「CV」 图片检索资源汇总

相关资料：图片检索概述、视频检索资源 · 音频检索资源

1 综述

1.1 图片检索

1. A review of content-based image retrieval systems
   2000 paper
   $\bullet \bullet$
   67 页；

2. Relevance feedback in image retrieval: A comprehensive review
   2003 paper
   $\bullet \bullet$

3. A review of content-based image retrieval systems in medical applications—clinical benefits and future directions
   2004 paper
   $\bullet \bullet$

4. A review of text and image retrieval approaches for broadcast news video
   2007 paper
   $\bullet \bullet$
   40 页；

5. Content-based Image Retrieval: Feature Extraction Techniques and Applications
   2008 paper
   $\bullet \bullet$

6. A review of content-based image retrieval
   2010 paper
   $\bullet \bullet$

7. Review of medical image retrieval systems and future directions
   2011 paper
   $\bullet \bullet$

8. Comparative Study and Optimization of Feature-Extraction Techniques for Content based Image Retrieval
   2012-08-30 paper

9. large scale search
   2013 Microsoft note
   $\bullet \bullet$

10. A Survey on CBIR using Low Level Feature Combination
    2014 paper
    $\bullet \bullet$

11. Hashing for Similarity Search: A Survey
    2014-08-13 paper
    $\bullet \bullet$

12. [Describing Colors, Textures and Shapes for Content Based Image Retrieval 1. A Survey
    2015-02-25 paper
    $\bullet \bullet$
    传统特征汇总；

13. Study of Different Techniques for Image Retrieval
    2015 paper
    $\bullet \bullet$

14. Content based image retrieval using deep learning process
    2015 paper

15. A Survey on Learning to Hash
    2016-06-01 paper
    $\bullet \bullet$

16. A survey on combine approach of low level features extraction in CBIR

17. Recent Advance in Content-based Image Retrieval: A Literature Survey
    2017-06-19 paper
    $\bullet \bullet$

18. Content based Image Retrieval: A Review
    2018-04-24 paper
    $\bullet \bullet$

19. A comprehensive survey on content based image retrieval system and its application in medical domain
    2018 paper
    $\bullet \bullet$

20. Towards Practical Visual Search Engine Within
    SIGIR eCom 2018 2018-06-23 paper
    $\bullet \bullet$

21. A Benchmark on Tricks for Large-scale Image Retrieval
    2019-07-27 paper
    $\bullet \bullet$ tricks
    图像检索的很多技巧；在谷歌地标检索数据集上做的验证；

22. Deep Graph Similarity Learning: A Survey
    2019-12-25 paper
    $\bullet \bullet$ graph

1.2 度量

1. A Survey on Metric Learning for Feature Vectors and Structured Data
   2013 paper
   $\bullet \bullet$
   60 页；

2. Deep Metric Learning: A Survey
   2019-08-23 paper
   $\bullet \bullet$

2 理论

3 技术

3.1 特征提取

3.1.1 传统 3.1.1.1 局部特征

Harris角点、SIFT、PCA-SIFT和SURF等；

1. Object recognition from local scale-invariant features
   ICCV 1999 1999 paper
   sift；

2. Distinctive image features from scale-invariant keypoints
   IJCV 2004 2004 paper
   sift;

3. PCA-SIFT: A more distinctive representation for local image descriptors
   CVPR 2004 2004 paper
   PCA-Sift;

4. Gradient ordinal signature and fixed-point embedding for efficient near-duplicate video detection
   2012
   svd sift;

5. Learning local feature descriptors with triplets and shallow convolutional neural networks
   BMVC 2016 paper

3.1.1.2 全局特征

1. Ordinal measures for visual correspondence
   1996 paper
   顺序度量 OM;

2. Ordinal measures for image correspondence
   1998 paper
   顺序度量 OM；

3. Robust video signature based on ordinal measure
   2004 paper
   顺序度量 OM；

4. Spatio–Temporal Transform Based Video Hashing
   2006 paper
   DCT + Hash;

3.1.2 DL

1. Learning to compare image patches via convolutional neural networks
   CVPR 2015 2015-04-14 paper
   SCNN: 挛生网络；

2. good practice in cnn feature transfer
   2016-04-01 paper
   $\bullet \bullet$ CNN Practice

