|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Real-time object tracking via compressive feature selection显示文摘 | Kang LI Fazhi HE Xiao CHEN | 2016 | Frontiers of Computer Science2016，10，4： | 14 |
| 2 | Efficient random saliency map detection显示文摘Most image retargeting algorithms rely heavily on valid saliency map detection to proceed. However, the inefficiency of high quality saliency map detection severely restricts the application of these image retargeting methods. In this paper, we propose a random algorithm for efficient context-aware saliency map detection. Our method is a multiple level saliency map detection algorithm that integrates multiple level coarse saliency maps into the resulting saliency map and selectively updates unreliable regions of the saliency map to refine detection results. Because of the randomized search, our method requires very little additional memory beyond that for the input image and result map, and does not need to build auxiliary data structures to accelerate the saliency map detection. We have implemented our algorithm on a GPU and demonstrated the performance for a variety of images and video sequences, compared with state-of-the-art image processing. | HUANG ZhiYong HE FaZhi CAI XianTao ZOU ZhengQin LIU Jing LIANG MingMing & CHEN Xiao | 2011 | Science China(Information Sciences)2011，54，6： | 11 |
| 3 | Consistency Maintenance in Collaborative CAD Systems显示文摘 | LIU Huajun HE Fazhi ZHU Fuxi ZHU Qing | 2013 | Chinese Journal of Electronics2013，22，1： | 4 |
| 4 | A semi-transparent selective undo algorithm for multi-user collaborative editors显示文摘Multi-user collaborative editors are useful computer-aided tools to support human-to-human collaboration.For multi-user collaborative editors,selective undo is an essential utility enabling users to undo any editing operations at any time.Collaborative editors usually adopt operational transformation(OT)to address concurrency and consistency issues.However,it is still a great challenge to design an efficient and correct OT algorithm capable of handling both normal do operations and user-initiated undo operations because these two kinds of operations can interfere with each other in various forms.In this paper,we propose a semi-transparent selective undo algorithm that handles both do and undo in a unified framework,which separates the processing part of do operations from the processing part of undo operations.Formal proofs are provided to prove the proposed algorithm under the well-established criteria.Theoretical analysis and experimental evaluation are conducted to show that the proposed algorithm outperforms the prior OT-based selective undo algorithms. | Weiwei CAI Fazhi HE Xiao LV Yuan CHENG | 2021 | Frontiers of Computer Science2021，15，5： | 3 |
| 5 | A parallel and robust object tracking approach synthesizing adaptive Bayesian learning and improved incremental subspace learning显示文摘This paper presents a novel tracking algorithm which integrates two complementary trackers. Firstly, an improved Bayesian tracker(B-tracker) with adaptive learning rate is presented. The classification score of B-tracker reflects tracking reliability, and a low score usually results from large appearance change. Therefore, if the score is low, we decrease the learning rate to update the classifier fast so that B-tracker can adapt to the variation and vice versa. In this way, B-tracker is more suitable than its traditional version to solve appearance change problem. Secondly, we present an improved incremental subspace learning method tracker(Stracker). We propose to calculate projected coordinates using maximum posterior probability, which results in a more accurate reconstruction error than traditional subspace learning tracker. Instead of updating at every time, we present a stopstrategy to deal with occlusion problem. Finally, we present an integrated framework(BAST), in which the pair of trackers run in parallel and return two candidate target states separately. For each candidate state, we define a tracking reliability metrics to measure whether the candidate state is reliable or not, and the reliable candidate state will be chosen as the target state at the end of each frame. Experimental results on challenging sequences show that the proposed approach is very robust and effective in comparison to the state-of-the-art trackers. | Kang LI Fazhi HE Haiping YU Xiao CHEN | 2019 | Frontiers of Computer Science2019，13，5： | 3 |
| 6 | Dynamic strategy based parallel ant colony optimization on GPUs for TSPs显示文摘Metaheuristics are a type of approximate optimization algorithms for solving hard and complex problems in science and engineering[1].They can be defined as algorithm templates that can be easily adapted to solve specific optimization problems.Motivated by search behavior,most researchers divide metaheuristics into two classes:trajectory-based and population-based[1]. | Yi ZHOU Fazhi HE Yimin QIU | 2017 | Science China(Information Sciences)2017，60，6： | 3 |
