|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Cuckoo search with varied scaling factor显示文摘 | Lijin WANG Yilong YIN Yiwen ZHONG | 2015 | Frontiers of Computer Science2015，9，4： | 15 |
| 2 | Pre-course student performance prediction with multi-instance multi-label learning显示文摘Dear editor,Studying courses is one of the most basic and important tasks for college students.For each new course,the initial period of learning is crucial for students,and seriously influences subsequent learning activities.However,given a large number of classes in universities,it has become impossible for teachers to keep track of the individual performance of each student.In these circumstances,it is desirable to predict each student’s performance on a certain course prior to its commencement. | Yuling MA Chaoran CUI Xiushan NIE Gongping YANG Kashif SHAHEED Yilong YIN | 2019 | Science China(Information Sciences)2019，62，2： | 5 |
| 3 | Empirical estimates of regional carbon budgets imply reduced global soil heterotrophic respiration显示文摘Resolving regional carbon budgets is critical for informing land-based mitigation policy.For nine regions covering nearly the whole globe,we collected inventory estimates of carbon-stock changes complemented by satellite estimates of biomass changes where inventory data are missing.The net land–atmospheric carbon exchange(NEE)was calculated by taking the sum of the carbon-stock change and lateral carbon fluxes from crop and wood trade,and riverine-carbon export to the ocean.Summing up NEE from all regions,we obtained a global‘bottom-up'NEE for net land anthropogenic CO_(2)uptake of–2.2±0.6 Pg C yr^(-1)consistent with the independent top-down NEE from the global atmospheric carbon budget during 2000–2009.This estimate is so far the most comprehensive global bottom-up carbon budget accounting,which set up an important milestone for global carbon-cycle studies.By decomposing NEE into component fluxes,we found that global soil heterotrophic respiration amounts to a source of CO_(2)of 39 Pg C yr^(-1)with an interquartile of 33–46 Pg C yr^(-1)—a much smaller portion of net primary productivity than previously reported. | Philippe Ciais Yitong Yao Thomas Gasser Alessandro Baccini Yilong Wang Ronny Lauerwald Shushi Peng Ana Bastos Wei Li Peter A.Raymond Josep G.Canadell Glen P.Peters Rob J.Andres Jinfeng Chang Chao Yue A.Johannes Dolman Vanessa Haverd Jens Hartmann Goulven Laruelle Alexandra G.Konings Anthony W.King Yi Liu Sebastiaan Luyssaert Fabienne Maignan Prabir K.Patra Anna Peregon Pierre Regnier Julia Pongratz Benjamin Poulter Anatoly Shvidenko Riccardo Valentini Rong Wang Grégoire Broquet Yi Yin Jakob Zscheischler Bertrand Guenet Daniel SGoll Ashley-P.Ballantyne Hui Yang Chunjing Qiu Dan Zhu | 2021 | National Science Review2021，8，2： | 3 |
| 4 | Anchor-based manifold binary pattern for finger vein recognition显示文摘This paper proposes a novel learning method of binary local features for recognition of the finger vein. The learning methods existing in local features for image recognition intend to maximize the data variance, reduce quantitative errors, exploit the contextual information within each binary code, or utilize the label information, which all ignore the local manifold structure of the original data. The manifold structure actually plays a very important role in binary code learning, but constructing a similarity matrix for large-scale datasets involves a lot of computational and storage cost. The study attempts to learn a map, which can preserve the manifold structure between the original data and the learned binary codes for large-scale situations. To achieve this goal, we present a learning method using an anchor-based manifold binary pattern(AMBP) for finger vein recognition. Specifically, we first extract the pixel difference vectors(PDVs) in the local patches by calculating the differences between each pixel and its neighbors. Second,we construct an asymmetric graph, on which each data point can be a linear combination of its K-nearest neighbor anchors, and the anchors are randomly selected from the training samples. Third, a feature map is learned to project these PDVs into low-dimensional binary codes in an unsupervised manner, where(i) the quantization loss between the original real-valued vectors and learned binary codes is minimized and(ii) the manifold structure of the training data is maintained in the binary space. Additionally, the study fuses the discriminative binary descriptor and AMBP methods at the image representation level to further boost the performance of the recognition system. Finally, experiments using the MLA and PolyU databases show the effectiveness of our proposed methods. | Haiying LIU Gongping YANG Lu YANG Kun SU Yilong YIN | 2019 | Science China(Information Sciences)2019，62，5： | 2 |