3. Deep Image Retrieval: Learning global representations for image search
   ECCV 2016 2016-04-05 paper | project | slides

4. Image copy detection based on convolutional neural networks
   2016
   深度全局特征；

5. Compact CNN based video representation for efficient video copy detection
   2017
   VGG 提取帧特征；

6. Image similarity using Deep CNN and Curriculum Learning
   2017-09-26 paper
   多尺度网络提取细粒度特征；

7. SimNet: Similarity-based network embeddings with mean commute time
   2019-02-23 paper | matlab-official

8. Deep Signatures
   2019-05-21 paper | pytorch
   $\bullet \bullet$

3.1.3 特征编码

将局部特征组合成全局图像特征；

3.1.3.1 词袋模型

1. Near-duplicate keyframe retrieval with visual keywords and semantic context
   2007 paper

1. Hamming embedding and weak geometric consistency for large scale image search
   ECCV 2008 2008 paper
   使用 Hanmming 嵌入处理视觉词袋的量化误差；针对倒排索引中的弱几何一致性做了改进；

2. Improving bag-of-features for large scale image search
   2010 paper

3. Contextual weighting for vocabulary tree based image retrieval
   2011-11-15 paper

4. Effective and efficient global context verification for image copy detection
   2017 OR-GCD 处理视觉词袋的量化误差；

3.1.3.2 Fisher-Vector

1. Fisher kernels on visual vocabularies for image categorization
   CVPR 2007 2007 paper

2. Aggregating local descriptors into a compact image representation
   CVPR 2010 2010 paper

3.1.4 其他

1. A New Approach to Image Copy Detection Based on Extended Feature Sets
   2007 paper

3.2 检索

3.2.1 树形结构

3.2.2 VA-File

3.2.3 Hash 3.2.3.1 传统

1. Locality-sensitive hashing scheme based on p-stable distributions
   2004 paper
   LSH;

2. Multi-Probe LSH: Efficient Indexing for High-Dimensional Similarity Search
   2007 paper
   LSH 的改进版，速度一样，存储减小了一个数量级；

3. Bayesian Locality Sensitive Hashing for Fast Similarity Search
   2011-10-06 paper

4. Beyond Locality-Sensitive Hashing
   2013-06-06 paper

5. Locality-Sensitive Hashing of Curves
   2017-03-11 paper

6. Locality Sensitive Hashing for Similar Item Search

3.2.3.2 DL

用来提升检索速度；怎么提升的

1. Supervised Hashing for Image Retrieval via Image Representation Learning
   AAAI 2014 2014 中山大学·潘炎、颜水成 paper
   提出基于 CNN 的深度哈希；

2. Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
   CVPR 2015 2015-04-14 paper | paper

3. Hashing by Deep Learning
   2015 IBM paper

4. Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval
   CVPR 2015 2015-01-26 paper

5. Deep Learning of Binary Hash Codes for Fast Image Retrieval
   CVPR Workshop 2015 2015 paper | caffe | pytorch
   $\bullet \bullet$

6. Supervised Learning of Semantics-Preserving Hashing via Deep Neural Networks for Large-Scale Image Search
   2015-07-01 paper | caffe
   $\bullet \bullet$ SSDH

7. Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification
   2015-08-19 paper | project | caffe
   $\bullet \bullet$

8. Deep Supervised Hashing for Fast Image Retrieval
   CVPR 2016 2016 paper | caffe | tensorflow
   $\bullet \bullet$

9. Deep Hashing Network for Efficient Similarity Retrieval
   AAAI 2016 2016 paper

10. Feature Learning based Deep Supervised Hashing with Pairwise Labels
    IJCAI 2016 2015-11-12 paper | code-official | pytorch
    $\bullet \bullet$

