awesome-cbir-papers/README.md

## Awesome image retrieval papers

#### Local Feature Based

- [Object retrieval with large vocabularies and fast spatial matching](https://www.robots.ox.ac.uk/~vgg/publications/papers/philbin07.pdf)
- [Improving the Fisher Kernel for Large-Scale Image Classification](https://www.robots.ox.ac.uk/~vgg/rg/papers/peronnin_etal_ECCV10.pdf)
- [Visual Categorization with Bags of Keypoints](http://www.cs.princeton.edu/courses/archive/fall09/cos429/papers/csurka-eccv-04.pdf)
- [ORB: an efficient alternative to SIFT or SURF](https://www.willowgarage.com/sites/default/files/orb_final.pdf)
- [Object Recognition from Local Scale-Invariant Features](http://www.cs.ubc.ca/~lowe/papers/iccv99.pdf)
- [Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval](https://www.robots.ox.ac.uk/~vgg/publications/papers/philbin07.pdf)
- [Three things everyone should know to improve object retrieval](https://www.robots.ox.ac.uk/~vgg/publications/2012/Arandjelovic12/arandjelovic12.pdf)
- [On-the-fly learning for visual search of large-scale image and video datasets](https://www.robots.ox.ac.uk/~vgg/publications/2015/Chatfield15/chatfield15.pdf)

#### Deep Learning Feature Based

- [Deep Image Retrieval:Learning Global Representations for Image earch](https://arxiv.org/abs/1604.01325)
- [End-to-end Learning of Deep Visual Representations for Image retrieval](), DIR更详细的论文说明
- [What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?](), 关于layer选取的问题
- [Bags of Local Convolutional Features for Scalable Instance Search](https://arxiv.org/abs/1604.01325)
- [Faster R-CNN Features for Instance Search](https://github.com/imatge-upc/retrieval-2016-deepvision)
- [Cross-dimensional Weighting for Aggregated Deep Convolutional Features](https://arxiv.org/abs/1512.04065), [project](https://github.com/yahoo/crow)
- [Class-Weighted Convolutional Features for Image Retrieval](https://github.com/imatge-upc/retrieval-2017-cam)
- [Multi-Scale Orderless Pooling of Deep Convolutional Activation Features](), VLAD coding
- [Aggregating Deep Convolutional Features for Image Retrieval](https://arxiv.org/abs/1510.07493), [论文笔记](https://zhuanlan.zhihu.com/p/23136747), [基于深度学习的视觉实例搜索研究进展](https://zhuanlan.zhihu.com/p/22265265).
- [Particular object retrieval with integral max-pooling of CNN activations](https://arxiv.org/abs/1511.05879), [project](http://cmp.felk.cvut.cz/~toliageo/soft.html)
- [Particular object retrieval using CNN](https://github.com/AaltoVision/Object-Retrieval)
- [Learning to Match Aerial Images with Deep Attentive Architectures](https://vision.cornell.edu/se3/wp-content/uploads/2016/04/1204.pdf).
- [Siamese Network of Deep Fisher-Vector Descriptors for Image Retrieval](https://arxiv.org/pdf/1702.00338v1.pdf)
- [Combining Fisher Vector and Convolutional Neural Networks for Image Retrieval](http://ceur-ws.org/Vol-1653/paper_19.pdf), fv和cnn特征融合提升
- [Selective Deep Convolutional Features for Image Retrieval](https://arxiv.org/pdf/1707.00809v1.pdf)
- [Class-Weighted Convolutional Features for Image Retrieval](https://github.com/imatge-upc/retrieval-2017-cam)

