative positions among objects.
- Large-Scale Aerial Image Categorization Using a Multitask Topological Codebook42
This work proposes an efficient aerial image categorization algorithm that focuses on learning a discriminative topological codebook of aerial images under a multitask learning framework and is competitive to several existing recognition models.
- A ROI-guided deep architecture for robust facial expressions recognition40
A robust facial expression recognition framework, focusing on discovering the region of interest (ROI) to train an effective face-specific of convolutional neural networks (CNN) by exploiting the relationships among ROI areas, which can improve the reliability of predicted targets.
- Influence of fluid balance on the prognosis of patients with sepsis39
Positive fluid balances on days 1, 2, and 3 after sepsis diagnosis were associated with poor prognosis with the HRs of 1.29, 1.13, and 1.25, while the fluid balance on days 4 and 5 had no effect on the primary outcome.
- The relationship between hematocrit and serum albumin levels difference and mortality in elderly sepsis patients in intensive care units—a retrospective study based on two large database38
HCT-ALB is simple and easy to obtain and is a promising clinical predictor of early risk stratification for elderly sepsis patients in ICU and ICU/hospital mortality in the eICU-CRD database after multivariable adjustment.
- Establishment of a prognostic model for patients with sepsis based on SOFA: a retrospective cohort study35
A nomogram was established that performed better than the SOFA in predicting 30-, 60- and 90-day mortality risk in patients with sepsis, and the C-index, AUC, NRI, IDI, and DCA of the nomogram showed that it performs better thanThe SOFA alone.
- Influence of the trajectory of the urine output for 24 h on the occurrence of AKI in patients with sepsis in intensive care unit35
The outcome of this study is AKI that occurs 24 h after sepsis, and close attention should be paid to changes in the patient's urine output to prevent the occurrence of S-AKI.
- Semantic Photo Retargeting Under Noisy Image Labels35
A new semantically aware photo retargeting that shrinks a photo according to region semantics and a probabilistic model is proposed to enforce the spatial layout of a retargeted photo to be maximally similar to those from the training photos.
- 34
- Learning a Probabilistic Topology Discovering Model for Scene Categorization34
This paper mine a discriminative topology and a low-redundant topology from the local descriptors under a probabilistic perspective, which are further integrated into a boosting framework for scene categorization.
- Multiview and Multimodal Pervasive Indoor Localization33
This paper addresses the deficiency of using a single measurement by proposing the original idea of localization based on multi-view and multi-modal measurements, and constructs a benchmark dataset for the PIL task, which to this knowledge is the first public dataset that is tailored for multi-View multi- modal indoor localization and contains both magnetic and visual signals.
- Weakly Supervised Multilabel Clustering and its Applications in Computer Vision33
This paper proposes weakly supervised multilabel clustering, which allows assigning multiple labels to a bag and a deterministic annealing strategy is developed to optimize the nonconvex objective function.
- 32
- Analysis of the correlation between the longitudinal trajectory of SOFA scores and prognosis in patients with sepsis at 72 hour after admission based on group trajectory modeling31
Group-based trajectory modeling may help identify various groups of patients with sepsis, who may be at different levels of risk for adverse health outcomes, and provide subgroups with clinical importance.
- 31
- Learning User Attributes via Mobile Social Multimedia Analytics31
A unified model is proposed to jointly regularize the source consistency and graph-constrained relatedness among tasks and is able to learn the attribute-specific and attribute-sharing features via graph-guided fused lasso penalty.
- Integrating 3D structure into traffic scene understanding with RGB-D data31
Experimental results show that integrating depth data can improve the accuracy of object detection and recognition, and that the analyzed object information plus depth data facilitate two important traffic event detection applications: overtaking warning and collision avoidance.
- 30
- Weakly Supervised Multimodal Kernel for Categorizing Aerial Photographs30
A new image kernel is proposed for effectively recognizing aerial photographs, to encode high-level semantic cues into local image patches in a weakly supervised way, and integrate multimodal visual features using a newly developed hashing algorithm.