11. SSDH: Semi-supervised Deep Hashing for Large Scale Image Retrieval
    2016-07-28 paper

12. Deep Semantic-Preserving and Ranking-Based Hashing for Image Retrieval
    2016 paper

13. Deep Hashing: A Joint Approach for Image Signature Learning
    2016-08-12 paper

14. Transitive Hashing Network for Heterogeneous Multimedia Retrieval
    2016-08-15 paper

15. Deep Residual Hashing
    2016-12-16 paper

16. Large-Scale Image Retrieval with Attentive Deep Local Features
    ICCV 2017 2016-12-19 Google paper | tensorflow
    $\bullet \bullet$
    DELF，同时发布了较大的地标建筑检索数据集(详细说明)；

17. Places: A 10 Million Image Database for Scene Recognition
    2017 paper
    公布了千万级别的数据集；

18. Deep Binary Representation for Efficient Image Retrieval
    2017 上交 paper | tensorflow
    $\bullet \bullet$

19. Deep Region Hashing for Efficient Large-scale Instance Search from Images
    2017-01-26 paper

20. HashNet: Deep Learning to Hash by Continuation
    ICCV 2017 2017-02-02 paper | caffe/pytorch
    $\bullet \bullet$

21. Unsupervised Triplet Hashing for Fast Image Retrieval
    2017-02-28 paper

22. Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval
    CVPR spotlight paper 2017 2017-03-16 paper

23. Learning Robust Hash Codes for Multiple Instance Image Retrieval
    2017-03-16 paper

24. Simultaneous Feature Aggregating and Hashing for Large-scale Image Search
    CVPR 2017 2017-04-04 paper

25. Hashing as Tie-Aware Learning to Rank
    2017-05-23 paper

26. Deep Hashing Network for Unsupervised Domain Adaptation
    CVPR 2017 2017-06-22 paper | MatConvNet
    $\bullet \bullet$

27. Deep Binary Reconstruction for Cross-modal Hashing
    ACM Multimedia 2017 2017-08-17 paper

28. A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
    2017-11-16 paper

29. The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
    2017-11-22 paper

30. ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks
    2017-11-22 paper

31. Supervised Hashing with End-to-End Binary Deep Neural Network
    2017-11-24 paper

32. Transfer Adversarial Hashing for Hamming Space Retrieval
    2017-12-13 paper

33. Dual Asymmetric Deep Hashing Learning
    2018-01-25 paper

34. Attribute-Guided Network for Cross-Modal Zero-Shot Hashing
    2018-02-06 paper

35. Deep Reinforcement Learning for Image Hashing
    2018-02-07 paper

36. Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation
    2018-02-21 paper

37. Hashing with Mutual Information
    2018-03-02 paper

38. Zero-Shot Sketch-Image Hashing
    CVPR spotlight 2018 2018-03-06 paper

39. Instance Similarity Deep Hashing for Multi-Label Image Retrieval
    2018-03-08 paper

40. Deep Class-Wise Hashing: Semantics-Preserving Hashing via Class-wise Loss
    2018-03-12 paper

41. SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval
    CVPR 2018 2018-03-13 paper

42. Unsupervised Semantic Deep Hashing
    2018-03-19 paper

43. Improving Deep Binary Embedding Networks by Order-aware Reweighting of Triplets
    2018-04-17 paper

44. Deep Semantic Hashing with Generative Adversarial Networks
    SIGIR Oral 2017 2018-04-23 paper

45. Deep Ordinal Hashing with Spatial Attention
    2018-05-07 paper

46. Efficient end-to-end learning for quantizable representations
    ICML 2018 2018-05-15 paper | tensorflow
    $\bullet \bullet$

47. Unsupervised Deep Image Hashing through Tag Embeddings
    2018-06-15 paper
    Weakly Supervised Deep Image Hashing through Tag Embeddings