#### ANN search

- [Practical and Optimal LSH for Angular Distance](chrome-extension://ikhdkkncnoglghljlkmcimlnlhkeamad/pdf-viewer/web/viewer.html?file=http%3A%2F%2Fpapers.nips.cc%2Fpaper%2F5893-practical-and-optimal-lsh-for-angular-distance.pdf)
- [pq-fast-scan](https://github.com/technicolor-research/pq-fast-scan)
- [faiss](https://github.com/facebookresearch/faiss). A library for efficient similarity search and clustering of dense vectors.
- [lopq](https://github.com/yahoo/lopq). Training of Locally Optimized Product Quantization (LOPQ) models for approximate nearest neighbor search of high dimensional data in Python and Spark.
- [nns_benchmark](https://github.com/DBWangGroupUNSW/nns_benchmark). Benchmark of Nearest Neighbor Search on High Dimensional Data.
- [Optimized Product Quantization](http://kaiminghe.com/cvpr13/index.html)
- [Falconn](https://github.com/FALCONN-LIB/FALCONN). FAst Lookups of Cosine and Other Nearest Neighbors.
- [Annoy](https://github.com/spotify/annoy). Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk 
- [NMSLIB](https://github.com/searchivarius/nmslib). Non-Metric Space Library (NMSLIB): A similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.

#### Industry CBIR

- [Visual Search at Pinterest]()
- [Visual Discovery at Pinterest]()

#### feature fusion

- [Feature fusion using Canonical Correlation Analysis](https://github.com/mhaghighat/ccaFuse)

#### Plan to read

- [Visual Search at Pinterest](reading done)
- [VisualRank: Applying PageRank to Large-Scale Image Search]()

### Tutorials

- [Recent Image Search Techniques](http://cvpr2016.thecvf.com/program/tutorials)
- [Compact Features for Visual Search](http://cvpr2016.thecvf.com/program/tutorials)
- [multimedia-indexing](https://github.com/MKLab-ITI/multimedia-indexing). A framework for large-scale feature extraction, indexing and retrieval.


## Awesome multiclass classification

### papers

- [Loss Functions for Top-k Error: Analysis and Insights]() and [Top-k Multiclass SVM](), [code](https://github.com/mlapin/libsdca)

### Tutorials

- [Linear Classification](http://cs231n.github.io/linear-classify/), [中文版](http://blog.csdn.net/elaine_bao/article/details/50519970), [demo](http://vision.stanford.edu/teaching/cs231n/linear-classify-demo/)

---

## Logo Detection and Classification

### Papers

- [LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks](https://arxiv.org/abs/1511.02462)

---

## Object Detection and Recognition

### Papers

- [SSD: Single Shot MultiBox Detector](www.cs.unc.edu/~wliu/papers/ssd.pdf), [code](https://github.com/weiliu89/caffe/tree/ssd)
- [A Closer Look: Small Object Detection in Faster R-CNN]()

---

## Video Classification

### Papers

- [Large-scale Video Classification with Convolutional Neural Networks](vision.stanford.edu/pdf/karpathy14.pdf)
- [Learning Spatiotemporal Features With 3D Convolutional Networks](http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Tran_Learning_Spatiotemporal_Features_ICCV_2015_paper.pdf), [code](https://github.com/Lasagne/Recipes/blob/master/examples/Video%20features%20with%20C3D.ipynb), [doc](https://docs.google.com/document/d/1-QqZ3JHd76JfimY4QKqOojcEaf5g3JS0lNh-FHTxLag/edit), [project](http://vlg.cs.dartmouth.edu/c3d/)
- [ActionVLAD: Learning spatio-temporal aggregation for action classification](https://rohitgirdhar.github.io/ActionVLAD/)

---

## ROS for Robotics

- [Learning_ROS_for_Robotics_Programming_2nd_edition](https://github.com/AaronMR/Learning_ROS_for_Robotics_Programming_2nd_edition)

---

## Image Fingerprinting

- [Video fingerprinting tool. Finding duplicate movies in a large dataset](https://github.com/funzoneq/video_fingerprinting)
Update README.md 2016-11-06 23:28:06 +08:00			`## Awesome image retrieval papers`