- 29
- Music recommendation using graph based quality model29
This paper proposes a music recommendation framework based on graph based quality model to make fine-grained music recommendation, and proves that the framework is better than traditional song recommendation algorithms.
- Perceptually Aware Image Retargeting for Mobile Devices28
This paper proposes a novel retargeting framework that rapidly shrinks a photograph/video by leveraging human gaze behavior, and derives a geometry-preserving graph ranking algorithm that efficiently selects a few salient object patches to mimic the human gaze shifting path (GSP) when viewing a scene.
- 28
- Effects of Stress Hyperglycemia on Short-Term Prognosis of Patients Without Diabetes Mellitus in Coronary Care Unit27
Severe stress hyperglycemia (≥200 mg/dL) in patients without DM in CCU may increase the risk of short-term death, which is greater than the prognostic effect in patients with diabetes.
- Construction and Evaluation of a Sepsis Risk Prediction Model for Urinary Tract Infection26
The independent risk factors for sepsis in UTI patients were congestive heart failure, diabetes, liver disease, fluid electrolyte disorders, APSIII, neutrophils, lymphocytes, red blood cell distribution width, urinary protein, urinary blood, and microorganisms.
- 26
- 26
- Influence of systolic blood pressure trajectory on in-hospital mortality in patients with sepsis25
Maintaining a systolic blood pressure of approximately 140 mmHg in patients with sepsis within 10 h of admission was associated with a lower risk of in-hospital mortality.
- Bone mesenchymal stem cell-derived extracellular vesicles inhibit DAPK1-mediated inflammation by delivering miR-191 to macrophages25
Evidence is found that primary human bone mesenchymal stem cell (BMSC)-derived extracellular vesicles (EVs) antagonize LPS-induced inflammation in the THP-1 human macrophage-like cell line and highlights BMSC-derived EVs as a potential vehicle to deliver biomacromolecules to macrophages.
- An efficient message access quality model in vehicular communication networks25
A hierarchical message access quality model in VANET which is scalable and efficient in dynamic vehicular communication environment and achieves fine-grained access control among various types of vehicles using well defined attributes is proposed.
- Associations of air pollution with all-cause dementia, Alzheimer’s disease, and vascular dementia: a prospective cohort study based on 437,932 participants from the UK biobank24
Air pollution is associated with the risk of all-cause dementia, Alzheimer’s disease (AD), and vascular dementia, and the combined effect of air pollution and Alzheimer's disease genetic risk score (AD-GRS) on the development of AD is examined using a Cox proportional hazards model.
- The association between continuous renal replacement therapy as treatment for sepsis-associated acute kidney injury and trend of lactate trajectory as risk factor of 28-day mortality in intensive care units24
There was no significant association betweenCRRT use and 28-day survival in S-AKI patients, and JM showed that CRRT use might be associated with elevation of longitudinal lactate levels.
- Constrained Low-Rank Learning Using Least Squares-Based Regularization24
This paper aims to learn both the discriminant low-rank representation (LRR) and the robust projecting subspace in a supervised manner and proposes a novel constrained LRR method formulated as a constrained nuclear norm minimization problem, which can be solved by the inexact augmented Lagrange multiplier algorithm.
- Grassmann multimodal implicit feature selection24
A new multimodal feature selection algorithm, termed Grassmann manifold feature selection (GMFS), is proposed, which proposes supervised/unsupervised feature selection algorithms to achieve a physically meaningful embedding of the multi-feature features.
- Discriminative Cellets Discovery for Fine-Grained Image Categories Retrieval23
A new fine-grained image categorization model that can be deemed as an improved version spatial pyramid matching (SPM) is proposed that outperforms the state-of-the-art and describes object components by cellets that connect spatially adjacent cells from the same pyramid level.
- 23
- 22
- A New Scoring System for Predicting In-hospital Death in Patients Having Liver Cirrhosis With Esophageal Varices21
The first prognostic nomogram for predicting the in-hospital death of LCEV patients is established, which is easy to use, performs well, and can be used to guide clinical practice, but further external prospective validation is still required.
