Huawei

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..

On functionality separation for green mobile networks: concept study over LTE

Abstract: Traditional wireless networks are designed for ubiquitous network access provision with low-rate voice services, which thus preserve the homogeneous architecture and tight coupling for infrastructures such as base stations. With the traffic explosion and the paradigm shift from voice-oriented services to data-oriented services, traditional homogeneous architecture no longer maintains its optimality, and heterogeneous deployment with flexible network control capability becomes a promising evolution direction. To achieve this goal, in this article, we propose a two-layer network functionality separation scheme, targeting at low control signaling overhead and flexible network reconfiguration for future mobile networks. The proposed scheme is shown to support all kinds of user activities defined in current networks. Moreover, we give two examples to illustrate how the proposed scheme can be applied to multicarrier networks and suggest two important design principles for future green networks. Numerical results show that the proposed scheme achieves significant energy reduction over traditional LTE networks, and can be recommended as a candidate solution for future green mobile networks.

Methods and apparatus for event-driven routing

Abstract: A router routes data packets. The router includes input physical channels for incrementally receiving portions of the data packets, and output physical channels. The router further includes data buffers, coupled with the input and output physical channels, for storing the portions of the data packets. The router further includes control circuitry, coupled with the input and output physical channels and the data buffers, for generating virtual channel assignments that assign virtual channels to the data packets, and generating physical channel assignments that assign the output physical channels to the virtual channels. Each of the assignments is generated in response to queued arrival and credit events. The portions of the data packets are forwarded from the data buffers to the output physical channels according to the generate virtual and physical channel assignments.

GLAD: Global–Local-Alignment Descriptor for Scalable Person Re-Identification

Abstract: The huge variance of human pose and the misalign-ment of detected human images significantly increase the difficulty of pedestrian image matching in person Re-Identification (Re-ID). Moreover, the massive visual data being produced by surveillance video cameras requires highly efficient person Re-ID systems. Targeting to solve the first problem, this work proposes a robust and discriminative pedestrian image descriptor, namely, the Global–Local-Alignment Descriptor (GLAD). For the second problem, this work treats person Re-ID as image retrieval and proposes an efficient indexing and retrieval framework. GLAD explicitly leverages the local and global cues in the human body to generate a discriminative and robust representation. It consists of part extraction and descriptor learning modules, where several part regions are first detected and then deep neural networks are designed for representation learning on both the local and global regions. A hierarchical indexing and retrieval framework is designed to perform offline relevance mining to eliminate the huge person ID redundancy in the gallery set, and accelerate the online Re-ID procedure. Extensive experimental results on widely used public benchmark datasets show GLAD achieves competitive accuracy compared to the state-of-the-art methods. On a large-scale person, with the Re-ID dataset containing more than 520 K images, our retrieval framework significantly accelerates the online Re-ID procedure while also improving Re-ID accuracy. Therefore, this work has the potential to work better on person Re-ID tasks in real scenarios.

Learning Channel-Wise Interactions for Binary Convolutional Neural Networks

Abstract: In this paper, we propose a channel-wise interaction based binary convolutional neural network learning method (CI-BCNN) for efficient inference. Conventional methods apply xnor and bitcount operations in binary convolution with notable quantization error, which usually obtains inconsistent signs in binary feature maps compared with their full-precision counterpart and leads to significant information loss. In contrast, our CI-BCNN mines the channel-wise interactions, through which prior knowledge is provided to alleviate inconsistency of signs in binary feature maps and preserves the information of input samples during inference. Specifically, we mine the channel-wise interactions by a reinforcement learning model, and impose channel-wise priors on the intermediate feature maps through the interacted bitcount function. Extensive experiments on the CIFAR-10 and ImageNet datasets show that our method outperforms the state-of-the-art binary convolutional neural networks with less computational and storage cost.

Discovering Meta-Paths in Large Heterogeneous Information Networks

Abstract: The Heterogeneous Information Network (HIN) is a graph data model in which nodes and edges are annotated with class and relationship labels. Large and complex datasets, such as Yago or DBLP, can be modeled as HINs. Recent work has studied how to make use of these rich information sources. In particular, meta-paths, which represent sequences of node classes and edge types between two nodes in a HIN, have been proposed for such tasks as information retrieval, decision making, and product recommendation. Current methods assume meta-paths are found by domain experts. However, in a large and complex HIN, retrieving meta-paths manually can be tedious and difficult. We thus study how to discover meta-paths automatically. Specifically, users are asked to provide example pairs of nodes that exhibit high proximity. We then investigate how to generate meta-paths that can best explain the relationship between these node pairs. Since this problem is computationally intractable, we propose a greedy algorithm to select the most relevant meta-paths. We also present a data structure to enable efficient execution of this algorithm. We further incorporate hierarchical relationships among node classes in our solutions. Extensive experiments on real-world HIN show that our approach captures important meta-paths in an efficient and scalable manner.