Update README.md 2016-12-13 18:55:39 +08:00			`#### Local Feature Based`

Update README.md 2016-12-19 23:49:56 +08:00			`- [Object retrieval with large vocabularies and fast spatial matching](https://www.robots.ox.ac.uk/~vgg/publications/papers/philbin07.pdf)`
			`- [Improving the Fisher Kernel for Large-Scale Image Classification](https://www.robots.ox.ac.uk/~vgg/rg/papers/peronnin_etal_ECCV10.pdf)`
			`- [Visual Categorization with Bags of Keypoints](http://www.cs.princeton.edu/courses/archive/fall09/cos429/papers/csurka-eccv-04.pdf)`
			`- [ORB: an efficient alternative to SIFT or SURF](https://www.willowgarage.com/sites/default/files/orb_final.pdf)`
			`- [Object Recognition from Local Scale-Invariant Features](http://www.cs.ubc.ca/~lowe/papers/iccv99.pdf)`
Update README.md 2017-03-01 20:28:05 +08:00			`- [Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval](https://www.robots.ox.ac.uk/~vgg/publications/papers/philbin07.pdf)`
Update README.md 2017-03-02 10:19:00 +08:00			`- [Three things everyone should know to improve object retrieval](https://www.robots.ox.ac.uk/~vgg/publications/2012/Arandjelovic12/arandjelovic12.pdf)`
Update README.md 2017-03-02 10:19:50 +08:00			`- [On-the-fly learning for visual search of large-scale image and video datasets](https://www.robots.ox.ac.uk/~vgg/publications/2015/Chatfield15/chatfield15.pdf)`
Update README.md 2016-12-13 18:55:39 +08:00
			`#### Deep Learning Feature Based`