- FastShrinkage21
A novel retargeting framework which fast shrinks photo/video by leveraging human gaze behavior, and the retargeted photos/videos produced by the method outperform its competitors significantly based on the paired-comparison-based user study.
- 19
- 19
- Vehicles overtaking detection using RGB-D data19
A vehicles overtaking detection method using RGB-D data captured by the Kinect device in simulated traffic scenes and an efficient vehicle tracking algorithm for overtaking judgment is implemented.
- 18
- Jointly social grouping and identification in visual dynamics with causality-induced hierarchical Bayesian model18
A causality-induced hierarchical Bayesian model to tackle the interaction activity video, referring to the “what” interaction activities happen, “where’ interaction atomic occurs in spatial, and “when” group interaction happens in temporal is proposed.
- Multi-source alert data understanding for security semantic discovery based on rough set theory18
A multi-source alert data understanding scheme based on rough set theory for security semantic discovery that could reduce more than 80% repetitive alerts in the data sets.
- A classification model for semantic entailment recognition with feature combination17
A classification model is constructed based on support vector machine to detect high-level semantic entailment relations in Chinese text pair, including entailment and non-entailment for the Binary-Class and forward entailment, reverse entailsment, bidirectional entailments, contradiction and independence for the Multi-Class.
- 17
- Context-Aware Recommendation Using Role-Based Trust Network17
A term role is defined to model common context-aware interests among a group of users and an efficient role mining algorithm to mine roles from a “user-context-behavior” matrix, and a role-based trust model is proposed to calculate context- aware trust value between two users.
- 17
- 16
- Spatiotemporal Activity Modeling Under Data Scarcity: A Graph-Regularized Cross-Modal Embedding Approach15
BranchNet, a spatiotemporal activity model that transfers knowledge from external sources for alleviating data scarcity, is proposed, which adopts a graph-regularized cross-modal embedding framework and is capable of effectively transferring knowledge from External sources to learn better spatiotmporal activity models and outperforming strong baseline methods.
- Perceptual multi-channel visual feature fusion for scene categorization15
This work designs a weakly supervised embedding algorithm which projects the local image features of graphlets onto the pre-defined semantic space, and formulates a sparsity-constrained graphlet ranking algorithm which incorporates visual clues at both the low-level and the high-level.
- HyperSSR: A hypergraph based semi-supervised ranking method for visual search reranking15
This paper proposes a hypergraph based semi-supervised ranking method called HyperSSR for image search reranking that jointly incorporate the hypergraph regularizer and the prior pairwise preferences information into a unified ranking learning framework.
- 15
- Perceptually Guided Photo Retargeting15
Perceptually guided photo retargeting, which shrinks a photo by simulating a human's process of sequentially perceiving visually/semantically important regions in a photo, is proposed, which outperforms its competitors significantly and AGP is more indicative of photo esthetics than conventional saliency maps.
- 15
- Early prediction of in-hospital mortality in patients with congestive heart failure in intensive care unit: a retrospective observational cohort study14
The novel nomogram, which included age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, accurately predicted the in-hospital mortality of patients with CHF.
- 14
- Empirical risk minimization for metric learning using privileged information14
An effective metric learning method is proposed by exploiting privileged information to relax the fixed threshold under the empirical risk minimization framework and jointly learn two distance metrics by minimizing the empirical loss penalizing the difference between the distance in the original space and that in the privileged space.
- 13
- Describing Human Aesthetic Perception by Deeply-learned Attributes from Flickr.13
A deep architecture to learn aesthetically-relevant visual attributes from Flickr, which are localized by multiple textual attributes in a weakly-supervised setting, is developed and applied on image retargeting, aesthetics ranking, and retrieval.
- Recognizing multi-view objects with occlusions using a deep architecture13
This approach constructs a multi-view shape model based on 3D objects by using an encode-decode deep learning network to represent the features and demonstrates that this approach can significantly improve the efficiency of feature representation and the performance of object recognition with occlusion.
