Institution
Huawei
Company•Shenzhen, China•
About: Huawei is a company organization based out in Shenzhen, China. It is known for research contribution in the topics: Terminal (electronics) & Node (networking). The organization has 41417 authors who have published 44698 publications receiving 343496 citations. The organization is also known as: Huawei Technologies & Huawei Technologies Co., Ltd..
Papers published on a yearly basis
Papers
More filters
••
TL;DR: A novel local subspace indexing model for image search termed Subspace Indexing Model on Grassmann Manifold (SIM-GM), which is able to deal with a large number of training samples efficiently and return an effective local space model, so the recognition performance could be significantly improved.
Abstract: Conventional linear subspace learning methods like principal component analysis (PCA), linear discriminant analysis (LDA) derive subspaces from the whole data set. These approaches have limitations in the sense that they are linear while the data distribution we are trying to model is typically nonlinear. Moreover, these algorithms fail to incorporate local variations of the intrinsic sample distribution manifold. Therefore, these algorithms are ineffective when applied on large scale datasets. Kernel versions of these approaches can alleviate the problem to certain degree but face a serious computational challenge when data set is large, where the computing involves Eigen/QP problems of size N × N. When N is large, kernel versions are not computationally practical. To tackle the aforementioned problems and improve recognition/searching performance, especially on large scale image datasets, we propose a novel local subspace indexing model for image search termed Subspace Indexing Model on Grassmann Manifold (SIM-GM). SIM-GM partitions the global space into local patches with a hierarchical structure; the global model is, therefore, approximated by piece-wise linear local subspace models. By further applying the Grassmann manifold distance, SIM-GM is able to organize localized models into a hierarchy of indexed structure, and allow fast query selection of the optimal ones for classification. Our proposed SIM-GM enjoys a number of merits: 1) it is able to deal with a large number of training samples efficiently; 2) it is a query-driven approach, i.e., it is able to return an effective local space model, so the recognition performance could be significantly improved; 3) it is a common framework, which can incorporate many learning algorithms. Theoretical analysis and extensive experimental results confirm the validity of this model.
107 citations
••
TL;DR: A novel learning framework, termed Adversarial Reciprocal Point Learning (ARPL), is proposed to minimize the overlap of known distribution and unknown distributions without loss of known classification accuracy and extensive experimental results indicate that the proposed method is significantly superior to other existing approaches and achieves state-of-the-art performance.
Abstract: Open set recognition (OSR), aiming to simultaneously classify the seen classes and identify the unseen classes as unknown, is essential for reliable machine learning. The key challenge of OSR is how to reduce the empirical classification risk on the labeled known data and the open space risk on the potential unknown data simultaneously. To handle the challenge, we formulate the open space risk problem from the perspective of multi-class integration, and model the unexploited extra-class space with a novel concept Reciprocal Point. Follow this, a novel Adversarial Reciprocal Point Learning framework is proposed to minimize the overlap of known distribution and unknown distributions without loss of known classification accuracy. Specifically, each reciprocal point is learned by the extra-class space with the corresponding known category, and the confrontation among multiple known categories are employed to reduce the empirical classification risk. An adversarial margin constraint is proposed to reduce the open space risk by limiting the latent open space constructed by reciprocal points. Moreover, an instantiated adversarial enhancement method is designed to generate diverse and confusing training samples. Extensive experimental results on various benchmark datasets indicate that the proposed method is significantly superior to existing approaches and achieves state-of-the-art performance.
107 citations
••
TL;DR: The most critical points related to high-speed Volterra filter design and implementation are investigated and a simple guidance for filter complexity reduction and useful hints for channel acquisition are provided.
Abstract: Unlike ultralong coherent optical systems that seriously suffer from fiber nonlinearities, short-reach noncoherent systems such as data center interconnections, which utilize small, cheap, and low-bandwidth components, are sensitive to nonlinearities that are mainly produced by devices responsible for electrical signal amplification, modulation, and demodulation. One of the most promising schemes for these applications is the four-level pulse amplitude modulation format combined with intensity modulation and direct detection; however, it can be significantly degraded by linear and nonlinear intersymbol interference. Linear and nonlinear signal degradation can efficiently be handled by different types of equalizers. In many cases, the straightforward linear equalizer cannot lower the error rate at the acceptable level. Therefore, much stronger equalizers based on nonlinear models such as the Volterra series are proposed. Volterra filter that can also be orthogonalized by the Wiener model is well described in the existing literature, and, in this paper, we investigate the most critical points related to high-speed Volterra filter design and implementation. Several experiments are carried out in order to indicate filter requirements/complexity, acquisition, and stability. We also provide a simple guidance for filter complexity reduction and useful hints for channel acquisition.
106 citations
•
18 Sep 2003TL;DR: In this paper, the first radio station carries out communications by selectively modulating a subcarrier with which a desired transmission rate can be obtained in the second radio station, thereby providing a radio communication system that does not require the monitoring of each time slot by a terminal.
Abstract: A TDMA radio communication system using a multiple subcarrier modulation method and comprising at least a first and a second radio station. The first radio station carries out communications by selectively modulating a subcarrier with which a desired transmission rate can be obtained in the second radio station, thereby providing a radio communication system that does not require the monitoring of each time slot by a terminal.
106 citations
••
TL;DR: The K-user single-input single-output (SISO) additive white Gaussian noise (AWGN) interference channel and 2×K SISO AWGN X channel are considered, where the transmitters have delayed channel state information through noiseless feedback links.
Abstract: The $K$-user single-input single-output (SISO) AWGN interference channel and $2\times K$ SISO AWGN X channel are considered where the transmitters have the delayed channel state information (CSI) through noiseless feedback links. Multi-phase transmission schemes are proposed for both channels which possess novel ingredients, namely, multi-phase partial interference nulling, distributed interference management via user scheduling, and distributed higher-order symbol generation. The achieved degrees of freedom (DoF) values are greater than the best previously known DoFs for both channels with delayed CSI at transmitters.
106 citations
Authors
Showing all 41483 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yu Huang | 136 | 1492 | 89209 |
Xiaoou Tang | 132 | 553 | 94555 |
Xiaogang Wang | 128 | 452 | 73740 |
Shaobin Wang | 126 | 872 | 52463 |
Qiang Yang | 112 | 1117 | 71540 |
Wei Lu | 111 | 1973 | 61911 |
Xuemin Shen | 106 | 1221 | 44959 |
Li Chen | 105 | 1732 | 55996 |
Lajos Hanzo | 101 | 2040 | 54380 |
Luca Benini | 101 | 1453 | 47862 |
Lei Liu | 98 | 2041 | 51163 |
Tao Wang | 97 | 2720 | 55280 |
Mohamed-Slim Alouini | 96 | 1788 | 62290 |
Qi Tian | 96 | 1030 | 41010 |
Merouane Debbah | 96 | 652 | 41140 |