Update README.md 2016-12-19 23:49:56 +08:00			`- [Deep Image Retrieval:Learning Global Representations for Image earch](https://arxiv.org/abs/1604.01325)`
Update README.md 2017-05-04 09:28:58 +08:00			`- [End-to-end Learning of Deep Visual Representations for Image retrieval](), DIR更详细的论文说明`
			`- [What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?](), 关于layer选取的问题`
Update README.md 2016-12-19 23:49:56 +08:00			`- [Bags of Local Convolutional Features for Scalable Instance Search](https://arxiv.org/abs/1604.01325)`
			`- [Faster R-CNN Features for Instance Search](https://github.com/imatge-upc/retrieval-2016-deepvision)`
			`- [Cross-dimensional Weighting for Aggregated Deep Convolutional Features](https://arxiv.org/abs/1512.04065), [project](https://github.com/yahoo/crow)`
new cbir paper added 2017-07-12 14:11:12 +08:00			`- [Class-Weighted Convolutional Features for Image Retrieval](https://github.com/imatge-upc/retrieval-2017-cam)`
Update README.md 2017-05-04 09:28:58 +08:00			`- [Multi-Scale Orderless Pooling of Deep Convolutional Activation Features](), VLAD coding`
Update README.md 2017-01-17 23:18:29 +08:00			`- [Aggregating Deep Convolutional Features for Image Retrieval](https://arxiv.org/abs/1510.07493), [论文笔记](https://zhuanlan.zhihu.com/p/23136747), [基于深度学习的视觉实例搜索研究进展](https://zhuanlan.zhihu.com/p/22265265).`
Update README.md 2017-06-03 17:33:53 +08:00			`- [Particular object retrieval with integral max-pooling of CNN activations](https://arxiv.org/abs/1511.05879), [project](http://cmp.felk.cvut.cz/~toliageo/soft.html)`
			`- [Particular object retrieval using CNN](https://github.com/AaltoVision/Object-Retrieval)`
			`- [Learning to Match Aerial Images with Deep Attentive Architectures](https://vision.cornell.edu/se3/wp-content/uploads/2016/04/1204.pdf).`
new paper 2017-02-04 23:00:49 +08:00			`- [Siamese Network of Deep Fisher-Vector Descriptors for Image Retrieval](https://arxiv.org/pdf/1702.00338v1.pdf)`
Update README.md 2017-06-02 09:51:01 +08:00			`- [Combining Fisher Vector and Convolutional Neural Networks for Image Retrieval](http://ceur-ws.org/Vol-1653/paper_19.pdf), fv和cnn特征融合提升`
new cbir paper added 2017-07-12 14:11:12 +08:00			`- [Selective Deep Convolutional Features for Image Retrieval](https://arxiv.org/pdf/1707.00809v1.pdf)`
Update README.md 2017-07-13 09:20:43 +08:00			`- [Class-Weighted Convolutional Features for Image Retrieval](https://github.com/imatge-upc/retrieval-2017-cam)`
Update README.md 2016-11-06 23:28:06 +08:00
Update README.md 2017-03-08 09:32:01 +08:00			`#### ANN search`
Update README.md 2017-01-04 11:37:50 +08:00
			`- [Practical and Optimal LSH for Angular Distance](chrome-extension://ikhdkkncnoglghljlkmcimlnlhkeamad/pdf-viewer/web/viewer.html?file=http%3A%2F%2Fpapers.nips.cc%2Fpaper%2F5893-practical-and-optimal-lsh-for-angular-distance.pdf)`
Update README.md 2017-02-06 09:28:45 +08:00			`- [pq-fast-scan](https://github.com/technicolor-research/pq-fast-scan)`
Update README.md 2017-03-08 09:32:01 +08:00			`- [faiss](https://github.com/facebookresearch/faiss). A library for efficient similarity search and clustering of dense vectors.`
			`- [lopq](https://github.com/yahoo/lopq). Training of Locally Optimized Product Quantization (LOPQ) models for approximate nearest neighbor search of high dimensional data in Python and Spark.`
			`- [nns_benchmark](https://github.com/DBWangGroupUNSW/nns_benchmark). Benchmark of Nearest Neighbor Search on High Dimensional Data.`
			`- [Optimized Product Quantization](http://kaiminghe.com/cvpr13/index.html)`
			`- [Falconn](https://github.com/FALCONN-LIB/FALCONN). FAst Lookups of Cosine and Other Nearest Neighbors.`
			`- [Annoy](https://github.com/spotify/annoy). Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk`
			`- [NMSLIB](https://github.com/searchivarius/nmslib). Non-Metric Space Library (NMSLIB): A similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.`
Update README.md 2017-02-06 09:28:45 +08:00
Update README.md 2017-05-23 09:04:11 +08:00			`#### Industry CBIR`

			`- [Visual Search at Pinterest]()`
			`- [Visual Discovery at Pinterest]()`

Update README.md 2017-02-06 09:28:45 +08:00			`#### feature fusion`

			`- [Feature fusion using Canonical Correlation Analysis](https://github.com/mhaghighat/ccaFuse)`
Update README.md 2017-01-04 11:37:50 +08:00
Update README.md 2016-11-06 23:31:08 +08:00			`#### Plan to read`

Update README.md 2017-03-08 09:42:27 +08:00			`- [Visual Search at Pinterest](reading done)`
Update README.md 2016-12-19 23:49:56 +08:00			`- [VisualRank: Applying PageRank to Large-Scale Image Search]()`
Update README.md 2016-11-06 23:31:08 +08:00
Update README.md 2016-11-06 23:28:06 +08:00			`### Tutorials`

Update README.md 2016-12-19 23:49:56 +08:00			`- [Recent Image Search Techniques](http://cvpr2016.thecvf.com/program/tutorials)`
			`- [Compact Features for Visual Search](http://cvpr2016.thecvf.com/program/tutorials)`
Update README.md 2017-03-08 09:42:27 +08:00			`- [multimedia-indexing](https://github.com/MKLab-ITI/multimedia-indexing). A framework for large-scale feature extraction, indexing and retrieval.`
Update README.md 2016-11-06 23:28:06 +08:00