- Fine-Grained Image Categorization by Localizing TinyObject Parts from Unannotated Images13
A novel fine-grained image categorization model where no object annotation is required in the training/testing stage, and a dense graph mining algorithm is developed to discover graphlets representative to each sub- super-category.
- Effects of growth trajectory of shock index within 24 h on the prognosis of patients with sepsis12
Both initial SI and trajectory of SI were found to be independent factors that affect the prognosis of patients with sepsis and should be closely monitored to arrive at appropriate clinical decisions on basis of their change trajectory.
- 12
- 12
- 12
- 11
- Green H2O-Promoted Solvent-Free Synthesis of Enaminocarbonyl Compounds with High Stereoselectivity from Electron-Deficient Terminal Alkynes11
A green H2O-promoted solvent-free hydroamination of electron-deficient terminal alkynes with amines has been developed and all secondary amines gave the corresponding (E)-enamines in good to excellent yields, whereas primary aromatic amines afforded Z-configured products in moderate yields.
- 11
- Recognizing semantic correlation in image-text weibo via feature space mapping11
The experimental results show that the accuracy of the recognition model for semantic correlation between image and text in image-text weibo, with feature space mapping and support vector machine using the three types of multi-source features, achieves a significant performance compared to the traditional model only based on support Vector machine.
- Toward solving the Steiner travelling salesman problem on urban road maps using the branch decomposition of graphs11
A branch decomposition-based extraction algorithm for the Steiner travelling salesman problem in planar graphs that can solve the STSP in a planar graph G with a time complexity of 2O(bw(G))nO(1), where bw ( G ) is the branchwidth of G.
- Pedestrian detection by learning a mixture mask model and its implementation11
This paper proposes a high-level human-specific descriptor for detecting pedestrians in multiple videos by obtaining the feature matrix from a sliding window and using multiple mapping vectors to project the original feature matrix into different mask spaces.
- Integrating Local Features into Discriminative Graphlets for Scene Classification11
Geometric Local Features Integration (GLFI) is proposed, by segmenting a scene image into a set of regions, a so-called Region Adjacency Graph (RAG) is constructed to model their spatial relations.
- Effects of Gastric Acid Secretion Inhibitors for Ventilator-Associated Pneumonia10
PPIs did not have a significant association with either VAP or in-hospital mortality; the combination of H2RAs and PPIs was risk factor for VAP, but did not has a significantly associated with in- hospital mortality.
- Thiamine May Be Beneficial for Patients With Ventilator-Associated Pneumonia in the Intensive Care Unit: A Retrospective Study Based on the MIMIC-IV Database10
Thiamine supplementation may reduce ICU and in-hospital mortality in patients with VAP in the ICU, and so further clinical trials should be conducted to provide more-solid evidence on whether it improves the prognosis of patients withVAP.
- 10
- Online Robust Low-Rank Tensor Learning10
This paper proposes an Online Robust Lowrank Tensor Modeling (ORLTM) approach, which dynamically explores the high-order correlations across all tensor modes for low-rank structure modeling and introduces a new dictionary learning component to analyze mixture data from multiple subspaces.
- 9
- 9
- A Hierarchical Intrusion Detection System Based on Machine Learning9
This paper uses and analyzes the CIC-IDS series datasets and proposes a hierarchical detection model, which has shown that the stratified detection module has good classification accuracy for attack types with a small sample size.
- The Association Between Bronchoscopy and the Prognoses of Patients With Ventilator-Associated Pneumonia in Intensive Care Units: A Retrospective Study Based on the MIMIC-IV Database9
Bronchoscopy during IMV was associated with reducing the risk of ICU and in-hospital mortality in patients with VAP in ICUs, and this beneficial effect was partially mediated by changes in RDW levels.
- The Role of Glucocorticoids in the Treatment of ARDS: A Multicenter Retrospective Study Based on the eICU Collaborative Research Database9
Rational use of GCs can reduce the ICU mortality of ARDS patients in ICU and MSCM results also show thatGCs can improve the prognosis of patients.