| 5 | Multi-task MIML learning for pre-course student performance prediction显示文摘In higher education,the initial studying period of each course plays a crucial role for students,and seriously influences the subsequent learning activities.However,given the large size of a course’s students at universities,it has become impossible for teachers to keep track of the performance of individual students.In this circumstance,an academic early warning system is desirable,which automatically detects students with difficulties in learning(i.e.,at-risk students)prior to a course starting.However,previous studies are not well suited to this purpose for two reasons:1)they have mainly concentrated on e-learning platforms,e.g.,massive open online courses(MOOCs),and relied on the data about students’online activities,which is hardly accessed in traditional teaching scenarios;and 2)they have only made performance prediction when a course is in progress or even close to the end.In this paper,for traditional classroom-teaching scenarios,we investigate the task of pre-course student performance prediction,which refers to detecting at-risk students for each course before its commencement.To better represent a student sample and utilize the correlations among courses,we cast the problem as a multi-instance multi-label(MIML)problem.Besides,given the problem of data scarcity,we propose a novel multi-task learning method,i.e.,MIML-Circle,to predict the performance of students from different specialties in a unified framework.Extensive experiments are conducted on five real-world datasets,and the results demonstrate the superiority of our approach over the state-of-the-art methods. | Yuling Ma Chaoran Cui Jun Yu Jie Guo Gongping Yang Yilong Yin | 2020 | Frontiers of Computer Science2020，14，5： | 1 |
| 6 | A hybrid biometric identification framework for high security applications显示文摘 | Xuzhou LI Yilong YIN Yanbin NING Gongping YANG Lei PAN | 2015 | Frontiers of Computer Science2015，9，3： | 1 |
| 7 | Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows显示文摘We introduce a novel method using a new generative model that automatically learns effective representations of the target and background appearance to detect,segment and track each instance in a video sequence.Differently from current discriminative tracking-by-detection solutions,our proposed hierarchical structural embedding learning can predict more highquality masks with accurate boundary details over spatio-temporal space via the normalizing flows.We formulate the instance inference procedure as a hierarchical spatio-temporal embedded learning across time and space.Given the video clip,our method first coarsely locates pixels belonging to a particular instance with Gaussian distribution and then builds a novel mixing distribution to promote the instance boundary by fusing hierarchical appearance embedding information in a coarse-to-fine manner.For the mixing distribution,we utilize a factorization condition normalized flow fashion to estimate the distribution parameters to improve the segmentation performance.Comprehensive qualitative,quantitative,and ablation experiments are performed on three representative video instance segmentation benchmarks(i.e.,YouTube-VIS19,YouTube-VIS21,and OVIS)and the effectiveness of the proposed method is demonstrated.More impressively,the superior performance of our model on an unsupervised video object segmentation dataset(i.e.,DAVIS19)proves its generalizability.Our algorithm implementations are publicly available at https://github.com/zyqin19/HEVis. | Zheyun Qin Xiankai Lu Xiushan Nie Dongfang Liu Yilong Yin Wenguan Wang | 2023 | IEEE/CAA Journal of Automatica Sinica2023，10，5： | 1 |
