Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks158 from public data
- Consumers' decisions in social commerce context: An empirical investigation496
It is demonstrated that both emotional and informational social support significantly affected consumers' trust and community commitment, which in turn exerted profound impacts on both social shopping and social sharing intention.
- 204
- 174
- 157
- Augmented Dual-Contrastive Aggregation Learning for Unsupervised Visible-Infrared Person Re-Identification143
A dual-path contrastive learning framework with two modality-specific memories is proposed to learn the intra-modality person representation, which significantly outperforms existing unsupervised methods under various settings, and even surpasses some supervised counterparts, facilitating VI-ReID to real-world deployment.
- 107
- 92
- Person re-identification with content and context re-ranking90
A novel and efficient re-ranking technque to solve the person re-identification problem in the surveillance application and can be divided into offline and online parts, where the majority of computation load is accomplished by the offline part and the online computation complexity is only proportional to the size of the gallery data set.
- 85
- 82
- 65
- Voronoi-based k-order neighbour relations for spatial analysis65
In this paper, the concept of k-order neighbours is developed and a Voronoi-based model is formed for this type of neighbours, resulting in the so-called Vor onoi k- order neighbours.
- 63
- 63
- 62
- 57
- Ranking Optimization for Person Re-identification via Similarity and Dissimilarity56
This paper proposes to use both similarity and dissimilarity cues in a ranking optimization framework for person re-identification, based on the phenomenon that the true match should not only be similar to theStrong similar samples of the probe but also dissimilar to the strong dissimilar samples.
- 43
- Federated Learning With Long-Tailed Data via Representation Unification and Classifier Rectification42
- A Transactional Model for Data Warehouse Maintenance42
TxnWrap is complementary to maintenance algorithms from the literature by removing concurrency issues from their consideration and proposes a multiversion concurrency control technique appropriate for loosely-coupled environments with autonomous sources.
- 36
- Specific Person Retrieval via Incomplete Text Description36
A specific attribute completion is conducted to enrich the original text query and generate a more expressive attribute vector and a pairwise-based metric learning is introduced for completed attribute vectors.
- Manifold Projection for Adversarial Defense on Face Recognition34
This paper proposes Adversarial Variational AutoEncoder (A-VAE), a novel framework to tackle off-manifold and on-Manifold adversarial images, and hypothesizes that both off- manifoldand on-manIFold attacks move the image away from the high probability region of image manifold.
- Poly(9,9′‐diheylfluorene carbazole) Functionalized with Reduced Graphene Oxide: Convenient Synthesis using Nitrogen‐Based Nucleophiles and Potential Applications in Optical Limiting33
This one-step "grafting-to" strategy could be used to obtain RGO-based materials with different applications and displayed excellent optical-limiting response, in which both nonlinear absorption and nonlinear scattering play important roles.
- When Pedestrian Detection Meets Nighttime Surveillance: A New Benchmark32
This paper builds a novel pedestrian detection dataset from the nighttime surveillance aspect, and compares the performances of state-of-the-art pedestrian detectors and reveals that the methods cannot solve all the challenging problems of NightSurveillance.
- 29
- 29
- 28
- 28
- 26
- 25
- 25
- On the performance of real-time multi-item request scheduling in data broadcast environments25
A novel algorithm that considers both request popularity and request timing requirement is proposed and the performance results of the simulation study show that the proposed algorithm is superior to other classical algorithms under a variety of circumstances.
- 24
- Event-based incremental updating of spatio-temporal database23
A new automatic (semi-automatic) incremental updating approach of spatio-temporal database (STDB) named as event-based incremental updating (E-BIU) is proposed and shown to be an efficient automatic updating approach for master STDB.
- 21
- Large-scale tissue histopathology image segmentation based on feature pyramid21
An image semantic segmentation algorithm based on feature Pyramid (ResNet50-GICN-GPP) is proposed that achieves 63% of the average segmentation accuracy on Camelyon16 and Gastric WSIs Data, compared with U-Net, FCN and SegNet which has 10~20% improvement, and fully demonstrates the effectiveness of this method in different types of cancer.
- Correlation Discrepancy Insight Network for Video Re-identification20
A novel correlation discrepancy insight network for video-based person ReID is proposed, which consists of an unsupervised correlation insight model for video purification and a discrepancy description network (DDN) for person representation that outperforms several state-of-the-art methods.