48. Adversarial Learning for Fine-grained Image Search
    2018-07-06 paper

49. Error Correction Maximization for Deep Image Hashing
    2018-08-06 paper

50. Deep Priority Hashing
    ACM MM 2018 2018-09-04 paper

51. Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing
    2018-09-07 paper

52. PDH : Probabilistic deep hashing based on MAP estimation of Hamming distance
    ICIP 2019 2019-05-21 paper

53. Deep Spherical Quantization for Image Search
    2019-06-07 paper

54. Adversarially Trained Deep Neural Semantic Hashing Scheme for Subjective Search in Fashion Inventory
    2019-06-30 paper

3.2.4 倒排

1. Hamming embedding and weak geometric consistency for large scale image search

2. Flip-invariant SIFT for copy and object detection
   2013
   解决弱几何一致性；

3.3 距离度量

3.3.1 Pairwise

1. Dimensionality Reduction by Learning an Invariant Mapping
   CVPR 2006 2006 paper | Caffe | tensorflow | Keras | pytorch1 | pytorch2
   $\bullet \bullet$ DrLIM

2. From Point to Set: Extend the Learning of Distance Metrics
   ICCV 2013 2013 paper

3. Deep metric learning using Triplet network
   2014-12-20 paper | torch
   $\bullet \bullet$ Triplet

4. Metric Learning with Adaptive Density Discrimination
   ICLR 2016 2015-11-18 Facebook AI Research & UC Berkeley paper | tensorflow | pytorch
   $\bullet \bullet$ Magnet

5. Deep Metric Learning via Lifted Structured Feature Embedding
   CVPR 2016 2015-11-19 | paper | project | chainer | caffe | pytorch1 | pytorch2 | tensorflow | dataset | blog
   $\bullet \bullet$ LSSS

6. Improved Deep Metric Learning with Multi-class N-pair Loss Objective
   NIPS 2016 2016 paper | pytorch | chainer
   $\bullet \bullet$ N-pair

7. Hard-Aware Deeply Cascaded Embedding
   ICCV 2017 2016-11-17 paper | caffe | caffe
   $\bullet \bullet$ HDC

8. Learnable Structured Clustering Framework for Deep Metric Learning
   2016-12-05 paper

9. Deep Metric Learning via Facility Location
   CVPR 2017 2016-12-05 | paper | tensorflow
   $\bullet \bullet$ NMI

10. Cross-modal Deep Metric Learning with Multi-task Regularization
    ICME 2017 2017-03-21 paper

11. Smart Mining for Deep Metric Learning
    2017-04-05 paper

12. Beyond triplet loss: a deep quadruplet network for person re-identification
    CVPR 2017 2017-05-13 paper
    Quadruplet

13. DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
    2017-07-05 paper
    TuSimple pedestrian re-identification

14. No Fuss Distance Metric Learning using Proxies
    ICCV 2017 2017-08-03 paper | pytorch1 | pytorch2 | chainer
    $\bullet \bullet$ Proxy NCA

15. Deep Metric Learning with Angular Loss
    ICCV 2017 2017-08-04 paper | tensorflow | chainer
    $\bullet \bullet$ Angular

16. Learning Non-Metric Visual Similarity for Image Retrieval
    2017-09-05 paper | openreview | matlab

17. Near-Duplicate Video Retrieval with Deep Metric Learning
    ICCV 2017 2017-10-23 paper

18. Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly
    2018-01-15 paper

19. Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval
    2018-02-27 paper

20. Generalization in Metric Learning: Should the Embedding Layer be the Embedding Layer?
    2018-03-08 paper

21. Attention-based Ensemble for Deep Metric Learning
    paper

22. Online Deep Metric Learning
    2018-05-15 paper

23. Deep Randomized Ensembles for Metric Learning
    ECCV 2018 2018-08-13 paper | pytorch
    $\bullet \bullet$ DREML

24. Deep Metric Learning by Online Soft Mining and Class-Aware Attention
    AAAI 2019 2018-11-04 paper

25. Ranked List Loss for Deep Metric Learning
    CVPR 2019 2019-03-08 paper
    RLL

26. Hardness-Aware Deep Metric Learning
    CVPR 2019 2019-03-14 paper | tensorflow
    $\bullet \bullet$ HDML

27. Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning
    CVPR 2019 2019-04-04 paper

