Huawei

About: Huawei is a company organization based out in Shenzhen, China. It is known for research contribution in the topics: Terminal (electronics) & Signal. 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..

Video Generation From Single Semantic Label Map

Abstract: This paper proposes the novel task of video generation conditioned on a SINGLE semantic label map, which provides a good balance between flexibility and quality in the generation process. Different from typical end-to-end approaches, which model both scene content and dynamics in a single step, we propose to decompose this difficult task into two sub-problems. As current image generation methods do better than video generation in terms of detail, we synthesize high quality content by only generating the first frame. Then we animate the scene based on its semantic meaning to obtain temporally coherent video, giving us excellent results overall. We employ a cVAE for predicting optical flow as a beneficial intermediate step to generate a video sequence conditioned on the initial single frame. A semantic label map is integrated into the flow prediction module to achieve major improvements in the image-to-video generation process. Extensive experiments on the Cityscapes dataset show that our method outperforms all competing methods.

BigDataBench: a Big Data Benchmark Suite from Internet Services

Abstract: As architecture, systems, and data management communities pay greater attention to innovative big data systems and architectures, the pressure of benchmarking and evaluating these systems rises. Considering the broad use of big data systems, big data benchmarks must include diversity of data and workloads. Most of the state-of-the-art big data benchmarking efforts target evaluating specific types of applications or system software stacks, and hence they are not qualified for serving the purposes mentioned above. This paper presents our joint research efforts on this issue with several industrial partners. Our big data benchmark suite BigDataBench not only covers broad application scenarios, but also includes diverse and representative data sets. BigDataBench is publicly available from this http URL . Also, we comprehensively characterize 19 big data workloads included in BigDataBench with varying data inputs. On a typical state-of-practice processor, Intel Xeon E5645, we have the following observations: First, in comparison with the traditional benchmarks: including PARSEC, HPCC, and SPECCPU, big data applications have very low operation intensity; Second, the volume of data input has non-negligible impact on micro-architecture characteristics, which may impose challenges for simulation-based big data architecture research; Last but not least, corroborating the observations in CloudSuite and DCBench (which use smaller data inputs), we find that the numbers of L1 instruction cache misses per 1000 instructions of the big data applications are higher than in the traditional benchmarks; also, we find that L3 caches are effective for the big data applications, corroborating the observation in DCBench.

Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments

Abstract: Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on deep neural networks, have recently emerged as potential alternatives to traditional unsupervised approaches and with sufficient training, can alleviate the shortcomings of the unsupervised methods in various real-life acoustic environments. In this light, we review recently developed, representative deep learning approaches for tackling non-stationary additive and convolutional degradation of speech with the aim of providing guidelines for those involved in the development of environmentally robust speech recognition systems. We separately discuss single- and multi-channel techniques developed for the front-end and back-end of speech recognition systems, as well as joint front-end and back-end training frameworks.

Thread-based message prioritization

Abstract: To perform thread-based message prioritization, metadata may be extracted from a received electronic message. Based on the extracted message metadata and accumulated metadata extracted from previously received messages, a message thread to which the received electronic message belongs may be identified. Based on a set of thread priority assessment criteria, a priority level for the message thread may be determined. At least part of the message thread may be processed according to the priority level. The processing may be altering a notification behavior of an electronic messaging client for electronic messages of the message thread. Thread priority assessment may be based on user-configurable criteria that may be set via a graphical user interface. Message thread identification may also be based on user-configurable criteria that may be set via a graphical user interface.

Cooperative Communication-Aware Spectrum Leasing in Cognitive Radio Networks

Abstract: In this paper, we focus on the dynamic spectrum access of two infrastructure-based cognitive radio networks, primary network and secondary network, which are collocated with each other. To improve network performance of two networks, we propose a cooperative communication-aware spectrum leasing framework, in which, primary network leverages secondary users as cooperative relays, and decides the optimal strategy on the relay selection and the price for spectrum leasing. Based on primary network's strategy, secondary network determines the length of spectrum access time it purchases from the primary network. Finally, each network allocates the total spectrum access time of the network among its end users. The above sequential decision procedure is formulated as a Stackelberg game, with primary network acting as the leader and secondary network as the follower, and a unique Nash Equilibrium (NE) point is achieved through backward induction analysis. At this NE point, both networks maximize their utilities in terms of transmission rate and revenue/payment. Meanwhile, the optimal relay selection and spectrum resource allocation among all the users are also derived based on the Nash Equilibrium. Simulation results show that both primary and secondary networks achieve higher utility by exploiting cooperative transmission under our proposed framework, which gives both networks incentive for cooperation.