图像检索（Image Retrieval）专知荟萃

入门学习

1. 相似图片搜索的原理 阮一峰
   • [http://www.ruanyifeng.com/blog/2011/07/principle_of_similar_image_search.html]
2. Google 图片搜索的原理是什么？
   • [https://www.zhihu.com/question/19726630]
3. 基于内容的图像检索技（CBIR）术相术介绍
   • [http://blog.csdn.net/kezunhai/article/details/11614989]
4. 图像检索：基于内容的图像检索技术
   • [http://yongyuan.name/blog/cbir-technique-summary.html]
5. 基于内容的图像检索技术
   • [http://www.cs.cmu.edu/~juny/Prof/papers/Part2-CBIR.pdf]
6. 图像检索：CNN卷积神经网络与实战 CNN for Image Retrieval
   • [http://yongyuan.name/blog/CBIR-CNN-and-practice.html]
7. 用Python和OpenCV创建一个图片搜索引擎的完整指南
   • [http://blog.csdn.net/kezunhai/article/details/46417041]

综述

1. Recent Advance in Content-based Image Retrieval: A Literature Survey. Wengang Zhou, Houqiang Li, and Qi Tian 2017
   • [https://arxiv.org/pdf/1706.06064.pdf]
2. Intelligent Image Retrieval Techniques: A Survey 2014
   • [http://www.sciencedirect.com/science/article/pii/S1665642314716098]
3. A survey on content based image retrieval. 2013
   • [http://ieeexplore.ieee.org/document/6496719/]

进阶文章

2011

1. Using Very Deep Autoencoders for Content-Based Image Retrieval
   • [https://www.cs.toronto.edu/~hinton/absps/esann-deep-final.pdf]

2013

1. Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data
   • [http://arxiv.org/abs/1312.4740]

2014

1. Neural Codes for Image Retrieval
   • [http://arxiv.org/abs/1404.1777]
2. Efficient On-the-fly Category Retrieval using ConvNets and GPUs
   • [http://arxiv.org/abs/1407.4764]

2015

1. Learning visual similarity for product design with convolutional neural networks SIGGRAPH 2015
   • [http://www.cs.cornell.edu/~kb/publications/SIG15ProductNet.pdf]
2. Exploiting Local Features from Deep Networks for Image Retrieval
   • [https://arxiv.org/abs/1504.05133]
3. Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network ICCV 2015
   • [http://arxiv.org/abs/1505.07922]
4. Where to Buy It: Matching Street Clothing Photos in Online Shops ICCV 2015
   • [http://www.tamaraberg.com/papers/street2shop.pdf]
5. Aggregating Deep Convolutional Features for Image Retrieval
   • [http://arxiv.org/abs/1510.07493]
6. Particular object retrieval with integral max-pooling of CNN activations
   • [https://arxiv.org/abs/1511.05879]

2016

1. Deep Image Retrieval: Learning global representations for image search ECCV 2016
   • [https://arxiv.org/abs/1604.01325]
2. Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks. CVPR 2016
   • [http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Lin_Learning_Compact_Binary_CVPR_2016_paper.pdf]
3. Fast Training of Triplet-based Deep Binary Embedding Networks. CVPR 2016
   • [http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhuang_Fast_Training_of_CVPR_2016_paper.pdf]
4. Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles. CVPR 2016
   • [http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Liu_Deep_Relative_Distance_CVPR_2016_paper.pdf]
5. Bags of Local Convolutional Features for Scalable Instance Search. Best Poster Award at ICMR 2016.
   • [https://imatge-upc.github.io/retrieval-2016-icmr/]
6. Group Invariant Deep Representations for Image Instance Retrieval
   • [http://arxiv.org/abs/1601.02093]
7. Natural Language Object Retrieval
   • [http://arxiv.org/abs/1511.04164]
8. Faster R-CNN Features for Instance Search
   • [http://imatge-upc.github.io/retrieval-2016-deepvision/]
9. Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
   • [https://arxiv.org/abs/1606.06811]
10. Adversarial Training For Sketch Retrieval
    • [http://arxiv.org/abs/1607.02748]
11. DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations
    • [http://personal.ie.cuhk.edu.hk/~lz013/projects/DeepFashion.html]
12. CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
    • [http://cmp.felk.cvut.cz/~radenfil/projects/siamac.html]
13. PicHunt: Social Media Image Retrieval for Improved Law Enforcement
    • [http://arxiv.org/abs/1608.00905]
14. The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies
    • [http://sketchy.eye.gatech.edu/]
15. End-to-end Learning of Deep Visual Representations for Image Retrieval
    • [http://www.xrce.xerox.com/Research-Development/Computer-Vision/Learning-Visual-Representations/Deep-Image-Retrieval]
16. What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
    • [https://arxiv.org/abs/1611.01640]

2017

1. AMC: Attention guided Multi-modal Correlation Learning for Image Search. CVPR 2017
   • [https://arxiv.org/abs/1704.00763]
2. Deep image representations using caption generators. ICME 2017
   • [https://arxiv.org/abs/1705.09142]
3. One-Shot Fine-Grained Instance Retrieval. ACM MM 2017
   • [https://arxiv.org/abs/1707.00811]
4. Selective Deep Convolutional Features for Image Retrieval. ACM MM 2017
   • [https://arxiv.org/abs/1707.00809]
5. Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval. ICCV 2017
   • [https://arxiv.org/abs/1708.02531]
6. Image2song: Song Retrieval via Bridging Image Content and Lyric Words. ICCV 2017
   • [https://arxiv.org/abs/1708.05851]
7. SIFT Meets CNN: A Decade Survey of Instance Retrieval
   • [http://arxiv.org/abs/1608.01807]
8. Image Retrieval with Deep Local Features and Attention-based Keypoints
   • [https://arxiv.org/abs/1612.05478]