| 7 | A correlative denoising autoencoder to model social influence for top-N recommender system显示文摘In recent years,there are numerous works been proposed to leverage the techniques of deep learning to improve social-aware recommendation performance.In most cases,it requires a larger number of data to train a robust deep learning model,which contains a lot of parameters to fit training data.However,both data of user ratings and social networks are facing critical sparse problem,which makes it not easy to train a robust deep neural network model.Towards this problem,we propose a novel correlative denoising autoencoder(CoDAE)method by taking correlations between users with multiple roles into account to learn robust representations from sparse inputs of ratings and social networks for recommendation.We develop the CoDAE model by utilizing three separated autoencoders to learn user features with roles of rater,truster and trustee,respectively.Especially,on account of that each input unit of user vectors with roles of truster and trustee is corresponding to a particular user,we propose to utilize shared parameters to learn common information of the units that corresponding to same users.Moreover,we propose a related regularization term to learn correlations between user features that learnt by the three subnetworks of CoDAE model.We further conduct a series of experiments to evaluate the proposed method on two public datasets for Top-N recommendation task.The experimental results demonstrate that the proposed model outperforms state-of-the-art algorithms on rank-sensitive metrics of MAP and NDCG. | Yiteng PAN Fazhi HE Haiping YU | 2020 | Frontiers of Computer Science2020，14，3： | 3 |
| 8 | A Novel Attribute-Based Encryption Approach with Integrity Verification for CAD Assembly Models显示文摘Cloud manufacturing is one of the three key technologies that enable intelligent manufacturing.This paper presents a novel attribute-based encryption(ABE)approach for computer-aided design(CAD)assembly models to effectively support hierarchical access control,integrity verification,and deformation protection for co-design scenarios in cloud manufacturing.An assembly hierarchy access tree(AHAT)is designed as the hierarchical access structure.Attribute-related ciphertext elements,which are contained in an assembly ciphertext(ACT)file,are adapted for content keys decryption instead of CAD component files.We modify the original Merkle tree(MT)and reconstruct an assembly MT.The proposed ABE framework has the ability to combine the deformation protection method with a content privacy of CAD models.The proposed encryption scheme is demonstrated to be secure under the standard assumption.Experimental simulation on typical CAD assembly models demonstrates that the proposed approach is feasible in applications. | Yueting Yang Fazhi He Soonhung Han Yaqian Liang Yuan Cheng | 2021 | Engineering2021，7，6： | 3 |
| 9 | Tracking topological entity changes in 3D collaborative modeling systems显示文摘One of the key problems in collaborative geometric modeling systems is topological entity correspondence when topological structure of geometry models on collaborative sites changes.In this article,we propose a solution for tracking topological entity alterations in 3D collaborative modeling environment.We firstly make a thorough analysis and detailed categorization on the alteration properties and causations for each type of topological entity,namely topological face and topological edge.Based on collaborative topological entity naming mechanism,a data structure called TEST (Topological Entity Structure Tree) is introduced to track the changing history and current state of each topological entity,to embody the relationship among topological entities.Rules and algorithms are presented for identification of topological entities referenced by operations for correct execution and model consistency.The algorithm has been verified within the prototype we have implemented with ACIS. | Cheng Yuan He Fazhi Huang Zhiyong Cai Xiantao Zhang Dejun | 2012 | Computer Aided Drafting,Design and Manufacturing2012，22，1： | 2 |
| 10 | Real-time control of human actions using inertial sensors显示文摘Our study proposes a new local model to accurately control an avatar using six inertial sensors in real-time.Creating such a system to assist interactive control of a full-body avatar is challenging because control signals from our performance interfaces are usually inadequate to completely determine the whole body movement of human actors.We use a pre-captured motion database to construct a group of local regression models,which are used along with the control signals to synthesize whole body human movement.By synthesizing a variety of human movements based on actors’control in real-time,this study verifies the effectiveness of the proposed system.Compared with the previous models,our proposed model can synthesize more accurate results.Our system is suitable for common use because it is much cheaper than commercial motion capture systems. | LIU HuaJun HE FaZhi ZHU FuXi ZHU Qing | 2014 | Science China(Information Sciences)2014，57，7： | 2 |