28. Deep Metric Learning Beyond Binary Supervision
    CVPR 2019 2019-04-23 paper
    Log-loss

29. Deep Metric Learning to Rank
    CVPR 2019 2019-05-14 paper | pytorch
    $\bullet \bullet$ FastAP

30. Deep Asymmetric Metric Learning via Rich Relationship Mining
    CVPR 2019 2019-06-10 paper

31. SoftTriple Loss: Deep Metric Learning Without Triplet Sampling
    ICCV 2019 2019-09-11 paper | tensorflow | pytorch
    $\bullet \bullet$ SoftTriple

32. Visual Explanation for Deep Metric Learning
    2019-09-27 paper

33. Learning Tversky Similarity
    2020-05-27 paper
    基于 Tversky 做度量；

3.3.2 variant

3.3.3 Probabilistic

3.3.4 Boost-like

3.3.5 其他

1. Similarity Measures
   1999 paper

2. Comprehensive Survey on Distance/Similarity Measures between Probability Density Functions
   2007 paper
   比较了各种距离度量方法，并探讨了他们的相似性；

4 技术方向

4.1 检索

1. Using Very Deep Autoencoders for Content-Based Image Retrieval
   2011 Alex Krizhevsky, Geoffrey E. Hinton
   paper
   $\bullet \bullet$
   ESANN

2. Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data
   2013-12-17 paper

3. CNN Features off-the-shelf: an Astounding Baseline for Recognition
   CVPR workshop 2014-03-23 paper
   $\bullet \bullet$ CNN4Recognition
   融合从图像的不同区域提取到的全链接特征；

4. Neural Codes for Image Retrieval
   ECCV 2014 2014-04-07 paper | project | yael
   $\bullet \bullet$
   neuralcodes
   研究全连接层在图像检索中的应用；​

5. Visual Instance Retrieval with Deep Convolutional Networks
   2014-12-20 paper

6. Efficient On-the-fly Category Retrieval using ConvNets and GPUs
   2014-07-17 paper

7. A baseline for visual instance retrieval with deep convolutional networks
   ICLR 2015 2015 paper
   发现卷积层特征比全连接层特征更适合图像检索；​（效果很经验）
   $\bullet \bullet$

8. Learning visual similarity for product design with convolutional neural networks
   SIGGRAPH 2015 paper | home
   $\bullet \bullet$

9. A Practical Guide to CNNs and Fisher Vectors for Image Instance Retrieval
   2015-08-11 Vijay Chandrasekhar paper

10. Aggregating local deep features for image retrieval
    ICCV 2015 2015-10-26 paper
    $\bullet \bullet$
    对卷积层的特征进行求和，以此简化了描述子；​

11. Exploiting Local Features from Deep Networks for Image Retrieval
    2015-04-20 CVPR Workshop paper
    $\bullet \bullet$
    CNN 助力图片检索；

12. Visual Search at Pinterest
    SIGKDD 2015 2015-05-28 paper | home
    $\bullet \bullet$

13. Aggregating Deep Convolutional Features for Image Retrieval
    ICCV 2015 2015-10-26 paper
    $\bullet \bullet$
    Sum pooing

14. Particular object retrieval with integral max-pooling of CNN activations
    ICLR 2016 2015-11-18 paper
    $\bullet \bullet$
    use max-pooling to aggregate the deep descriptors, R-MAC (regional maximum activation of convolutions)；聚合不同区域的特征；

15. Where to Buy It: Matching Street Clothing Photos in Online Shops
    ICCV 2015 2015 paper | project
    $\bullet \bullet$