- RETRACTED ARTICLE: Real-time eye detection in multimedia environment9
This paper proposes a simple method only with a webcam to realize real-time eye detection, which converts eyes’ image to grayscale image in order to post-processing and uses Gaussian smoothing and Histogram equalization to enhance contrast.
- Exploring Web Images to Enhance Skin Disease Analysis Under A Computer Vision Framework9
A novel transfer learning model is presented, which is able to incorporate external knowledge obtained from the rich and relevant Web images contributed by grassroots, and is easily repeatable by other researchers and extendable to other disease types.
- 9
- Effect of early vasopressin combined with norepinephrine on short-term mortality in septic shock: A retrospective study based on the MIMIC-IV database8
There was no difference in short-term mortality between early AVP combined with norepinephrine and nonearly AVP with NE in septic shock.
- 8
- 8
- 8
- Relationship between the magnitude of haemoglobin changes and long-term mortality in patients with sepsis: a retrospective cohort study7
A 7% decrease in HGB levels on Day 4 after admission was associated with worse long-term prognosis in sepsis patients admitted to the ICU, and the correlation between early temporal changes in HGB levels and long-term mortality rates in septic patients was studied.
- 7
- Association of acetaminophen use with mortality and renal recovery in patients with sepsis-associated acute kidney injury7
Acetaminophen use is associated with decreased mortality and improved renal recovery in SA-AKI patients and was associated with improved renal recovery in SA-AKI patients.
- Blocking the ADAM9 / ITGAV Pathway Ameliorates Sepsis‐Induced Acute Lung Injury by Promoting Macrophage Efferocytosis6
In the lipopolysaccharide‐induced ALI mice, inhibiting ADAM9 in macrophages significantly improved ALI, simultaneously reducing the number of macrophages and neutrophils in BALF, along with a decrease in pro‐inflammatory cytokines, including IFN‐γ, iNOS and an increase in IL‐4, IL‐10.
- 6
- The Timing of Initiating Hydrocortisone and Long-term Mortality in Septic Shock6
In patients with septic shock, initiating hydrocortisone >12 hours after vasopressor use was associated with an increased risk of both short-term and long-term mortality, and a prolonged length of hospital stay.
- Special issue on weakly supervised learning6
This dissertation aims to provide a history of web exceptionalism from 1989 to 2002, a period chosen in order to explore its roots as well as specific cases up to and including the year in which descriptions of “Web 2.0” began to circulate.
- Abutilon theophrasti Medic . : A Review of its Traditional Uses, Phytochemistry, Pharmacology, and Pharmacokinetics5
An up-to-date research on the traditional uses, phytochemistry, pharmacology, and pharmacokinetics of A. theophrasti is provided to explore its clinical therapeutic potential.
- 5
- Effect of First Trough Vancomycin Concentration on the Occurrence of AKI in Critically Ill Patients: A Retrospective Study of the MIMIC-IV Database5
FVTC is associated with the occurrence of AKI and increased ICU and in-hospital mortality in critically ill patients and patients in intensive care settings receiving vancomycin should be closely monitored for FVTC to prevent drug-related nephrotoxicity and reduce patient mortality.
- Influence of ambulatory blood pressure-related indicators within 24 h on in-hospital death in sepsis patients5
Investigation of indicators related to the ambulatory blood pressure within 24 h found that attention should be paid to BPV and the circadian rhythm in order to improve the prognosis and the survival rate of sepsis patients.
- 5
- 5
- 5
- 4
- 4
- Norepinephrine combined with phenylephrine versus norepinephrine in patients with septic shock: a retrospective cohort study4
NE combined with PE was inferior to NE alone in patients with septic shock, and it was associated with a higher hospital mortality rate.
- Malignant cancer may increase the risk of all-cause in-hospital mortality in patients with acute myocardial infarction: a multicenter retrospective study of two large public databases4
Among the patients with AMI, the all-cause in-hospital mortality risk of those with cancer was higher than those without cancer, and comprehensive considerations should be made from a multidisciplinary perspective involving cardiology and oncology, with the treatment plan adjusted accordingly.
