Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks206 from public data
- An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning398
An end-to-end automatic CDB tuning system, CDBTune, using deep reinforcement learning (RL), which enables end- to-end learning and accelerates the convergence speed of the model and improves efficiency of online tuning.
- Rational Design and Synthesis of Novel Dual PROTACs for Simultaneous Degradation of EGFR and PARP189
Gefitinib, olaparib, and CRBN or VHL E3 ligands were used as substrates to synthesize novel dual PROTACs that successfully degraded both the epidermal growth factor receptor (EGFR) and poly(ADP-ribose) polymerase (PARP) simultaneously in cancer cells.
- Healthcare workers’ stress when caring for COVID-19 patients: An altruistic perspective174
A low stress level among healthcare workers indicated their professional devotion and altruism during COVID-19 epidemic, which will be a lesson to other countries that awaking healthcare workers’ inside motivation and providing necessary support from government and society were significant.
- Influence of perceived stress and workload on work engagement in front‐line nurses during COVID‐19 pandemic168
Front‐line nurses perceived low stress and workload, but high work engagement, especially in self‐dedication, however, infection control, PPE discomfort and frustration were negatively associated with nurses’Work engagement, while mental demand and good performance were positively associated with Nurses’ work engagement.
- Emergency management of nursing human resources and supplies to respond to coronavirus disease 2019 epidemic108
The emergency management of nursing human resources and material resources for COVID-19 of the hospital is successful, but several deficiencies were identified, which indicated that the hospital needs to establish an efficient emergency management system and pay attention to the practice of nursing emergency plans to enhance coping capacities in public health emergencies.
- 99
- Combination of Cloud Computing and Internet of Things (IOT) in Medical Monitoring Systems85
This paper study and analyze the application of cloud computing and the Internet of Things on the field of medical environment and proposes the hospital medical information service cloud system monitoring and management application.
- HUNTER: An Online Cloud Database Hybrid Tuning System for Personalized Requirements71
An online CDB tuning system called HUNTER, which uses samples generated by Genetic Algorithm to warm-start the finer grained exploration of deep reinforcement learning, and employs Principal Component Analysis, Random Forest, and Fast Exploration Strategy to reduce the search space and the update time of the learning model.
- Learning Where to Focus for Efficient Video Object Detection70
A novel module called Learnable Spatio-Temporal Sampling (LSTS) has been proposed to learn semantic-level correspondences among adjacent frame features accurately and achieves state-of-the-art performance on the ImageNet VID dataset with less computational complexity and real-time speed.
- Deep Self-taught Hashing for Image Retrieval68
A deep self-taught hashing (DSTH) framework to combine deep structures with hashing to improve the retrieval performance by automatically learning robust visual features and hash functions and applies CNNs and Multi-layer Perceptron under deep learning scheme.
- Mining high utility itemsets by dynamically pruning the tree structure67
This paper proposes an efficient concurrent algorithm, called CHUI-Mine (Concurrent High Utility Itemsets Mine), for mining high utility itemsets by dynamically pruning the tree structure, and implements dynamicCHUI-Tree pruning, and discusses the rationality thereof.
- An Evolutionary Algorithm Based on Cloud Model64
The successful integrating of the cloud model and evolution principle expands the research fields of Cloud Theory and also indicates a new way for the research of evolutionary computation.
- Human emotion recognition with a microcomb‐enabled integrated optical neural network54
The proposed MIONN provides a high-speed and energy-efficient neuromorphic computing hardware for deep learning models with emotional interaction capabilities for fast and low-power computing.
- Fast Graph Convolution Network Based Multi-label Image Recognition via Cross-modal Fusion54
Experimental results demonstrate the MFB component efficiently fuses image representations and label co-occurrence embeddings and thus greatly improves the convergence efficiency of the model and proposes F-GCN, a fast graph convolution network (GCN) based multi-label image recognition model.
- 48
- 48
- DeepIndex for Accurate and Efficient Image Retrieval44
This work attempts to introduce deep features into inverted index based image retrieval and proposes the DeepIndex framework, which finds the optimal integration of one midlevel deep feature and one high- level deep feature, from two different CNN architectures separately.
