#mfiohgap789432＜＞k,.

最新推荐文章于 2022-05-10 14:03:05 发布

米米碰碰碰

最新推荐文章于 2022-05-10 14:03:05 发布

阅读量490

点赞数

分类专栏： survey

本文链接：https://blog.youkuaiyun.com/weixin_43091381/article/details/110394779

版权

survey 专栏收录该内容

1 篇文章

订阅专栏

本文汇总了多个研究项目，涉及深度学习在视频流处理中的应用。从DDS到NoScope，探讨了服务器驱动的视频流、自适应宽域流分析和神经网络查询优化。同时提到了如CLIO和Pocket等方案，分别关注跨物联网和云端的深度学习管道自动化编译及无服务器分析的弹性存储。此外，还讨论了无线链接的建模和无人机视频分析的仿真器。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

prior:

dds:
Benchmarking videos used in dds. https://github.com/KuntaiDu/dds.

paper:Server-Driven Video Streaming for Deep Learning Inference
author:Kuntai Du
source:sigcomm,2020

awstream:
https://github.com/awstream/awstream

paper:AWStream: Adaptive Wide-Area Streaming Analytics
author:Ben Zhang
source:sigcomm,2018

noscope:
D. Kang, J. Emmons, F. Abuzaid, P. Bailis, and M. Zaharia. NoScope project website.
https://github.com/stanford-futuredata/noscope.
（videoedge说比它好）

paper：NoScope: Optimizing Neural Network Queries
over Video at Scale
author:Daniel Kang
source：vldb,2017

unknown：

Github repo. https://github.com/jinhuang01/CLIO.

paper:CLIO: Enabling automatic compilation of deep learning
pipelines across IoT and Cloud
source:mobicom 2020

https://github.com/hszhao/ICNet
(my paper location：desktop/wwj/paper/13…)

paper:Bridging the Edge-Cloud Barrier for Real-time Advanced Vision Analytics
author:Yiding Wang

pass:

The MIRIS source code is available at https://github.com/favyen/miris
存好的视频，偏数据库

Caesar’s demo code is available at https://github.com/USC-NSL/Caesar
偏上层

Source code and experimental data for Reducto are
available at https://github.com/reducto-sigcomm-2020/reducto.
readme太少

https://github.com/xumengwei/DeepCache
tecent ncnn,readme 太少

no help now:

仿真器：
Other attempts aimed at
modeling wireless links within the Mininet environment use
the emulation features of ns-3 for WiFi [5]
and the Lena module
of ns-3 for the cellular network (OpenNet[6]
). While OpenNet
is similar to openLEON, it is not an end-to-end emulator and
does not model the data center. An emulator for LTE using
LENA is available [15].
[5]Available at: https://github.com/mininet/mininet/wiki/Link-modeling-using-ns-3
[6]Available at: https://github.com/dlinknctu/OpenNet

DroneNet-Sim: A Learning-based Trace Simulation Framework for Control Networking in Drone Video Analytics
for Control Networking in Drone Video Analytics（无人机）
C. Qu and A. Esquivel. 2020. DroneNetsim. https://github.com/CaesarQu/DroneCOCoNet-Sim.

osdi
Pocket
Elastic Ephemeral Storage for Serverless Analytics
Pocket: https://github.com/stanford-mast/pocket, 2018.