- Pre-intensive care unit use of selective serotonin reuptake inhibitors and mortality in critically ill adults with mental disorders: analysis from the MIMIC-IV database4
Pre-ICU use of SSRIs is associated with an increase in the hazard for in-hospital mortality in critically ill adults with mental disorders.
- 4
- Association between statin use and the prognosis of patients with acute myocardial infarction complicated with diabetes4
Even in the population without hyperlipidemia, statins can still reduce the mortality in patients with AMI and diabetes, and Kaplan-Meier survival curves demonstrated that survival probability was higher in the statin group than in the non-statin group.
- 4
- 4
- 4
- 4
- RETRACTED ARTICLE: Moving object surveillance using object proposals and background prior prediction4
A moving object detection algorithm is combined with a background estimate and a Bing (Binary Norm Gradient) object is proposed in video surveillance and can not only achieve high detection rate (DR), but also reduce false alarm rate (FAR) and time cost.
- 4
- 3
- Hybrid image super-resolution using perceptual similarity from pre-trained network3
This paper proposes a hybrid method for image SR that exploits the complementary advantages of external and internal SR methods, and calculates the perceptual similarity between the feature representations from the pre-trained VGG network to learn an adaptive weight.
- 3
- RETRACTED: Moving object surveillance using object proposals and background prior prediction3
A moving object detection algorithm is combined with a background estimate and a Bing (Binary Norm Gradient) object is proposed in video surveillance and can not only achieve high detection rate (DR), but also reduce false alarm rate (FAR) and time cost.
- Sparse Code Filtering for Action Pattern Mining3
This paper proposes a sparse code filtering (SCF) framework which can mine the action patterns of multi-view action recognition by integrating the classifiers and the class-wise sparse coding process into a collaborative filtering (CF) framework to mine the discriminative sparse codes and classifiers jointly.
- Mining location-aware discriminative blocklets for recognizing landmark architectures3
This work proposes a location-aware building recognition model by introducing blocklets, i.e., spatial adjacent blocks associated with their relative positions that is robust to occlusions and large change in backgrounds.
- Points of Interest Detection from Multiple Sensor-Rich Videos in Geo-Space3
This work proposes a probability model to formulate the capture intention distribution for video frames and detects POIs by considering the contributions from multiple videos, demonstrating that the algorithm successfully detects POI with a reduced error distance from several dozens to a few meters.
- 2
- 2
- 2
- 2
- 2
- 2
- Interactive Rare-Category-of-Interest Mining from Large Datasets2
A new model named IRim is contributed, which can interactively mine rare category data examples of interest over large datasets and achieves the response time in seconds for user interactions, and outperforms state-of-the-art competitors significantly in accuracy and number of queries.
- Can modified minimax win in Pearl’s game?2
This research proposes a possible way to fix the pathology of Minimax by taking the opponent’s strategy into consideration in some specific cases and overcomes the pathology.
- Exploiting Spatial Relationship between Scenes for Hierarchical Video Geotagging2
The Spatial Relationship Model (SRM) for geotagging is presented which integrates the geo-spatial relationship of scenes into a hierarchical framework and segment the Earth's surface into multiple levels of grids and measure the likelihood of input videos with an adaptation to region granularities.
- Large-Scale Aerial Image Categorization by Multi-Task Discriminative Topologies Discovery2
This work proposes an efficient aerial image categorization system, aiming at mining discriminative topologies of aerial images under a multi-task learning framework, and integrates it into an AdaBoost model for predicting aerial image categories.
- Feature Relationships Hypergraph for Multimodal Recognition2
A so-called Feature Relationships Hypergraph (FRH) is proposed to model the high-order correlations among the multimodal features and a multi-class boosting strategy is developed to obtain a strong classifier by combining the weak classifiers learned from the intra- partition matrices.
- kPose: A New Representation For Action Recognition2
This work presents a novel action recognition approach by describing the action with a few frames of representative poses, namely kPose, based on a newly proposed Pose-Weighted Distribution Model.
