<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[Hello World]]></title><description><![CDATA[paper reading]]></description><link>https://blog.youkuaiyun.com/fuxin607</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; fuxin607]]></copyright><item><title><![CDATA[跨模态预训练迁移]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/122957748</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/122957748</guid><author>fuxin607</author><pubDate>Thu, 17 Feb 2022 19:50:36 +0800</pubDate><description><![CDATA[1.ViLD，Zero-Shot Detection via Vision and Language Knowledge Distillation。code
2.OVR-CNN，Open-Vocabulary Object Detection Using Captions[CVPR2021]。code
3.LSeg，Language-driven Semantic Segmentation[ICLR2022]。code
4.OpenSeg，Open-Vocabulary Image Segmentatio.]]></description><category></category></item><item><title><![CDATA[跨模态预训练]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/121876539</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/121876539</guid><author>fuxin607</author><pubDate>Sat, 11 Dec 2021 17:19:01 +0800</pubDate><description><![CDATA[1.LXMERT，LXMERT: Learning Cross-Modality Encoder Representations from Transformers[EMNLP2019]。[code]（https://github.com/airsplay/lxmert）


]]></description><category></category></item><item><title><![CDATA[语义分割最新进展]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/80415093</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/80415093</guid><author>fuxin607</author><pubDate>Sat, 15 Aug 2020 10:11:14 +0800</pubDate><description><![CDATA[https://www.jeremyjordan.me/semantic-segmentation/]]></description><category></category></item><item><title><![CDATA[计算机视觉中的长尾问题]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/105253176</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/105253176</guid><author>fuxin607</author><pubDate>Wed, 01 Apr 2020 19:13:43 +0800</pubDate><description><![CDATA[现实生活中的计算视觉问题往往会存在长尾问题，即类别的数据量分布不均衡，有的类样本非常多，而有的类却非常少。

1.单标签分类。
2.多标签分类。
3.目标检测。
4.语义分割。


...]]></description><category></category></item><item><title><![CDATA[如何做学术研究]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/104098633</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/104098633</guid><author>fuxin607</author><pubDate>Tue, 28 Jan 2020 12:10:47 +0800</pubDate><description><![CDATA[翻译MIT Bill Freeman教授 http://people.csail.mit.edu/billf/publications/How_To_Do_Research.pdf

]]></description><category></category></item><item><title><![CDATA[image caption研究进展]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/80506416</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/80506416</guid><author>fuxin607</author><pubDate>Fri, 08 Nov 2019 12:10:20 +0800</pubDate><description><![CDATA[主要介绍image caption最近的几篇文章，及其相关的应用。


1.Google NIC，Show and Tell: A Neural Image Caption Generator [CVPR2015]。
2.Hard(soft)-Attention，Show, Attend and Tell: Neural Image Caption Generation with Visual A...]]></description><category></category></item><item><title><![CDATA[Baby Talk and Neural Baby Talk]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/89081848</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/89081848</guid><author>fuxin607</author><pubDate>Thu, 16 May 2019 21:22:54 +0800</pubDate><description><![CDATA[Baby Talk: Understanding and Generating Image Descriptions
Neural Baby Talk


]]></description><category></category></item><item><title><![CDATA[跨媒体分析中的新任务]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/85128064</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/85128064</guid><author>fuxin607</author><pubDate>Thu, 20 Dec 2018 17:10:26 +0800</pubDate><description><![CDATA[
1.Measuring Depression Symptom Severity from Spoken Language and 3D Facial Expressions, https://arxiv.org/pdf/1811.08592.pdf.
2.Composing Text and Image for Image Retrieval - An Empirical Odyssey, ht...]]></description><category></category></item><item><title><![CDATA[深度学习500问]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/84849098</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/84849098</guid><author>fuxin607</author><pubDate>Thu, 06 Dec 2018 11:04:47 +0800</pubDate><description><![CDATA[深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，近30万字。
https://github.com/scutan90/DeepLearning-500-questions

...]]></description><category></category></item><item><title><![CDATA[读NeurIPS 2018 accepted paper list的十点感想]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/84656177</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/84656177</guid><author>fuxin607</author><pubDate>Fri, 30 Nov 2018 16:10:23 +0800</pubDate><description><![CDATA[
1.变分非常火(Variational) ，至少有35篇变分的文章。


