利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

212 条记录 (耗时 0.03 秒)

    HARDWARE ADAPTIVE MULTI-MODEL SCHEDULING
    81.
    发明公开
    HARDWARE ADAPTIVE MULTI-MODEL SCHEDULING 审中-公开

    公开(公告)号：US20240185587A1

    公开(公告)日：2024-06-06

    申请号：US18556636

    申请日：2021-08-16

    申请人： Baidu.com Times Technology (Beijing) Co., Ltd.

    发明人： Haofeng KOU ,  Xing LI ,  Huimeng ZHENG ,  Lei WANG ,  Zhen CHEN

    IPC分类号： G06V10/776 ,  G06V10/82 ,  G06V10/94

    CPC分类号： G06V10/776 ,  G06V10/82 ,  G06V10/955

    摘要： Modem deep neural network (DNN) models have many layers with a single layer potentially involving large matrix multiplications. Such heavy calculation brings challenges to deploy such DNN models on a single edge device, which has relatively limited computation resources. Therefore, multiple and even heterogeneous edge devices may be required for applications with stringent latency requirements. Disclosed in the present patent documents are embodiments of a model scheduling framework that schedules multiple models on a heterogeneous platform. Two different approaches, model first scheduling (MFS) and hardware first scheduling (HFS), are presented to allocate a group of models for a service into corresponding heterogeneous edge devices, including CPU, VPU and GPU. Experimental results prove the effectiveness of the MFS and HFS methods for improving the inference speed of single and multiple AI-based services.

    ROBUST AND EFFICIENT BLIND SUPER-RESOLUTION USING VARIATIONAL KERNEL AUTOENCODER
    82.
    发明公开
    ROBUST AND EFFICIENT BLIND SUPER-RESOLUTION USING VARIATIONAL KERNEL AUTOENCODER 审中-公开

    公开(公告)号：US20240185386A1

    公开(公告)日：2024-06-06

    申请号：US18556653

    申请日：2021-09-30

    申请人： Baidu USA, LLC ,  Baidu.com Times Technology (Beijing) Co., Ltd.

    发明人： Zhihong PAN ,  Baopu LI ,  Dongliang HE ,  Wenhao WU ,  Tianwei LIN

    IPC分类号： G06T3/4076 ,  G06T3/4046

    CPC分类号： G06T3/4076 ,  G06T3/4046

    摘要： Image super-resolution (SR) refers to the process of recovering high-resolution (HR) images from low-resolution (LR) inputs. Blind image SR is a more challenging task which involves unknown blurring kernels and characterizes the degradation process from HR to LR. In the present disclosure, embodiments of a variational autoencoder (VAE) are leveraged to train a kernel autoencoder for more accurate degradation representation and more efficient kernel estimation. In one or more embodiments, a kernel-agnostic loss is used to learn more robust kernel features in the latent space from LR inputs without using ground-truth kernel references. In addition, attention-based adaptive pooling is introduced to improve kernel estimation accuracy, and spatially non-uniform kernel features are passed into SR restoration resulting in additional kernel estimation error tolerance. Extensive experiments on synthetic and real-world images show that embodiments of the presented model outperform state-of-the-art methods significantly with the peak signal-to-noise ratio (PSNR) raised considerably.

    Method and apparatus for aligning paragraph and video
    85.
    发明授权
    Method and apparatus for aligning paragraph and video 有权

    公开(公告)号：US11758088B2

    公开(公告)日：2023-09-12

    申请号：US16703075

    申请日：2019-12-04

    申请人： Baidu.com Times Technology (Beijing) Co., Ltd. ,  Baidu USA LLC

    发明人： Hao Tian ,  Xi Chen ,  Jeff ChienYu Wang ,  Daming Lu

    IPC分类号： H04N7/025 ,  G06F16/45

    CPC分类号： H04N7/025 ,  G06F16/45

    摘要： Embodiments of the present disclosure provide a method and apparatus for aligning a paragraph and a video. The method may include: acquiring a commentary and a candidate material resource set corresponding to the commentary, a candidate material resource being a video or an image; acquiring a matching degree between each paragraph in the commentary and each candidate material resource in the candidate material resource set; and determining a candidate material resource sequence corresponding to the each paragraph in the commentary based on the matching degrees between the paragraphs in the commentary and the candidate material resources, playing durations of the candidate material resources and text lengths of the paragraphs in the commentary, an image playing duration being a preset image playing duration.