- 1
- 1
- N-Acetylserotonin Alleviates Retinal Autophagy via TrkB/AKT/Nrf2 Signaling Pathway in Retinal Ischemia-Reperfusion Injury Rats1
The administration of NAS activates the TrkB/Akt/Nrf2 signaling pathway, reduces autophagy, alleviates retinal edema, promotes the survival of retinal ganglion cells (RGCs), and provides neuroprotection against retinal injury in rats.
- Anti-embolism devices therapy to improve the ICU mortality rate of patients with acute myocardial infarction and type II diabetes mellitus1
Simple-AE-device therapy was associated with reduced risks of ICU mortality and 28-day mortality, as well as an improvement in the benefit on in-hospital survival in patients with AMI complicated with type II DM.
- Pelvic Injury Discriminative Model Based on Data Mining Algorithm.1
In the evaluation of pelvic injury, the pelvic injury data mining model based on CT images reaches high accuracy, which lays a foundation for automatic and rapid identification of pelvic injuries.
- An Adaptive Feature Recognition Algorithm and Its Hardware Accelerator for Arc Fault Recognition1
The experimental results show that the adaptive arc fault detection chip realizes the fault arc detection function and only has a low delay of about 15us after the traditional discrete wavelet transform algorithm is improved to a three-level adaptive feature processing algorithm.
- Visual Analysis of Urban Block Risk Based on Bayesian Network——Taking Traffic as an Example1
This paper focuses on urban traffic and public health emergencies, integrates disaster related data, constructs Bayesian network reasoning model, and uses spatial analysis technology to visualize risk information on dynamic map.
- 1
- Aerial Photograph Categorization by Cross-Resolution Deep Human Gaze Behavior Learning1
This work proposes a cross-domain aerial photograph categorization system by leveraging the low-resolution spatial composition to enhance the deep encoding of human gaze shifting path (GSP) with a high-resolution.
- Machine-Vision-Based Enhanced Deep Genetic Algorithm for Robot Action Analysis1
A robot species method (BAS-GA) that supports machine vision and improved genetic algorithm rules is proposed, and Experimental inference have shown that the BAS-GA algorithm rule achieves the optimal conclusion similar to the pseudo-annealing algorithmic program plant.
- Mean Arterial Pressure Should Above 65 mmHg at Vasopressor Weaning — Exploratory Study of Optimal Weaning Blood Pressure for Patients in Intensive Care Unit1
WMAP is a powerful indicator for in-hospital mortality, and its value should be greater than 65mmHg and close to 85 mmHg to reach the highest survival probability for ICU patients after vasopressor treatment.
- Impact of Continuous Renal Replacement Therapy as Treatment for Sepsis-Associated Acute Kidney Injury on Lactate Levels and the Risk of 28-Day Mortality in Intensive Care Units1
CRRT does not improve the prognosis of patients with sepsis and acute kidney injury in critical-care units and has a tendency of increasing lactate levels, which is a significant risk factor for the prog outlook.
- Establishment of a Highly Predictive Survival Nomogram For Patients With Sepsis: A Retrospective Cohort Study1
The net benefit of the nomogram is greater than the SOFA score for any predicted probability, both in the training set and in the validation set, indicating that it has a substantial net benefit in predicting 30-, 60- and 90-days survival rates.
- 1
- Efficient large-scale graph data optimization for intelligent video surveillance1
A comprehensive survey of recent studies to solve the problem of topology learning, Object appearance modeling and global activity understanding sparse camera network is presented and some of the current open Research issues are discussed.
- 1
- Utilizing Sensor-Social Cues to Localize Objects-of-Interest in Outdoor UGVs1
This paper proposes a novel framework for OOI recognition in outdoor UGVs to identify semantically important regions by leveraging geo-sensor and social data and deploying a spatial pyramid representation to describe social objects from images and OOIs from UgVs.
- Guest editors' introduction: Perception, Aesthetics, and Emotion in Multimedia Quality Modeling1
The articles featured in this special issue cover a wide range of applications based on multimodal quality models, such as human action retrieval, quality-model-based traffic analysis,quality-based image enhancement, and video summarization techniques.