- 41
- 40
- UniNet: Unified Architecture Search with Convolution, Transformer, and MLP40
This work studies the learnable combination of convolution, transformer, and MLP by proposing a novel unified architecture search approach, and proposes context-aware downsampling modules (DSMs) to mitigate the gap between the different types of operators.
- Unsupervised deep hashing with node representation for image retrieval40
NRDH, an unsupervised method with extensive experiments on CIFAR-10, MS-COCO and FLICKR25K show NRDH can achieve higher performance and outperform the state-of-the-art un supervised deep hashing methods.
- Label-Attended Hashing for Multi-Label Image Retrieval34
A Label-Attended Hashing (LAH) algorithm is proposed which enables an end-to-end hash model with inter-dependency feature extraction and the usage of co-occurrence relationship and MFB not only promotes the precision of hash codes but also accelerates the hash learning.
- Exploring Hierarchical Information in Hyperbolic Space for Self-Supervised Image Hashing33
This paper proposes a new self-supervised hashing method named Hierarchical Hyperbolic Contrastive Hashing (HHCH), making breakthroughs in three aspects, including to embed continuous hash codes into hyperbolic space for accurate semantic expression and to exploit the hierarchical semantic structures in hyperbolic space.
- 33
- Context-Aware Temporal Knowledge Graph Embedding33
This work decomposes the target fact into two parts, relation and entities, and measures the usefulness of a context for each part respectively, and adopts deep neural networks to encode contexts and score the temporal consistency.
- $$\hbox {CDBTune}^{+}$$: An efficient deep reinforcement learning-based automatic cloud database tuning system31
An end-to-end automatic CDB tuning system that utilizes the deep deterministic policy gradient method to find the optimal configurations in a high-dimensional continuous space and adopts the reward-feedback mechanism in RL instead of traditional regression.
- Towards Systematic Parallel Programming over MapReduce31
A homomorphism-based framework named Screwdriver for systematic parallel programming with MapReduce, making use of the program calculation theory of list homomorphisms, which enables us to resolve many problems that it would be nontrivial to resolve directly with Map Reduce.
- 29
- Deep sentiment hashing for text retrieval in social CIoT29
A deep model for hash functions learning is built, which is supervised by both the generated hash labels and the original sentiment labels, and ensures that the ultimate hash codes produced by the learned hash functions maintain sentiment-level similarity.
- A distributed cross-layer intrusion detection system forad hoc networks29
An anomaly-based ids is proposed that utilizes cross-layer features to detect attacks, and localizes attack sources within onehop perimeter, and develops a novel collaborative detection scheme that enables theIds to correlate local and global alerts.
- 28
- 99mTc-labeled SWL specific peptide for targeting EphA2 receptor27
The expression of EphA2 can be noninvasively investigated by SPECT imaging using (99m)Tc-HYNIC-SWL, a novel peptide-based probe developed and its potential to specifically target EPhA2-positive tumors was investigated.
- Supervised Hierarchical Online Hashing for Cross-modal Retrieval26
This work designs a hierarchical similarity learning method in the online learning framework, which includes virtual center learning and hierarchical similarity embedding, and proposes a Weighted Retrieval Strategy (WRS) to mitigate the impact caused by bit-flipping errors.
- A framework for intrusion detection systems by social network analysis methods in ad hoc networks25
This paper introduces a SNA method as a new approach to build an intrusion detection system (SN-IDS) in mobile ad hoc networks that has clear advantages over the conventional association rule based data mining IDS in terms of computation and system complexity.
- 23
- Semantic-aware data quality assessment for image big data23
This work proposes a semantic-aware data quality assessment (SDQA) architecture which includes off-line analysis and on-line assessment, and proposes an algorithm to calculate the importance score for each node of a graph, taking both the quantity of relevant images and the degree of semantic similarity into consideration.
- 22
- A hybrid data mining anomaly detection technique in ad hoc networks22
This paper incorporates two data mining techniques, that is, association-rule mining and cross-feature mining, to characterise normal behaviours of mobile nodes and detect anomalies by finding deviance from the norm in node-based Intrusion Detection Systems (IDS).
- Image retrieval for Structure-from-Motion via Graph Convolutional Network21
This paper presents a novel retrieval method based on Graph Convolutional Network (GCN) to generate accurate pairwise matches without costly redundancy and demonstrates that it performs remarkably well on the challenging dataset of highly ambiguous and duplicated scenes.