16. Cross-dimensional Weighting for Aggregated Deep Convolutional Features
    ECCV 2016 2015-12-13 paper
    $\bullet \bullet$
    非参数空间，通道维度；效果提升很大；​

17. Group Invariant Deep Representations for Image Instance Retrieval
    2016-01-09 paper

18. Large-Scale Image Retrieval with Attentive Deep Local Features
    2016-12-19 paper | tensorflow
    $\bullet \bullet$
    deep local feature DELF 用 Google 数据集测试的；

19. End-to-end Learning of Deep Visual Representations for Image Retrieval
    IJCV 2017 2016-10-25 paper | project
    $\bullet \bullet$
    Extended version of our ECCV2016 paper “Deep Image Retrieval: Learning global representations for image search”

20. Bags of Local Convolutional Features for Scalable Instance Search
    ICMR 2016 Best Poster 2016-04-15 paper | project | slides
    $\bullet \bullet$
    BoW

21. Faster R-CNN Features for Instance Search
    CVPR 26 DeepVision 26-04-29 paper | project | tensorflow | 解读
    $\bullet \bullet$
    instance

22. CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
    ECCV 2016 2016-04-08 paper | project Matlab-official | pytorch-official
    $\bullet \bullet$
    siamac

23. Embedding based on function approximation for large scale image search
    2016-05-23 paper

24. Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
    2016-06-22 paper
    query adaptive matching (QAM), Feature Map Pooling, Overlapped Spatial Pyramid Pooling（OSPP）

25. Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks
    CVPR 2016 2016 paper | caffe
    $\bullet \bullet$
    DeepBit

26. Fast Training of Triplet-based Deep Binary Embedding Networks
    CVPR 2016 2016 paper | theano-official
    $\bullet \bullet$

27. Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles
    CVPR 2016 2016 paper
    $\bullet \bullet$
    vehicle re-identification, vehicle retrieval. coupled clusters loss

28. DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations
    CVPR 2016 2016 paper | project
    $\bullet \bullet$
    FashionNet

29. The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies
    2016-07 paper | project | caffe | pytorch
    $\bullet \bullet$
    sketchy

30. Adversarial Training For Sketch Retrieval
    2016-07-10 paper

31. PicHunt: Social Media Image Retrieval for Improved Law Enforcement
    2016-08-02 paper

32. SIFT Meets CNN: A Decade Survey of Instance Retrieval
    2016-08-05 paper

33. What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
    ICLR 2017 2016-11-05 paper
    $\bullet \bullet$

34. Image Retrieval with Deep Local Features and Attention-based Keypoints
    2016-12-16 paper

35. Internet-Based Image Retrieval Using End-to-End Trained Deep Distributions
    2016-12-22 paper

36. Compression of Deep Neural Networks for Image Instance Retrieval
    DCC 2017 2017-01-18 paper

37. Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval
    2017-01-18 paper

38. Siamese Network of Deep Fisher-Vector Descriptors for Image Retrieval
    2017-02-01 paper

39. Deep Geometric Retrieval
    2017-02-21 paper

40. Context Aware Query Image Representation for Particular Object Retrieval
    SCIA 2017 extention 2017-03-03 paper
    $\bullet \bullet$

41. AMC: Attention guided Multi-modal Correlation Learning for Image Search
    CVPR 2017 2017-04-03 paper | sklearn
    $\bullet \bullet$
    AMC

42. Deep image representations using caption generators
    ICME 2017 2017-05-25 paper
    $\bullet \bullet$

43. Visual Search at eBay
    SIGKDD 2017 2017-06-10 paper
    $\bullet \bullet$

44. Sampling Matters in Deep Embedding Learning
    2017-06-23 UT Austin & A9/Amazon paper
    $\bullet \bullet$
    distance weighted sampling