- Key Issues of Continuous Updating of Geo-spatial Databases20
A number of key problems to be solved in continuous updating of the multi-scale geo-spatial databases was discussed in this paper, such as the incremental data modelling of master databases, automatic registration of multi-resource remote sensed imageries and digitized maps.
- 18
- M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition17
This work designs a multi-task decoder with a rich set of supervisory signals, including the original contrastive learning head, a cross-modal classification head, a cross-modal masked language modeling head, and a visual classification head that adeptly satisfies the need for strong supervised performance within a multimodal framework.
- A mutual neighbor-based clustering method and its medical applications17
A novel clustering algorithm based on representative data objects derived from mutual neighbors to identify different shaped clusters that can effectively identify arbitrary-shaped clusters and disease types in comparing to the state-of-the-art clustering ones.
- Sparsity-Based Occlusion Handling Method for Person Re-identification17
A sparsity-based patch matching method using a sparse representation model to determine the occlusion state of each image patch, which is further utilized to adjust the weight of patch pairs in the feature matching process.
- 17
- BF-SAM: enhancing SAM through multi-modal fusion for fine-grained building function identification16
A multi-modal foundation model for BFI is proposed by fine-tuning a large visual model, Segment Anything Model (SAM), with multi-modal features related to urban functions, called BF-SAM, which harnesses the segmentation capability of SAM for building delineation and fuses it with multi-modal representation learning for functional identification through a novel multi-modal fine-tuning method for SAM.
- Generating Adversarial Examples for Static PE Malware Detector Based on Deep Reinforcement Learning16
A reinforcement learning environment based on gym-malware-mini is proposed through which adversarial examples are generated using DQN and A2C deep reinforcement learning algorithm to expose vulnerability of malware detection model and designing better malware detector.
- Listen, Look, and Find the One15
According to extensive experiments on the CSM-V dataset, the proposed multimodality person search framework outperforms the state-of-the-art methods and can retrieve all targets depending only on the facial features of the query portrait.
- 14
- 13
- Triglyceride-glucose index and hsCRP-to-albumin ratio as predictors of major adverse cardiovascular events in STEMI patients with hypertension11
It is demonstrated that the TyG index and hsCAR provide strong combined predictive power and the synergistic utilization offers a comprehensive approach to cardiovascular risk assessment.
- Vertex points are not enough: Monocular 3D object detection via intra- and inter-plane constraints11
A novel 3D monocular object detection method to improve the accuracy of detection objects with large differences in deformation by introducing the geometric constraints of the object 3D bounding box plane.
- Learning heterogeneous information network embeddings via relational triplet network11
The empirical results demonstrate that the proposed relational triplet network algorithm can obtain multiple types of representations and outperform other state-of-the-art methods in node classification and link prediction.
- 11
- Coupled Discriminant Multi-Manifold Analysis with Application to Low-Resolution Face Recognition11
Experimental results conducted on two standard face recognition databases demonstrate the superiority of the proposed coupled discriminant multi-manifold analysis (CDMMA).
- 11
- A QTM-based Algorithm for Generation of the Voronoi Diagram on a Sphere11
To efficiently store and analyse spatial data at a global scale, the digital expression of the Earth's data must be global, continuous and conjugate, i.e., a spherical dynamic data model is needed.
- 10
- 10
- Single image de-raining via clique recursive feedback mechanism10
A new rain removal network based on the clique recursive feedback mechanism is proposed, considering the interaction of the feature between different convolution layers, and constructing a residual clique block (RCB) to infer the local information, allowing the network to rectify the model parameters in RCB alternately.
- 9
- Grid Service Concurrency Control Protocol9
The Share and Compete (S&C) concurrency control protocol is proposed, which mainly solves resource conflicts between function equivalent services of the internal transaction in the grid real-time transaction model based on function equivalent service.
- 9
- 8
- 8
- Dynamic Texture Modeling Applied on Computer Vision Based Fire Recognition8
The algorithm proposed in this paper works on the second step of fire pixel classification, and parameters of the models are employed to determine the presence or absence of fire using the proposed recognition framework.
- Remote Sensing Image Generation From Audio7
A novel reranking audio-image translation method that maps the audio and image into a uniform feature space and adopts an audio- image matching network for every matched audio to generate a related image, and the most frequent image is voted as the final result.