| 8 | Finger vein recognition based on deformation information显示文摘The measurement of the vessel pattern in fingers is a superior method for identifying individuals owing to its convenience and the security it offers. We introduce in this paper a new perspective to accomplish finger vein recognition. This method, which regards deformations as discriminative information, is distinct from existing methods that attempt to prevent the influence of deformations. The proposed technique is based on the observation that regular deformation, which corresponds to a posture change, can only exist in genuine vein patterns. In terms of methodology, we incorporate optimized matching to generate pixelbased 2 D displacements that correspond to deformations. The texture of uniformity extracted from the displacement fields is taken as the final matching score. Evaluated on two publicly available databases,Poly U and SDU-MLA, extensive experiments demonstrated that the discriminability of the new feature derived from deformations is preferable. The equal error rate(EER) achieved is the lowest compared to that of state-of-the-art techniques. | Xianjing MENG Xiaoming XI Gongping YANG Yilong YIN | 2018 | Science China(Information Sciences)2018，61，5： | 1 |
| 9 | Spherical torus-based video hashing for near-duplicate video detection显示文摘Dear editor,With the rapid development of multimedia technologies,users can easily generate and share multiple videos through the Internet.Similarly,numerous illegal and useless near-duplicate videos generated through simple reformatting,transformation,and editing appear on the web.These nearduplicate videos inconvenience users when they are surfing the Internet and are considered a copyright infringement.Robust video hashing,which is also called video fingerprinting,does not require access to the video contents at the time of creation and can be used to detect existing contents.In general, | Xiushan NIE Yane CHAI Ju LIU Jiande SUN Yilong YIN | 2016 | Science China(Information Sciences)2016，59，5： | 1 |
| 10 | Non-negative locality-constrained vocabulary tree for finger vein image retrieval显示文摘Finger vein image retrieval is a biometric identification technology that has recently attracted a lot of attention. It has the potential to reduce the search space and has attracted a considerable amount of research effort recently. It is a challenging problem owing to the large number of images in biometric databases and the lack of efficient retrieval schemes. We apply a hierarchical vocabulary tree modelbased image retrieval approach because of its good scalability and high efficiency. However, there is a large accumulative quantization error in the vocabulary tree (VT) model that may degrade the retrieval precision. To solve this problem, we improve the vector quantization coding in the VT model by introducing a non-negative locality-constrained constraint: the non-negative locality-constrained vocabulary tree-based image retrieval model. The proposed method can effectively improve coding performanee and the discriminative power of local features. Extensive experiments on a large fused finger vein database demonstrate the superiority of our encoding method. Experimental results also show that our retrieval strategy achieves better performanee than other state-of-theart methods, while maintaining low time complexity. | Kun SU Gongping YANG Lu YANG Peng SU Yilong YIN | 2019 | Frontiers of Computer Science2019，13，2： | 1 |
| 11 | Fractional-order Sparse Representation for Image Denoising显示文摘Sparse representation models have been shown promising results for image denoising. However, conventional sparse representation-based models cannot obtain satisfactory estimations for sparse coefficients and the dictionary. To address this weakness, in this paper, we propose a novel fractional-order sparse representation(FSR) model. Specifically, we cluster the image patches into K groups, and calculate the singular values for each clean/noisy patch pair in the wavelet domain. Then the uniform fractional-order parameters are learned for each cluster.Then a novel fractional-order sample space is constructed using adaptive fractional-order parameters in the wavelet domain to obtain more accurate sparse coefficients and dictionary for image denoising. Extensive experimental results show that the proposed model outperforms state-of-the-art sparse representation-based models and the block-matching and 3D filtering algorithm in terms of denoising performance and the computational efficiency. | Leilei Geng Zexuan Ji Yunhao Yuan Yilong Yin | 2018 | IEEE/CAA Journal of Automatica Sinica2018，5，2： | 1 |
