Institution
Nanjing University of Information Science and Technology
Education•Nanjing, China•
About: Nanjing University of Information Science and Technology is a education organization based out in Nanjing, China. It is known for research contribution in the topics: Precipitation & Aerosol. The organization has 14129 authors who have published 17985 publications receiving 267578 citations. The organization is also known as: Nan Xin Da.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: This paper surveys state-of-the-art transfer learning algorithms in visual categorization applications, such as object recognition, image classification, and human action recognition, to find out if they can be efficiently solved.
Abstract: Regular machine learning and data mining techniques study the training data for future inferences under a major assumption that the future data are within the same feature space or have the same distribution as the training data. However, due to the limited availability of human labeled training data, training data that stay in the same feature space or have the same distribution as the future data cannot be guaranteed to be sufficient enough to avoid the over-fitting problem. In real-world applications, apart from data in the target domain, related data in a different domain can also be included to expand the availability of our prior knowledge about the target future data. Transfer learning addresses such cross-domain learning problems by extracting useful information from data in a related domain and transferring them for being used in target tasks. In recent years, with transfer learning being applied to visual categorization, some typical problems, e.g., view divergence in action recognition tasks and concept drifting in image classification tasks, can be efficiently solved. In this paper, we survey state-of-the-art transfer learning algorithms in visual categorization applications, such as object recognition, image classification, and human action recognition.
698 citations
••
TL;DR: Numerical experiments on the several benchmark and real-world data sets show that the incremental algorithm can converge to the optimal solution in a finite number of steps, and is faster than the existing batch and incremental SVOR algorithms.
Abstract: Support vector ordinal regression (SVOR) is a popular method to tackle ordinal regression problems. However, until now there were no effective algorithms proposed to address incremental SVOR learning due to the complicated formulations of SVOR. Recently, an interesting accurate on-line algorithm was proposed for training $
u $ -support vector classification ( $
u $ -SVC), which can handle a quadratic formulation with a pair of equality constraints. In this paper, we first present a modified SVOR formulation based on a sum-of-margins strategy. The formulation has multiple constraints, and each constraint includes a mixture of an equality and an inequality. Then, we extend the accurate on-line $
u $ -SVC algorithm to the modified formulation, and propose an effective incremental SVOR algorithm. The algorithm can handle a quadratic formulation with multiple constraints, where each constraint is constituted of an equality and an inequality. More importantly, it tackles the conflicts between the equality and inequality constraints. We also provide the finite convergence analysis for the algorithm. Numerical experiments on the several benchmark and real-world data sets show that the incremental algorithm can converge to the optimal solution in a finite number of steps, and is faster than the existing batch and incremental SVOR algorithms. Meanwhile, the modified formulation has better accuracy than the existing incremental SVOR algorithm, and is as accurate as the sum-of-margins based formulation of Shashua and Levin.
689 citations
••
06 Sep 2014
TL;DR: A novel explicit scale adaptation scheme is proposed, able to deal with target scale variations efficiently and effectively, and the Fast Fourier Transform is adopted for fast learning and detection in this work, which only needs 4 FFT operations.
Abstract: In this paper, we present a simple yet fast and robust algorithm which exploits the dense spatio-temporal context for visual tracking. Our approach formulates the spatio-temporal relationships between the object of interest and its locally dense contexts in a Bayesian framework, which models the statistical correlation between the simple low-level features (i.e., image intensity and position) from the target and its surrounding regions. The tracking problem is then posed by computing a confidence map which takes into account the prior information of the target location and thereby alleviates target location ambiguity effectively. We further propose a novel explicit scale adaptation scheme, which is able to deal with target scale variations efficiently and effectively. The Fast Fourier Transform (FFT) is adopted for fast learning and detection in this work, which only needs 4 FFT operations. Implemented in MATLAB without code optimization, the proposed tracker runs at 350 frames per second on an i7 machine. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods in terms of efficiency, accuracy and robustness.
683 citations
••
TL;DR: The FLUXNET2015 dataset provides ecosystem-scale data on CO 2 , water, and energy exchange between the biosphere and the atmosphere, and other meteorological and biological measurements, from 212 sites around the globe, and is detailed in this paper.
Abstract: The FLUXNET2015 dataset provides ecosystem-scale data on CO2, water, and energy exchange between the biosphere and the atmosphere, and other meteorological and biological measurements, from 212 sites around the globe (over 1500 site-years, up to and including year 2014). These sites, independently managed and operated, voluntarily contributed their data to create global datasets. Data were quality controlled and processed using uniform methods, to improve consistency and intercomparability across sites. The dataset is already being used in a number of applications, including ecophysiology studies, remote sensing studies, and development of ecosystem and Earth system models. FLUXNET2015 includes derived-data products, such as gap-filled time series, ecosystem respiration and photosynthetic uptake estimates, estimation of uncertainties, and metadata about the measurements, presented for the first time in this paper. In addition, 206 of these sites are for the first time distributed under a Creative Commons (CC-BY 4.0) license. This paper details this enhanced dataset and the processing methods, now made available as open-source codes, making the dataset more accessible, transparent, and reproducible.
681 citations
••
TL;DR: This paper study and solve the problem of personalized multi-keyword ranked search over encrypted data (PRSE) while preserving privacy in cloud computing with the help of semantic ontology WordNet, and proposes two PRSE schemes for different search intentions.
Abstract: In cloud computing, searchable encryption scheme over outsourced data is a hot research field. However, most existing works on encrypted search over outsourced cloud data follow the model of “one size fits all” and ignore personalized search intention. Moreover, most of them support only exact keyword search, which greatly affects data usability and user experience. So how to design a searchable encryption scheme that supports personalized search and improves user search experience remains a very challenging task. In this paper, for the first time, we study and solve the problem of personalized multi-keyword ranked search over encrypted data (PRSE) while preserving privacy in cloud computing. With the help of semantic ontology WordNet, we build a user interest model for individual user by analyzing the user’s search history, and adopt a scoring mechanism to express user interest smartly. To address the limitations of the model of “one size fit all” and keyword exact search, we propose two PRSE schemes for different search intentions. Extensive experiments on real-world dataset validate our analysis and show that our proposed solution is very efficient and effective.
665 citations
Authors
Showing all 14448 results
Name | H-index | Papers | Citations |
---|---|---|---|
Ashok Kumar | 151 | 5654 | 164086 |
Lei Zhang | 135 | 2240 | 99365 |
Bin Wang | 126 | 2226 | 74364 |
Shuicheng Yan | 123 | 810 | 66192 |
Zeshui Xu | 113 | 752 | 48543 |
Xiaoming Li | 113 | 1932 | 72445 |
Qiang Yang | 112 | 1117 | 71540 |
Yan Zhang | 107 | 2410 | 57758 |
Fei Wang | 107 | 1824 | 53587 |
Yongfa Zhu | 105 | 355 | 33765 |
James C. McWilliams | 104 | 535 | 47577 |
Zhi-Hua Zhou | 102 | 626 | 52850 |
Tao Li | 102 | 2483 | 60947 |
Lei Liu | 98 | 2041 | 51163 |
Jian Feng Ma | 97 | 305 | 32310 |