45. One-Shot Fine-Grained Instance Retrieval
    MM 2017 2017-07-04 paper

46. Selective Deep Convolutional Features for Image Retrieval
    MM 2017 2017-07-04 paper

47. Class-Weighted Convolutional Features for Visual Instance Search
    BMVC 2017 2017-07-09 paper | project | theano
    $\bullet \bullet$ CAMs

48. Learning a Repression Network for Precise Vehicle Search
    2017-08-08 paper

49. SUBIC: A supervised, structured binary code for image search
    ICCV 2017 2017-08-09 paper
    $\bullet \bullet$ SBC

50. Pruning Convolutional Neural Networks for Image Instance Retrieval
    2017-07-18 paper

51. Image2song: Song Retrieval via Bridging Image Content and Lyric Words
    ICCV 2017 2017-08-19 paper
    $\bullet \bullet$

52. Deep Shape Matching
    ECCV 2018 2017-09-11 paper | matlab-official
    $\bullet \bullet$ shape

53. Region-Based Image Retrieval Revisited
    ACM Multimedia 2017 (Oral) 2017-09-26 paper
    $\bullet \bullet$ RBIR Revisited

54. Fine-tuning CNN Image Retrieval with No Human Annotation
    TPAMI 2018 2017-11-03 paper | pytorch-official | matlab-official
    $\bullet \bullet$ GeM

55. Beyond Part Models: Person Retrieval with Refined Part Pooling
    2017-11-26 paper

56. Query-Adaptive R-CNN for Open-Vocabulary Object Detection and Retrieval
    2017-11-27 paper

57. Saliency Weighted Convolutional Features for Instance Search
    2017-11-29 paper | project
    $\bullet \bullet$
    local convolutional features (BLCF), human visual attention models (saliency)

58. DeepStyle: Multimodal Search Engine for Fashion and Interior Design
    2018-01-08 paper

59. From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
    2018-02-07 paper

60. Web-Scale Responsive Visual Search at Bing
    2018-02-14 Microsoft paper

61. Approximate Query Matching for Image Retrieval
    2018-03-14 paper

62. Triplet-Center Loss for Multi-View 3D Object Retrieval
    CVPR 2018 2018-03-16 paper
    $\bullet \bullet$

63. Deep Feature Aggregation with Heat Diffusion for Image Retrieval
    2018-05-22 paper | matlab
    $\bullet \bullet$ Heat Diffusion

64. Collaborative Multi-modal deep learning for the personalized product retrieval in Facebook Marketplace
    2018-05-31 Facebook paper
    $\bullet \bullet$

65. DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval
    ICPR 2018 2018-06-08 paper | pytorch-official
    $\bullet \bullet$
    DeepFirearm

66. Instance Search via Instance Level Segmentation and Feature Representation
    2018-06-10 paper

67. Single Shot Scene Text Retrieval
    ECCV 2018 2018-08-27 paper
    $\bullet \bullet$

68. Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
    CVPR 2019 2018-12-04 Google paper | tensorflow
    $\bullet \bullet$
    detect
    基于检测的检索；

69. ACTNET: end-to-end learning of feature activations and aggregation for effective instance image retrieval
    2019-07-12 paper
    多层特征融合；

70. A Compact Neural Architecture for Visual Place Recognition
    2019-10-15 paper
    跨越白天黑夜，春夏秋冬；

4.2 跨模态

4.2.1 文本

1. Natural Language Object Retrieval
   CVPR 2016 2015 paper | project | caffe | tensorflow & caffe

2. An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning
   2017 paper

3. Object Captioning and Retrieval with Natural Language
   2018 paper

4. DeepSeek: Content Based Image Search & Retrieval
   2018-01-09 paper

5. Building Contextual Implicit Links for Image Retrieval
   2018 paper

6. [Scene Graph based Image Retrieval -1. A case study on the CLEVR Dataset
   2019-11-03 paper

4.2.2 其他

1. Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network
   DARN [2015] ICCV；​cross-entropy loss, triplet loss；
   paper