- Multimodal quality model: New methods and applications1
This special issue targets the recent technical progresses on computational models for multimodal quality prediction, such as photo/video esthetic quality ranking and retargeting, and fosters focused attention on the new types of visual cues in computational quality models.
- Opponent and Feedback: Visual Attention Captured1
A new and effective saliency model which considers the inner opponent relationship of the image information and constructs the saliency map according to the optimal combination of these feedbacks by using the least square regression with constraints method.
- 1
- Describing Human Identity Using Attributes1
An attribute based description of human identity is introduced and the human identification based on voter-candidate scheme is carried out by taking into account of human outside of the training data, robust to view changes, attributes-loss and different backgrounds.
- –
- –
- –
- –
- –
- Association between blood pressure during vasopressor weaning and in-hospital survival: an analysis of vasopressor targets–
Higher blood pressures during vasopressor weaning are associated with longer in-hospital survival in ICU patients and the optimum pressure ranges are SBP, 110-150 mmHg; DBP, 60-85 mmH g; and MAP, 75-110 mmHG.
- –
- RETRACTED: Simulating human visual perception behaviors for video quality assessment–
Evidence of systematic manipulation of the publication process, including compromised peer review, is uncovered in this article, which was submitted as part of a guest-edited special section.
- RETRACTED: Mimicking human vision systems: deep-learning-based feature fusion for semantic image retrieval–
Evidence of systematic manipulation of the publication process, including compromised peer review, is uncovered in this article, submitted as part of a guest-edited special section.
- –
- Encoding Human Visual Perception Into Deep Hashing for Aerial Image Classification–
A novel image assortment model that personate each aerial image by optimally encoding a gaze shifting path (GSP), and the phantom copy of the progress classification is more accurate than its competitors, and the GSPs propagated by Alzheimer's patients are discriminative from those produced by typical observers, making the classification competitive.
- –
- –
- Corrigendum: Anti-embolism devices therapy to improve the ICU mortality rate of patients with acute myocardial infarction and type II diabetes mellitus–
This research presents a novel probabilistic approach to estimating the response of the immune system to laser-spot assisted, 3D image analysis of central nervous system injuries.
- –
- –
- –
- –
- –
- –
- Optimal Blood Pressure at Vasopressor Weaning in Intensive Care Units — What Are Targets of Blood Pressure Management?–
Higher vasopressor weaning blood pressure can significantly improve survival, and the best target WSBP, WDBP, WMAP is 120-160, 50-65, and >80 mmHg.
- –
- –
- Development and Validation of a 90-day Mortality Prediction Nomogram for AMI Patients: A Retrospective Cohort Study–
The results of this study indicated that age, troponinT, VT, VFI, MI_his, APS-III, bypass, and PCI were risk factors for 90-day mortality in AMI patients.
- Risk Factors and Clinical Characteristics of Catheter Line-associated Bloodstream Infection in MIMIC IV Database–
This study investigated independent risk factors for CLABSI and their association with in-hospital mortality and described the etiological characteristics, drug sensitivity, and the distribution of antibiotics used for treatment.
- –
- Gaze Shifting Kernel: Engineering Perceptually- Aware Features for Scene Categorization–
A novel gaze shifting kernel for scene image categorization is proposed, focusing on discovering the mechanism of humans perceiving visually/semantically salient regions in a scene.
- –
- [Development of an algorithm for wrist oscillometric blood pressure-measurement using singular value decomposition].–
Comparison of the results of SCFA with those of traditional curve fitting algorithm (TCFA) found that the proposed SCFA could be used to reduce the partial intrinsic interference and efficiently improve the accuracy of the ABP at wrist.
- Fast Multi-view Graph Kernels for Object Classification–
The experimental results on different datasets validate the effectiveness of the proposed Fast Multi-view Graph Kernel, which segments each view image into several regions and computed the kernel between objects by accumulating all matchings' of walk structures between corresponding multi-view region graphs.
- –
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 2026-10-12. 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.