转自:http://emuch.net/t.php?tid=6226942 前段时间比较幸运地中了一篇spl,把自己浅薄的经验写出来,直接从自己博客上转过来,分享给大家,望抛砖引玉吧~~~ 从投稿到录用经过近三个月最终论文成功接收,博士期间第一篇SCI,前面的辛苦与努力总算得到回报. 认真总结,希望对有心投此期刊的童鞋有所帮助,也当做自己的经验,以后备用. 期刊整体情况IEEE signal processing letters (以下简称SPL)在信号处理领域影响力还是很不错的,与IEEE T
Meta Learning/ Learning to Learn/ One Shot Learning/ Lifelong Learning 2018-08-03 19:16:56 本文转自:https://github.com/floodsung/Meta-Learning-Papers 1 Legacy Papers [1] Nicolas Schweighofer and Kenji Doya. Meta-learning in reinforcement learning. Neural
Xiaoguang Tu (涂晓光): CV: Ph.D. Candidate of School of Communication and Information Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, P.R. China. Research field: Face Recognition; Medical Image Processing; Compute
附录二:按SCI影响因子排序的前50人工智能期刊列表 出版物名称,影响因子 IEEE TRANSACTIONS ON FUZZY SYSTEMS, 6.701 International Journal of Neural Systems, 6.085 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 6.077 IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATIO
论文地址:用于端到端语音增强的卷积递归神经网络 论文代码:https://github.com/aleXiehta/WaveCRN 引用格式:Hsieh T A, Wang H M, Lu X, et al. WaveCRN: An efficient convolutional recurrent neural network for end-to-end speech enhancement[J]. IEEE Signal Processing Letters, 2020, 27: 2149
一位cornell的教授做的计算机类期刊会议依据Microsoft Research引用数的排名 link:http://www.cs.cornell.edu/andru/csconf.html The following are the journals and conferences in computer science that have published at least 100 papers (2003–2013), with at least 5 citations per pa
Paper about Event Detection. #@author: gr #@date: 2014-03-15 #@email: forgerui@gmail.com 看一些相关的论文. 1. <Efficient Visual Event Detection using Volumetric Features> ICCV 2005 扩展2D box 特征到3D时空特征. 构建一个实时的检测器基于容积特征. 采用传统的兴趣点方法检测事件. 2. <ARMA-HMM: A New
本文来自<ArcFace: Additive Angular Margin Loss for Deep Face Recognition>,时间线为2018年1月.是洞见的作品,一作目前在英国帝国理工大学读博. CNN近些年在人脸识别上效果显著,为了增强softmax loss的辨识性特征学习能力,Sphereface提出的multiplicative angular margin,参考文献[43,44]提出的additive cosine margin等分别通过将角度边际和余弦边际整合到lo
本文来自<MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices>,时间线为2018年11月.是作者分别来自CMU和uark学校. 0 引言 随着DCNN的普及,在目标检测,目标分割等领域都有不小的进步,然而其较高准确度背后却是大量的参数和计算量.如AlexNet需要61百万参数量,VGG16需要138百万参数量,Resnet-50需要25百万参数量.Densenet190(k=40)需要40百万参数量.