2. Deep Cross-Modal Hashing
   2016-02-06 paper

3. Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval
   2018-04-30 paper

4. Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval
   [2017] ICCV
   paper

5. MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval
   paper

6. Cross-Domain Image Retrieval with Attention Modeling
   paper

7. Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
   paper

8. HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
   paper

9. Objects that Sound
   DeepMind, VGG
   paper

10. Learnable PINs: Cross-Modal Embeddings for Person Identity
    VGG
    paper

11. Revisiting Cross Modal Retrieval
    [2018] ECCVW (MULA 2018)
    paper

12. Simple to Complex Cross-modal Learning to Rank
    Xi’an Jiaotong University & University of Technology Sydney & National University of Singapore & CMU
    paper

13. One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network
    IJCAI 2019-07-01 paper
    还用了 GAN；

4.3 重识别

4.3.1 行人

4.3.2 车辆

4.4 内容检索

1. GetNet: Get Target Area for Image Pairing
   2019-10-08 paper
   先检测再检索；

4.5 零样本检索

1. Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval
   ICCV 2019 2019-04-05 paper
   什么是零样本检索

2. Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval
   IJCV 2020 2020-06-20 paper
   复杂的 GAN 实现草图检索图片；

4.6 伪造检测

1. Copy-move forgery detection based on deep learning
   2017

2. Tampering Detection and Localization through Clustering of Camera-Based CNN Features
   CVPR 2017 2017 paper

3. Copy-move Forgery Detection based on Convolutional Kernel Network
   2017-07-05 paper

4. Protecting World Leaders Against Deep Fakes
   CVPR 2019 workshop 2019-01 paper

4.7 重复性

1. Bundling features for large scale partial-duplicate web image search
   CVPR 2009 2018-01-04 paper

2. Efficient Feature Detection and Effective Post-Verification for Large Scale Near-Duplicate Image Search

3. Benchmarking unsupervised near-duplicate image detection
   2019-07-03 paper

5 应用

5.1 地标检索

1. TraffickCam: Explainable Image Matching For Sex Trafficking Investigations
   2019-10-08 paper
   地标检索助力人口贩卖；

5.2 草图检索

1. Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval
   ICCV 2019 2019-04-05

5.3 图片推荐

1. Salienteye: Maximizing Engagement While Maintaining Artistic Style on Instagram Using Deep Neural Networks
   Conference 2020 2020-06-13 paper
   基于目标检测的图片检索，用于作品推荐；

---

TOP

附录

A 研究者

1. Wu-Jun LI:LAMDA 研究室成员

B 参考资料

a 论文汇总

1. 图像检索Image Retrieval知识资料全集 专知
2. Image Retrieval paperwithcode
3. 图像检索资源/论文列表
4. Reading-Paper
5. Image Retrieval 韩东
6. Survey_of_Deep_Metric_Learning 论文汇总；
7. Computer-Vision-Leaderboard

b 技术总结

1. zwr1994. Learning to Hash 综述阅读笔记[EB/OL]. https://blog.csdn.net/zwr1994/article/details/78047703. 2018-03-16/2019-07-02.
2. -. Learning to Hash[EB/OL]. https://cs.nju.edu.cn/lwj/L2H.html. -/2019-07-02.
3. CVPR 2018 地标建筑物识别
4. Image Tampering Detection and Localization
5. 图像检索中的相似度度量：EMD距离
6. 阿里研究员华先胜：图像搜索的前世今生
7. Deep Metric Learning 知乎
8. 度量学习—综述
9. 图像检索：layer选择与fine-tuning性能提升验证

C 开源项目

1. Faiss
   Faiss流程与原理分析

2. SPTAG

3. Milvus
   github
   为海量特征向量的近似最近邻搜索（ANNS）而设计；提供完整的向量数据更新，索引与查询框架；利用 GPU（Nvidia）进行索引加速与查询加速，能大幅提高单机性能；

4. DeepHash
5. Easily Extendable Basic Deep Metric Learning Pipeline
6. Deep Metric Learning-PyTorch