- 7
- Global Contrast Based Salient Region Boundary Sampling for Action Recognition7
The iDT method is improved by advancing a novel salient region boundary based dense sampling strategy, which reduces the number of trajectories while preserves the discriminative power, and can improve the performance of action recognition with minor computational cost of mask production.
- Modeling spatial database incremental updating based on base state with amendments7
Experimental results show that using the models presented in this paper can store incremental information effectively, and integrate the incremental information into the old databases quickly.
- Occluded suspect search via channel-guided mechanism6
A channel-guided mechanism (CGM) for occluded suspect search using different body areas have been activated via different channels in convolutional neural networks which can identify suspects using a rule which focuses more on the visible area and focuses less on the occluding area in the specific occlusion pattern.
- Multi-branch Body Region Alignment Network for Person Re-identification6
A Multi-branch Body Region Alignment Network (MBRAN), to learn discriminative representations for person Re-ID, and extensive experiments have indicated that this method outperforms several state-of-the-art methods on two mainstream person re-identification datasets.
- An Improved Lookup Algorithm on Over-DHT Paradigm Based P2P Network6
A improved lookup algorithm, Nearest Upper Boundary Lookup (NUBL for short) to reduce the DHT-lookup times during single data record searching procedure in LIGHT is proposed and proved the effectiveness of NUBL by simulating experiments.
- Study of decoding mental state based on eye tracks using SVM6
This paper can interpret different problem-solving strategies according to the results of classification of eye tracks, and uses feature values, the weighted value of the composite indicators, such as the duration, regression time of each AOI, to train SVM classifier.
- 5
- 5
- 5
- One-Shot Face Recognition with Feature Rectification via Adversarial Learning5
This paper proposes feature rectification generative adversarial network (FR-GAN) which is able to rectify features closer to corresponding classification weights considering existing classification weights information.
- SIST: Online Scale-Adaptive Object tracking with Stepwise Insight5
This work proposes an online scale-adaptive correlation tracker by collaboratively learning a target-insight model (TIM) for object localization and a scale-insights model (SIM) for progressive refinement, which outperforms several state-of-the-art methods.
- 5
- Research on Point Cloud Registration and Stitching Fusion Algorithm Based on GCN-PRFNet4
A fusion algorithm for registration and stitching based on a GCN-PRFNet point cloud is proposed, indicating that the constructed end-to-end point-cloud registration and splicing model is considerably effective in real-world application scenarios.
- 4
- 4
- 4
- 4
- Robust Tracking Using On-Line Selection of Multiple Features4
A novel on-line feature selection mechanism based on mean shift tracking algorithm, which adjusts the weight for each feature and each bin in feature histograms during the tracking process, according to the discrimination between the appearance of object and background with different features is presented.
- An instance-based approach for schema matching in GIS client database updating4
Unlike other schema matching methods that only focus on attribute-level matching, this method adopts a hierarchical strategy to determine mapping relationship form two-level schema elements including feature classes and attributes.
- 3
- Potential trend discovery for highway drivers on spatio‐temporal data3
A travel-characteristic based method is proposed to discover the potential trend of payment identity for highway drivers, modeled on monthly data from highway toll stations, through which predictive errors can be reduced by gradient boosting classification.
- 3
- A Multi-scale Triplet Deep Convolutional Neural Network for Person Re-identification3
Experimental results on two public person re-identification datasets demonstrate that the proposed MVT-CNN method outperforms most of the existing feature learning algorithms by 8%–10% at rank@1 in term of the cumulative matching curve (CMC) criterion.
- 3
- 3
- A Method for Global-Scale Archiving of Imaging Data Based on QTM Pixels3
The Quaternary Triangular Mesh (QTM) (Dutton, 1989), as a continuous, hierarchal quadtree data structure with uniform grids on a sphere, is proposed for global-scale seamless image archiving and the result indicates that the QTM pixel data structure can keep global- scale images seamless.
- A method for generating contour tree based on voronoi interior adjacency3
A new method for generating contour trees by introducing a Voronoi-based interior adjacency concept is proposed in this paper and has advantages over existing methods such as the geometric method and the region growing-based method.
- Learning Hierarchically Consistent Disentanglement with Multi-Channel Augmentation for Public Security-Oriented Sketch Person Re-Identification2
A novel network architecture that integrates multi-channel augmentation with hierarchically consistent disentanglement learning is proposed and a modality-disentangled prototype(MDP) module is introduced to decompose pedestrian representations at the feature level into modality-invariant structural prototypes and modality-specific appearance prototypes.