| 12 | Sequential quadratic programming enhanced backtracking search algorithm显示文摘 | Wenting ZHAO Lijin WANG Yilong YIN Bingqing WANG Yuchun TANG | 2018 | Frontiers of Computer Science2018，12，2： | 1 |
| 13 | K-Means based fingerprint segmentation with sensor interoperability显示文摘 | Yang Gongping Zhou Guangtong Yin Yilong | 2010 | Eurasip Journal on Advances in Signal Processing2010，，： | 1 |
| 14 | Ridge Distance Estimation in Fingerprint Images:Algorithm and Performance Evaluation显示文摘 | Jie Tian Xiukun Yang | 2004 | EURASIP Journal on Applied Signal Processing2004，2，4： | 1 |
| 15 | Preparation and magnetic properties of anisotropic Nd2Fe14B/Sm2Co17 hybrid-bonded magnets显示文摘In the present work, anisotropic Nd2 Fe14 B/Sm2 Co17 hybrid-bonded magnets were prepared with different Nd-Fe-B contents. It is found that the particle distributions and ratios between the two magnetic phases have important roles in the magnetic properties, microstructures and thermal stability of the magnets. With increase of Nd-Fe-B content, the saturation magnetization of the anisotropic hybrid magnet increases significantly, however, coercivity decreases, and the demagnetization curves show magnetically single-phase behavior. The anisotropic Nd2 Fe14 B/Sm2 Co17 hybrid-bonded magnets exhibit a maximum energy product and remanence of 14.15 MGOe and 99.53 A·m2/kg, respectively, when the NdFe-B content is 70 wt% at room temperature. Furthermore, the hybrid magnets also have better thermal stability at elevated temperatures due to the interaction between the two magnetic particles. | Xueguo Yin Yue Sui Qiqi Yang Qian Shen Yilong Ma Bin Shao Jianchun Sun Donglin Guo | 2019 | Journal of Rare Earths2019，37，10： | 1 |
| 16 | Recursive narrative alignment for movie narrating显示文摘Movie narrating can enable the capture of not only the subject matter but also the emotive essence of the subject.For example,'having a good time'or'feeling exhausted',which relates to the narrative of'holding a birthday party'.Movie narrating converts the human-like expressivity in movie shots(i.e.,sets of film frames)into a cohesive and coherent narrative(i.e.,sentences that tell a logical story). | Zhongyi HAN Hongbo WU Benzheng WEI Yilong YIN Shuo LI | 2020 | Science China(Information Sciences)2020，63，7： | 1 |
| 17 | Finger vein recognition with manifold learning 显示文摘 | LIU Zhi YIN Yilong WANG Hongjun | 2010 | Journal of Network and Computer Applications2010，，33： | 1 |
| 18 | Physical mechanism of field modulation effects in ion implanted edge termination of vertical GaN Schottky barrier diodes显示文摘In this study,the physical properties of F ion-implanted GaN were thoroughly studied,and the related electric-field modulation mechanisms in ion-implanted edge termination were revealed.Transmission electron microscopy re.sults indicate that the ion-implanted region maintains a single-crystal structure even with the implantation of high-energy F ions,indicating that the high resistivity of the edge termination region is not induced by amorphization.Alternately,ion implantation-induced deep levels could compensate the electrons and lead to a highly resistive layer In addition to the bulk ffect,the direct bombardment of high-energy F ions resulted in a rough and nitrogen-deficient surface,which was confirmed via atomic force microscopy(AFM)and X-ray photoelectron spectroscopy,The implanted surface with a large density of nitrogen vacancies can accommodate electrons,and it is more conductive than the bulk in the implanted region,which is validated via spreading resistance profiling and conductive AFM measurements.Under reverse bias,the implanted surface can spread the potential in the lateral direction,whereas the acceptor traps capture electrons acting as space charges,shifting the peak electric field into the bulk region in the vertical direction.As a result,the Schottky barrier diode terminated with high-energy F ion-implanted regions exhibits a breakdown voltage of over 1.2 kv. | Ruiyuan Yin Chiachia Li Bin Zhang Jinyan Wang Yunyi Fu Cheng P.Wen Yilong Hao Bo Shen Maojun Wang | 2022 | Fundamental Research2022，2，4： | 1 |
| 19 | Singular points detection based on multi-resolution in finger-print images 显示文摘 | Weng Dawei Yin Yilong Yang Dong | 2011 | Neurocomputing2011，74，17： | 1 |
| 20 | Cuckoo search with varied scaling factor显示文摘 | Lijin WANG Yilong YIN Yiwen ZHONG | 2020 | Frontiers of Computer Science2020，14，1： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员