Tutorial

1. CVPR’16 Tutorial on Image Tag Assignment, Refinement and Retrieval
   • [http://www.lambertoballan.net/2016/06/cvpr16-tutorial-image-tag-assignment-refinement-and-retrieval/]
2. Content-based image retrieval tutorial by Joani Mitro
   • [https://arxiv.org/pdf/1608.03811.pdf]
3. Tutorial on Image Retrieval System, (IRS)
   • [http://da.biostr.washington.edu/~sigdemos/tutorial/tutorial.pdf]

视频教程

1. Deep Image Retrieval: Learning global representations for image search
   • [https://www.youtube.com/watch?v=yT52xDML6ys]
2. Image Instance Retrieval: Overview of state-of-the-art
   • [https://www.youtube.com/watch?v=EYq-rpaZn1o]

代码

1. Neural Codes for Image Retrieval
   • [https://github.com/arbabenko/Spoc]
2. Natural Language Object Retrieval
   • [https://github.com/andrewliao11/Natural-Language-Object-Retrieval-tensorflow]
3. Bags of Local Convolutional Features for Scalable Instance Search
   • [https://github.com/imatge-upc/retrieval-2016-icmr]
4. Faster R-CNN Features for Instance Search
   • [https://github.com/imatge-upc/retrieval-2016-deepvision]
5. CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
   • [http://ptak.felk.cvut.cz/personal/radenfil/siamac/siaMAC_code.tar.gz]
6. Class-Weighted Convolutional Features for Visual Instance Search
   • [https://github.com/imatge-upc/retrieval-2017-cam]

领域专家

1. Hervé Jégou
   • [http://people.rennes.inria.fr/Herve.Jegou/]
2. Andrew Zisserman
   • [https://www.robots.ox.ac.uk/~az/]
3. Qi Tian
   • [http://www.cs.utsa.edu/~qitian/]
4. Artem Babenko
   • [https://www.hse.ru/en/org/persons/133709478]

Datasets

1. Corel 1000 and 10,000 图像数据库
   • [http://wang.ist.psu.edu/docs/related/]
2. The COREL Database for Content based Image Retrieval
   • [https://sites.google.com/site/dctresearch/Home/content-based-image-retrieval]
3. Corel-5K and Corel -10K Datasets该页面下面给出了图片的链接，可以用python写个脚本把它们爬下来。
   • [http://www.ci.gxnu.edu.cn/cbir/Dataset.aspx]
4. INSTRE，中科院计算所弄的一个数据库28543张图片，还有他们做的web检索系统ISIA。
   • [http://vipl.ict.ac.cn/isia/instre/]
5. MIRFLICKR 1M数据库，100多g.
   • [http://press.liacs.nl/mirflickr/mirdownload.html]
6. Image Similarity Triplet Dataset
   • [http://users.eecs.northwestern.edu/~jwa368/my_data.html]
7. INRIA Holidays 该数据集是Herve Jegou研究所经常度假时拍的图片（风景为主），一共1491张图，500张query（一张图一个group）和对应着991张相关图像，已提取了128维的SIFT点4455091个，visual dictionaries来自Flickr60K.
   • [http://lear.inrialpes.fr/~jegou/data.php]
8. Oxford Buildings Dataset，5k Dataset images，有5062张图片，是牛津大学VGG小组公布的，在基于词汇树做检索的论文里面，这个数据库出现的频率极高。
   • [http://www.robots.ox.ac.uk/~vgg/data/oxbuildings/]
9. Oxford Paris，The Paris Dataset，oxford的VGG组从Flickr搜集了6412张巴黎旅游图片，包括Eiffel Tower等。
   • [http://www.robots.ox.ac.uk/~vgg/data/parisbuildings/]
10. 201Books and CTurin180 The CTurin180 and 201Books Data Sets，2011.5，Telecom Italia提供于Compact Descriptors for Visual Search，该数据集包括：Nokia E7拍摄的201本书的封面图片（多视角拍摄，各6张），共1.3GB； Turin市180个建筑的视频图像，拍摄的camera有Galaxy S、iPhone 3、Canon A410、Canon S5 IS，共2.7GB
    • [http://pacific.tilab.com/www/datasets/]
11. Stanford Mobile Visual Search，Stanford Mobile Visual Search Dataset，2011.2，stanford提供，包括8种场景，如CD封面、油画等，每组相关图片都是采自不同相机（手机），所有场景共500张图；以后又发布了一个patch数据集，Compact Descriptors for Visual Search Patches Dataset，校对了相同patch。
    • [https://purl.stanford.edu/rb470rw0983]
12. UKBench，UKBench database，2006.7，Henrik Stewénius在他CVPR06文章中提供的数据集，图像都为640x480，每个group有4张图，文件接近2GB，提供visual words。
    • [http://vis.uky.edu/~stewe/ukbench/]

---

初步版本，水平有限，有错误或者不完善的地方，欢迎大家提建议和补充，会一直保持更新，本文为专知内容组原创内容，未经允许不得转载，如需转载请发送邮件至fangquanyi@gmail.com 或 联系微信专知小助手（Rancho_Fang）

敬请关注http://www.zhuanzhi.ai 和关注专知公众号，获取第一手AI相关知识