]]></description><category></category></item><item><title><![CDATA[文本检索]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/83583467</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/83583467</guid><author>fuxin607</author><pubDate>Wed, 31 Oct 2018 14:27:29 +0800</pubDate><description><![CDATA[纯文本检索相关资料 https://github.com/NTMC-Community/awaresome-neural-models-for-semantic-match

]]></description><category></category></item><item><title><![CDATA[计算机视觉方向如何写文章]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/83063574</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/83063574</guid><author>fuxin607</author><pubDate>Tue, 23 Oct 2018 18:45:13 +0800</pubDate><description><![CDATA[
Title
Abstract
Introduction
Related Work
Proposed methods
Experiments
Conclusion and Future Work
Acknowledgements


]]></description><category></category></item><item><title><![CDATA[关于GAN的一些资料]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/82847953</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/82847953</guid><author>fuxin607</author><pubDate>Wed, 26 Sep 2018 08:05:17 +0800</pubDate><description><![CDATA[VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN  pytorch code

]]></description><category></category></item><item><title><![CDATA[ECCV2018比较有意思的paper]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/82388894</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/82388894</guid><author>fuxin607</author><pubDate>Tue, 25 Sep 2018 14:28:41 +0800</pubDate><description><![CDATA[Double JPEG Detection in Mixed JPEG Quality Factors using Deep Convolutional Neural Network 
Fighting Fake News: Image Splice Detection via Learned Self-Consistency 
Face De-Spoofing: Anti-Spoofing vi...]]></description><category></category></item><item><title><![CDATA[自然语言处理会议期刊]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/80420677</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/80420677</guid><author>fuxin607</author><pubDate>Thu, 24 May 2018 10:10:07 +0800</pubDate><description><![CDATA[列一下自然语言处理(NLP)这个小方向的： 
会议(C): 
ACL (Annual Meeting of the Association for Computational Linguistics) 
NAACL (Annual Conference of the North American Chapter of Association for Computational Linguistic...]]></description><category></category></item><item><title><![CDATA[AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/80341711</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/80341711</guid><author>fuxin607</author><pubDate>Thu, 17 May 2018 21:08:53 +0800</pubDate><description><![CDATA[这是CVPR2018一篇关于文本到图像合成的文章，paper链接https://arxiv.org/abs/1711.10485，code已经released出来了https://github.com/taoxugit/AttnGAN，作者的homepage https://sites.google.com/view/taoxu。...]]></description><category></category></item><item><title><![CDATA[文本图像跨媒体检索进展]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/80248395</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/80248395</guid><author>fuxin607</author><pubDate>Tue, 15 May 2018 11:07:54 +0800</pubDate><description><![CDATA[主要介绍9篇关于文本图像双向检索任务的9篇论文。]]></description><category></category></item><item><title><![CDATA[Finding “It”: Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/80203575</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/80203575</guid><author>fuxin607</author><pubDate>Sat, 05 May 2018 10:51:51 +0800</pubDate><description><![CDATA[这是CVPR2018 Oral的一片关于Weakly-Supervised Video Grounding的文章，paper连接http://ai.stanford.edu/~dahuang/papers/cvpr18-ramil.pdf，作者的homepage http://ai.stanford.edu/~dahuang/，code暂时没有被released出来。 
文章要做的事情： 
输入：...]]></description><category></category></item><item><title><![CDATA[Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/80190522</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/80190522</guid><author>fuxin607</author><pubDate>Fri, 04 May 2018 09:37:39 +0800</pubDate><description><![CDATA[CVPR2018一篇关于Visual Question Answering Tricks的文章，作者是2017 VQA Challenge冠军团队成员之一，paper连接https://arxiv.org/abs/1708.02711，作者的homepage https://www.damienteney.info/adventures。 
文章要做的事情： 
visual question an...]]></description><category></category></item><item><title><![CDATA[Learning Cross-modal Embeddings for Cooking Recipes and Food Images]]></title><link>https://blog.youkuaiyun.com/fuxin607/article/details/80182529</link><guid>https://blog.youkuaiyun.com/fuxin607/article/details/80182529</guid><author>fuxin607</author><pubDate>Thu, 03 May 2018 16:48:37 +0800</pubDate><description><![CDATA[这是CVPR2017的一篇做cross-modal retrieval的文章，paper和相关数据代码链接http://im2recipe.csail.mit.edu/，作者的homepage https://imatge.upc.edu/web/people/amaia-salvador。 
文章要做的事情(recipe retreival)： 
输入：image（sentence）+datas...]]></description><category></category></item></channel></rss>