人工智能

Image source: Zalando ResearchWhen applying artificial intelligence to the world of fashion, in which the clothing and other articles involved have many varying individual properties, a meaningful

https://github.com/tigerneil/deep-reinforcement-learning-familydeep-reinforcement-learning-recordsExplicitly show the relationships between various techniques of deep reinforcement learn

AI 科技评论消息，Facebook人工智能研究中心FAIR负责人、深度学习三驾马车之一的Yann LeCun昨天在Facebook上评论转发了一条动态。Yann LeCun转发的这条动态来自跟他合作的一位纽约大学在读博士生Jake Zhao，介绍了一篇已经上传arXiv的论文。论文介绍了一种可以帮助GAN使用离散数据的“对抗性正则化的自动编码器”（ARAE，Adversarially Regul

https://zhuanlan.zhihu.com/p/27394105【简评】Loss Max-Pooling for Semantic Image Segmentationycszen3 天前这篇文章已经被CVPR2017收录，思想很明确，但是进行了很多数学证明，奈何数学功底不够啊，所以欢迎多多讨论交流。本文主要解决的是semantic seg

全球人工智能文章来源：arxiv.org 翻译：林一鸣文章投稿：news@top25.cnMobileNets: 面向手机视觉的高性能卷积网络摘要我们提供一类称为MobileNets的高效模型，用于移动和嵌入式视觉应用。 MobileNets是基于一个流线型的架构，它使用深度可分离的卷积来构建轻量级的深层神经网络。我们引入两个简单的全局超参数，在延迟

https://github.com/baidu-research/warp-ctc/blob/master/README.zh_cn.mdWarp-CTC是一个可以应用在CPU和GPU上高效并行的CTC代码库 （library） 介绍 CTCConnectionist Temporal Classification作为一个损失函数，用于在序列数据上进行监督式学习，不需要对齐输入数据及

https://github.com/MichaelLiang12/CVPR-2017-Abstracts-Collection/blob/master/CVPR2017_Abstract_Collection.mdCVPR 2017 Abstracts CollectionCollection of CVPR 2017, including titles, lin

Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual GroundingAkira Fukui, Dong Huk Park, Daylen Yang, Anna Rohrbach, Trevor Darrell, Marcus Rohrbach(Submitted on 6

Video Captioning with Multi-Faceted AttentionXiang Long, Chuang Gan, Gerard de Melo(Submitted on 1 Dec 2016)Recently, video captioning has been attracting an increasing amount of interes

缺少灵感？你一定需要这8篇论文 | 本周值得读 #3714小时前阅读1　　「本周值得读」是 PaperWeekly 的优质文章集合地。在这里，来自 NLP、CV、DL 等方向的学习达人，各自用精炼妙语推荐当下最新的高质量文章。　　这是第 37篇「本周值得读」➊#ICML#On orthogonality and learning recurrent

Multimodal Word DistributionsBen Athiwaratkun, Andrew Gordon Wilson(Submitted on 27 Apr 2017)Word embeddings provide point representations of words containing useful semantic information

Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-ArtJoel Janai, Fatma Güney, Aseem Behl, Andreas Geiger(Submitted on 18 Apr 2017)Recent years have witnessed a

Exploring Sparsity in Recurrent Neural NetworksSharan Narang, Gregory Diamos, Shubho Sengupta, Erich Elsen(Submitted on 17 Apr 2017)Recurrent Neural Networks (RNN) are widely used to sol

CIDEr: Consensus-based Image Description EvaluationRamakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh(Submitted on 20 Nov 2014 (v1), last revised 3 Jun 2015 (this version, v2))Automa

BLEU : 一种机器翻译自动评价方法BLEU：a Method for Automatic Evaluation of Machine Translation（1） Kishore Papineni，Salim Roukos，Todd Ward, and Wei-Jing Zhu编译： 洪洁   文章来源：多语工程技术研究中心《云翻译技术》第12期 摘要：这篇论文是关于BLE

https://arxiv.org/abs/1704.06933Lijun Wu, Yingce Xia, Li Zhao, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu(Submitted on 20 Apr 2017)In this paper, we study a new learning paradigm

WaveNet: A Generative Model for Raw AudioAaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, Koray Kavukcuoglu(

Convolutional Sequence to Sequence LearningJonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin(Submitted on 8 May 2017)The prevalent approach to sequence to sequ

Hierarchical Question-Image Co-Attention for Visual Question AnsweringJiasen Lu, Jianwei Yang, Dhruv Batra, Devi Parikh(Submitted on 31 May 2016 (v1), last revised 19 Jan 2017 (this version,