| 11 | An efficient GPU-based parallel tabu search algorithm for hardware/software co-design显示文摘Hardware/software partitioning is an essential step in hardware/software co-design.For large size problems,it is difficult to consider both solution quality and time.This paper presents an efficient GPU-based parallel tabu search algorithm(GPTS)for HW/SW partitioning.A single GPU kernel of compacting neighborhood is proposed to reduce the amount of GPU global memory accesses theoretically.A kernel fusion strategy is further proposed to reduce the amount of GPU global memory accesses of GPTS.To further minimize the transfer overhead of GPTS between CPU and GPU,an optimized transfer strategy for GPU-based tabu evaluation is proposed,which considers that all the candidates do not satisfy the given constraint.Experiments show that GPTS outperforms state-of-the-art work of tabu search and is competitive with other methods for HW/SW partitioning.The proposed parallelization is significant when considering the ordinary GPU platform. | Neng Hou Fazhi He Yi Zhou Yilin Chen | 2020 | Frontiers of Computer Science2020，14，5： | 2 |
| 12 | Computer-aided Tool for Collaborative Integrated Design Environments显示文摘 | He Fazhi Wang Shaomei Sun Guozheng | 2002 | Journal of Mechanical Engineering2002，38，6： | 1 |
| 13 | A method and tool for human- human interaction and instant collaboration in CSCW- based CAD 显示文摘 | Fazhi He Soonhung Han | 2006 | Computer in Industry (57)2006，，： | 1 |
| 14 | Survey of distributed andcollab- orative design显示文摘 | Gao Shuming He Fazhi | 2004 | Journal of Computer-Aided Design Computer Graphics2004，16，2： | 1 |
| 15 | Evolutionary Computation Based Optimization of Image Zernike Moments Shape Feature Vector显示文摘图象形状特征能到图象 Zernike 时刻被描述。在这篇论文,我们指出高尺寸图象 Zernike 时刻塑造的问题特征向量能描述原来的图象的更多的详细,但是有太多元素为下一个图象分析阶段造成麻烦。然后,低尺寸图象 Zernike 时刻形状特征向量应该被改进并且优化了描述原来的图象的更多的详细。优化算法因此基于进化计算被设计并且在这篇论文实现了解决这个问题。试验性的结果表明优化算法的可行性。 | LIU Maofu HU Hujun ZHONG Ming HE Yanxiang HE Fazhi | 2008 | Wuhan University Journal of Natural Sciences2008，13，2： | 1 |
| 16 | A method for topological entity correspondence in a replicated col- laborative CAD system 显示文摘 | Jing Shuxu He Fazhi Han Soonhung | 2009 | Computers in Industry2009，60，7： | 1 |
| 17 | A method and tool for human-human interaction and instant collaboration in CSCW-based CAD 显示文摘 | Fazhi He Soonhung Han | 2006 | Computers in Industry2006，，57： | 1 |
| 18 | CAD data exchange based on the recovery of feature modelling procedure 显示文摘 | Li Xiaoxia He Fazhi Cai Xiantao | 2012 | International Journal of Computer Integrated Manufacturing2012，25，10： | 1 |
| 19 | A method for topological entity matching in the integration of heterogeneous cad systems 显示文摘 | Li Xiaoxia He Fazhi Cai Xiantao | 2013 | Integrated Computer-Aided Engineering2013，20，1： | 1 |
| 20 | Weight asynchronous update:Improving the diversity of filters in a deep convolutional network显示文摘Deep convolutional networks have obtained remarkable achievements on various visual tasks due to their strong ability to learn a variety of features.A welltrained deep convolutional network can be compressed to 20%–40%of its original size by removing filters that make little contribution,as many overlapping features are generated by redundant filters.Model compression can reduce the number of unnecessary filters but does not take advantage of redundant filters since the training phase is not affected.Modern networks with residual,dense connections and inception blocks are considered to be able to mitigate the overlap in convolutional filters,but do not necessarily overcome the issue.To do so,we propose a new training strategy,weight asynchronous update,which helps to significantly increase the diversity of filters and enhance the representation ability of the network.The proposed method can be widely applied to different convolutional networks without changing the network topology.Our experiments show that the stochastic subset of filters updated in different iterations can significantly reduce filter overlap in convolutional networks.Extensive experiments show that our method yields noteworthy improvements in neural network performance. | Dejun Zhang Linchao He Mengting Luo Zhanya Xu and Fazhi He | 2020 | Computational Visual Media2020，6，4： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员