Update README.md 2016-11-19 11:42:50 +08:00			`## Awesome multiclass classification`

			`### papers`

Update README.md 2016-12-19 23:49:56 +08:00			`- [Loss Functions for Top-k Error: Analysis and Insights]() and [Top-k Multiclass SVM](), [code](https://github.com/mlapin/libsdca)`
Update README.md 2016-11-19 11:42:50 +08:00
Update README.md 2016-11-19 12:08:07 +08:00			`### Tutorials`
Update README.md 2016-11-19 11:42:50 +08:00
Update README.md 2016-12-19 23:49:56 +08:00			`- [Linear Classification](http://cs231n.github.io/linear-classify/), [中文版](http://blog.csdn.net/elaine_bao/article/details/50519970), [demo](http://vision.stanford.edu/teaching/cs231n/linear-classify-demo/)`
Update README.md 2016-12-01 00:15:23 +08:00
Update README.md 2017-01-04 11:38:47 +08:00			`---`

Update README.md 2016-12-01 00:15:23 +08:00			`## Logo Detection and Classification`

video classification 2016-12-07 19:22:59 +08:00			`### Papers`
Update README.md 2016-12-01 00:15:23 +08:00
Update README.md 2016-12-19 23:54:53 +08:00			`- [LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks](https://arxiv.org/abs/1511.02462)`
Update README.md 2016-12-05 22:52:25 +08:00
Update README.md 2017-01-04 11:38:47 +08:00			`---`

Update README.md 2016-12-05 22:52:25 +08:00			`## Object Detection and Recognition`

video classification 2016-12-07 19:22:59 +08:00			`### Papers`
Update README.md 2016-12-05 22:52:25 +08:00
Update README.md 2016-12-19 23:55:25 +08:00			`- [SSD: Single Shot MultiBox Detector](www.cs.unc.edu/~wliu/papers/ssd.pdf), [code](https://github.com/weiliu89/caffe/tree/ssd)`
new paper 2017-04-13 19:17:45 +08:00			`- [A Closer Look: Small Object Detection in Faster R-CNN]()`
video classification 2016-12-07 19:22:59 +08:00
Update README.md 2017-01-04 11:38:47 +08:00			`---`

Update README.md 2016-12-07 19:23:47 +08:00			`## Video Classification`
video classification 2016-12-07 19:22:59 +08:00
			`### Papers`

Update README.md 2016-12-19 23:49:56 +08:00			`- [Large-scale Video Classification with Convolutional Neural Networks](vision.stanford.edu/pdf/karpathy14.pdf)`
			`- [Learning Spatiotemporal Features With 3D Convolutional Networks](http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Tran_Learning_Spatiotemporal_Features_ICCV_2015_paper.pdf), [code](https://github.com/Lasagne/Recipes/blob/master/examples/Video%20features%20with%20C3D.ipynb), [doc](https://docs.google.com/document/d/1-QqZ3JHd76JfimY4QKqOojcEaf5g3JS0lNh-FHTxLag/edit), [project](http://vlg.cs.dartmouth.edu/c3d/)`
Update README.md 2017-05-09 09:05:54 +08:00			`- [ActionVLAD: Learning spatio-temporal aggregation for action classification](https://rohitgirdhar.github.io/ActionVLAD/)`
Update README.md 2017-02-06 09:28:45 +08:00
			`---`

			`## ROS for Robotics`

			`- [Learning_ROS_for_Robotics_Programming_2nd_edition](https://github.com/AaronMR/Learning_ROS_for_Robotics_Programming_2nd_edition)`

			`---`

			`## Image Fingerprinting`

			`- [Video fingerprinting tool. Finding duplicate movies in a large dataset](https://github.com/funzoneq/video_fingerprinting)`