- An Orientation-Aware Attention Network for Person Re-Identification2
This work introduces pixel-wise relative positions for the invariance of their orientations in viewpoint changes and combines relative positions with self-attention modules that perform on multi-level features to cope with the scale change of relative position.
- 2
- 2
- 2
- Deep Segmentation Domain Adaptation Network With Weighted Boundary Constraint2
Weighted boundary constraint is proposed to refine those segmentation predictions and incorporate it into a generative adversarial network (GAN)-based network for domain adaption to achieve further significant improvement.
- 2
- 2
- 2
- Adaptive Margin Nearest Neighbor for Person Re-Identification2
An Adaptive Margin Nearest Neighbor (AMNN) method is proposed, which aims to take unequal treatment to each samples impostors by pushing them to adaptive variable margins away, and is confirmed the superiority of the proposed method.
- 2
- 2
- Matching of road data with different scales for updating2
This paper presents an approach for road data matching based on level analysis, which meets the requirement for searching data unmatched and shows higher matching accuracy.
- 2
- 1
- 1
- 1
- CSCNN: Lightweight Modulation Recognition Model for Mobile Multimedia Intelligent Information Processing1
This approach proposes the Deep Complex Separable Convolution (DCSC) operation by combining separable convolution operation and complex convolution operation, and constructed the Complex Separable Convolutional Neural Network (CSCNN), a neural network that significantly reduces the complexity of the deep learning model.
- 1
- The Analysis for Binaural Signal’s Characteristics of a Real Source and Corresponding Virtual Sound Image1
This paper analyzed and compared binaural signal’s characteristics under different loudspeaker configurations and gains and may be act as a primary reference for further research about sound field reconstruction etc.
- Multi-Pedestrian Detection from Effective Proposal in Crowd Scene1
A novel MP detection method is presented that introduces bottom-up region proposals (which are called effective proposals) into the MP detection process, from which, high detection rate as well as low computation complexity can be simultaneously achieved.
- Autonomous Learning Framework Based on Online Hybrid Classifier for Multi-view Object Detection in Video.1
Experimental results on several video datasets show that the proposed framework achieves comparable performance to robust supervised methods and outperforms the state of the art online learning methods in varying imaging conditions.
- User-Driven Sports Video Customization System for Mobile Devices1
A user-driven sports video customization system, aiming to provide interesting video clips for mobile users according to their personalized preferences, and the proposed extended-hidden Markov model extended-HMM is proved to be able to recognize the clock time precisely.
- Group recursive discriminant subspace learning with image set decomposition1
A novel recursive learning approach that is group recursive discriminant subspace learning, which can rapidly learn multiple orthogonal subspaces with each spanned by a group of projective vectors is proposed.
- 1
- The Reconstruction of 3D Human Face Based on the Post-Plastic Surgery1
This paper employs three 2D digital color photos to obtain high-resolution textures and takes advantages of 3D face model reconstructed from CT data for flexible deformation of finite elements.
- Saliency-Based Deformable Model for Pedestrian Detection1
In SBDM method, it is presented that, besides the local features, the saliency in the image provides important constraints that are not yet well utilized, and a probabilistic framework is proposed to model the relationship between Saliency detection and the feature Deformable Model via a Bayesian rule to detect pedestrians in the still image.
- Histograms of Salience for Pedestrian Detection1
A salience representation for pedestrian detection, Histograms-Of-Salience (HOS) is proposed and investigated, extracted saliency map learned from data by using Histogram Based Contrast, and aggregate salient value and oriented gradients to form local HOS.
- A Multi-Core Architecture for Video Streaming1
This paper has implemented the video streaming system with proposed architecture, and provided evidences of 48% outperformance based on Cavium OCTEON CN5860 multi-core processor than full parallel architecture.
- 1
- Basic Issues for GIS Client Database Updating1
The definition and basic implementing approaches of GIS client database updating is firstly explained, and then the basic issues during the process of updating implementation such as change capture, delta modeling, data heterogeneity, updating integration, software platform, and policy standard are discussed.
- The design and implementation of geo-spatial database updating system based on digital map generalization1
A method is described to update geo-spatial database based map generalization technology and it is shown the method is less cost and more efficient in the multi-scale geo- Spatial database updating.