- 20
- 19
- 19
- CHAIN: Exploring Global-Local Spatio-Temporal Information for Improved Self-Supervised Video Hashing18
The proposed Contrastive Hashing with Global-Local Spatio-temporal Ibnformation (CHAIN) outperforms state-of-the-art self-supervised video hashing methods on four video benchmark datasets.
- 18
- Economic and Deterministic Quantum Teleportation of Arbitrary Bipartite Pure and Mixed State with Shared Cluster Entanglement18
A novel protocol for teleportation of arbitrary bipartite pure and mixed state with shared cluster entanglement by employing Bell-state measurement on the teleported state and the shared cluster state twice, which is more efficient and applicable than the previous schemes.
- 18
- 18
- Teach-DETR: Better Training DETR With Teachers17
It is shown that the predicted boxes from teacher detectors are effective medium to transfer knowledge of teacher detectors, which could be either RCNN-based or DETR-based detectors, to train a more accurate and robust DETR model.
- A survey on AI for storage16
This paper categorizes storage research employing intelligent algorithms according to public literature in recent years into Architecture-oriented, Data-specific, and Operation & Maintenance, and fine-categorizes all of the studies by application environment to provide guidelines for future research on how to employ AI technologies.
- 16
- 15
- 15
- Genesis: A scalable distributed system for large-scale parallel network simulation15
A novel approach to scalability and efficiency of parallel network simulations based on partitioning a network into domains and of the simulation time into intervals is described, which allows the parallelization with infrequent synchronization, and achieves significant simulation speedups.
- 14
- 14
- A Novel Student Achievement Prediction Method Based on Deep Learning and Attention Mechanism14
A student achievement prediction model based on deep learning and attention mechanism (MCAG) is proposed, which indicates that the proposed model can predict student achievement more accurately.
- Multi-view multi-label learning for image annotation13
A multi-view multi-label (abbreviated by MVML) learning algorithm, in which it makes full use of the complementarity among the views and the base learners of ensemble learning, leading to higher accuracy of image annotation.
- 12
- 12
- 11
- 11
- 10
- A hash centroid construction method with Swin transformer for multi-label image retrieval10
HCCST, a hash centroid construction method with Swin transformer for multi-label image retrieval that can achieve better retrieval performance compared with the state-of-the-art image hashing methods is proposed.
- Label graph learning for multi-label image recognition with cross-modal fusion10
LGLM first constructs a label graph according to the word vector of each object and then adopts graph convolution network to learn the label correlations to generate label co-occurrence embeddings and the experimental results demonstrate the superiority of LGLM compared with the state-of-the-art image recognition methods.
- Campus View: An Innovative Location and Context-Aware Video Sharing Application on Smart Phone10
The development framework of Campus View application is presented and an evaluation of key framework components to assess their consumption of mobile device’s resources are presented.
- 9
- 9
- A Framework for Image Dark Data Assessment8
An assessment framework which includes offline and online stages for image dark data, which can apply to large-scale datasets, and help the user conduct subsequent data mining work is proposed.
- 8
- 8
- 8
- A low cost and un-cancelled laplace noise based differential privacy algorithm for spatial decompositions7
It is proved that adding Lapmin(λ) noise to query answer guarantees both differential privacy and minimal relative error comparing with unlimited Laplace noise.
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- Deep Hash-based Relevance-aware Data Quality Assessment for Image Dark Data4
A Deep Hash-based Relevance-aware Data Quality Assessment framework, which contains off-line learning and relevance mining parts as well as an on-line assessing part, which can gain the most desired data with the same mining resources.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Learning Motion Priors for Efficient Video Object Detection.1
This paper first initialize some motion priors for each location and then use them to propagate features across frames and achieves state-of-the-art performance on the ImageNet VID dataset with real-time speed.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Multi-teacher Knowledge Distillation for Knowledge Graph Completion.–
The experimental results show that MulDE can effectively improve the performance and training speed of low-dimensional KGE models, and the distilled 32-dimensional models are very competitive compared to some of state-or-the-art (SotA) high-dimensional methods on several commonly-used datasets.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- A discussion on a quantum key remote distribution scheme not based on the quantum entanglement state–
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 2026-10-16. 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.