Abstract:An attentional mechanism has lately been used to improve neural machine translation (NMT) by selectively focusing on parts of the source sentence during translation. However, there has be

Hierarchical Boundary-Aware Neural Encoder for Video CaptioningLorenzo Baraldi, Costantino Grana, Rita Cucchiara(Submitted on 28 Nov 2016 (v1), last revised 10 Apr 2017 (this version, v3))

Video Captioning with Transferred Semantic AttributesYingwei Pan, Ting Yao, Houqiang Li, Tao Mei(Submitted on 23 Nov 2016)Automatically generating natural language descriptions of videos

Multimodal Memory Modelling for Video CaptioningJunbo Wang, Wei Wang, Yan Huang, Liang Wang, Tieniu Tan(Submitted on 17 Nov 2016)Video captioning which automatically translates video cli

Dynamic Memory Networks for Visual and Textual Question AnsweringCaiming Xiong, Stephen Merity, Richard Socher(Submitted on 4 Mar 2016)Neural network architectures with memory and attent

英文投稿的一点经验【转载】From： http://chl033.woku.com/article/2893317.html1. 首先一定要注意杂志的发表范围, 超出范围的千万别投,要不就是浪费时间;另外，每个杂志都有他们的具体格式要求，一定要按照他们的要求把论文写好，免得浪费时间，前些时候，我的一个同事向一个著名的英文杂志投稿，由于格式问题，人家过两个星期就退回来了，而且说了很多

Fluency-Guided Cross-Lingual Image CaptioningWeiyu Lan, Xirong Li, Jianfeng Dong(Submitted on 15 Aug 2017)Image captioning has so far been explored mostly in English, as most available d

Deep Learning based Recommender System: A Survey and New PerspectivesShuai Zhang, Lina Yao, Aixin Sun(Submitted on 24 Jul 2017 (v1), last revised 3 Aug 2017 (this version, v5))With the e

Semantic Compositional Networks for Visual CaptioningZhe Gan, Chuang Gan, Xiaodong He, Yunchen Pu, Kenneth Tran, Jianfeng Gao, Lawrence Carin, Li Deng(Submitted on 23 Nov 2016 (v1), last r

Deep Reinforcement Learning-based Image Captioning with Embedding RewardZhou Ren, Xiaoyu Wang, Ning Zhang, Xutao Lv, Li-Jia Li(Submitted on 12 Apr 2017)Image captioning is a challenging

Captioning Images with Diverse ObjectsSubhashini Venugopalan, Lisa Anne Hendricks, Marcus Rohrbach, Raymond Mooney, Trevor Darrell, Kate Saenko(Submitted on 24 Jun 2016 (v1), last revise

Steganography is collection of methods to hide secret information (“payload”) within non-secret information (“container”). Its counterpart, Steganalysis, is the　practice of determining if a message co

Dynamic Coattention Networks For Question AnsweringCaiming Xiong, Victor Zhong, Richard Socher(Submitted on 5 Nov 2016 (v1), last revised 13 Feb 2017 (this version, v3))Several deep lear

https://github.com/terryum/awesome-deep-learning-papersAwesome - Most Cited Deep Learning PapersA curated list of the most cited deep learning papers (since 2012)We believe that th

Dense-Captioning Events in VideosRanjay Krishna, Kenji Hata, Frederic Ren, Li Fei-Fei, Juan Carlos Niebles(Submitted on 2 May 2017)Most natural videos contain numerous events. For exam

Spatio-Temporal Attention Models for Grounded Video CaptioningMihai Zanfir, Elisabeta Marinoiu, Cristian Sminchisescu(Submitted on 17 Oct 2016 (v1), last revised 18 Oct 2016 (this version, v

End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question AnsweringYoungjae Yu, Hyungjin Ko, Jongwook Choi, Gunhee Kim(Submitted on 10 Oct 2016 (v1), last revised 13 De

Deep Learning for Video Classification and CaptioningZuxuan Wu, Ting Yao, Yanwei Fu, Yu-Gang Jiang(Submitted on 22 Sep 2016)Accelerated by the tremendous increase in Internet bandwidth a

Frame- and Segment-Level Features and Candidate Pool Evaluation for Video Caption GenerationRakshith Shetty, Jorma Laaksonen(Submitted on 17 Aug 2016)We present our submission to the Micro

Beyond Caption To Narrative: Video Captioning With Multiple SentencesAndrew Shin, Katsunori Ohnishi, Tatsuya Harada(Submitted on 18 May 2016)Recent advances in image captioning task have

Video captioning with recurrent networks based on frame- and video-level features and visual content classificationRakshith Shetty, Jorma Laaksonen(Submitted on 9 Dec 2015)In this paper, w