- 1
- 1
- Research on modeling and classifying of topographical data change for incremental information distribution1
This work proposes a new conceptual model of changes based on the explicit description of state transformation of geographical entities in the real world and state Transformation of geographical objects in the data world, which is not only closest to the modeling of thereal world change processes but also is easy to identity the data delta resulted from the change process.
- COMPREHENSIVE EVALUATION OF RESERVOIRS BASED ON THE FUNCTIONS OF GIS SPATIAL ANALYSIS1
By establishment of database of reservoir comprehensive evaluation and analysis using the GIS functions of characteristic pick-up and combination, the useful characteristic information on reservoir evaluation, such as oilfield area data, geologic data, physical geography, and test can be obtained.
- –
- –
- –
- –
- –
- –
- Transferring fashion to surveillance with weak labels–
This paper addresses the problem of automatic clothing parsing in surveillance images using the information from user-generated tags, such as “jeans” and “T-shirt" using a weakly supervised transfer learning method.
- LDSNE: Learning Structural Network Embeddings by Encoding Local Distances–
This work proposes LDSNE, a novel algorithm for learning structural representations in both directed and undirected networks, which can obtain multiple types of representations and outperforms other state-of-the-art methods.
- Feature Synthesization for Real-Time Pedestrian Detection in Urban Environment–
A novel framework that utilizes reconstruction sparsity to synthesize the feature map online is proposed for real-time pedestrian detection for the early warning system of the unmanned vehicle in real world.
- Online Generative-Discriminative Model for Object Detection in Video: An Unsupervised Learning Framework–
This paper proposes Generative-Discriminative model to partition detection response space and assign each partition an individual descriptor that progressively achieves high classification accuracy, which can be employed in multi-view object detection applications from unsupervised learning process.
- Vulnerability Evaluation of Security Network Based on Neyman-Pearson Criterion–
A protection model of a security system based on Neyman-Pearson criterion is brought forward and methods to determine the most vulnerable path of aSecurity network are proposed and insight about the vulnerability is gained.
- Identification and Diagnosis of Cotton Disease Based on Multi-source Image Fusion Technology–
Based on disease recognition diagnostic methods with fusion multi-sensor information, intelligent cotton disease recognition system were constructed to provide theory basis for precise management of cotton disease and mechanized variable drug delivery techniques.
- The Application of Quantum Genetic Algorithm in Gray Image–
Through simulation experiments, the effectiveness of genetic algorithms to enhance image is verified through the use of quantum genetic algorithm for nonlinear transformation parameters α and β, which adaptive to achieve gray-scale image enhancement.
- –
- Analysis and validation of survivability for network service system–
In order to analyze the survivability of network service system with redundant components, an attack-resistance-recovery process model was established, and a quantitative assessment method for system survivability was proposed on the basis of the dependency relationship between service and components.
- IMS multimedia conferencing service platform design scheme–
Based on multimedia conference agreement IMS business platform, system architecture was studied, and the design scheme of the proposed scheme deployment platform was proposed.
- –
- –
- –
- –
- Research on database's dynamical modeling framework system–
A agile and powerful database concept design framework which can create database dynamically is achieved using the object-oriented method.
- Study of Resolving Heterogeneity in Database System–
One method is proposed, that can found the database of concept in the domain and then constitute the rule of mapping, and with those ways, the problem of heterogeneity in database system can be resolved.
- One Way of Reducing the Hardware Resource Usage in FIR Design Using FPGA–
A new realizing structure of FIR digital filter that greatly reduces the hardware usage of multiplier and ACC is presented and it is shown that as the digital filtering ability is concerned, there is no difference between the new structure and the traditional one.
- Integrating Fundamental Geographic Information,Serving Electronic Government–
The department of surveying and mapping has been suggested that it should plan the construction of national, provincial and city level fundamental geographic information as a whole to strengthen government supervision and administration on the construction, management, application and updating offundamental geographic information.
- Discussing on rough set theory and knowledge management decision making–
The feasibility of knowledge management decisionmaking based on rough set theory was discussed by view of rising level ofknowledge management decision-making.
- Methods of Feature Taxonomy and Representation in the Developed System Beased on UGII–
With the help of analysis on feature definition, the features in UGⅡ were classified and it was pointed out that the shape features were most important of all features, they could carry others.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.