Image Classification and Retrieval are ONE

By Lingxi Xie, Richang Hong, Qi Tian. 2015

138 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Qi Tian
3. Liang Zheng
4. Luc Van Gool
5. Dacheng Tao
6. Alan L. Yuille
7. Jiashi Feng
8. Xiaogang Wang

In Media Technology

1. Jingdong Wang
2. Qi Tian
3. Liang Zheng
4. Yi Yang
5. Lingxi Xie
6. Alan L. Yuille
7. Herv'e J'egou
8. Jiashi Feng

In Information Retrieval & Search

1. Liang Zheng
2. Giorgos Tolias
3. Jingdong Wang
4. Yi Yang
5. Qi Tian
6. Herv'e J'egou
7. Lingxi Xie
8. Alan L. Yuille

Citations in the corpus

• Genetic CNN (2017, methodology): “To this end, we propose an encoding method to represent each network structure by a fixedlength binary string.”
• Particular object retrieval with integral max-pooling of CNN activations (2015, methodology): “The recent work of Xie et al. (2015) is quite similar to theirs and is applied on both retrieval and classification.”
• Dynamic Match Kernel With Deep Convolutional Features for Image Retrieval (2018, unknown): “[37] [41] [44] [49] [42] [43] [47] [68] [38] [39] [69] [70] [3] [63] [1]”
• SIFT Meets CNN: A Decade Survey of Instance Retrieval (2016, methodology): “Apart from the above-mentioned strategies, we notice that several works [7], [133], [152] extract several region descriptors per image to do a many-to-many matching, called “spatial search” [7].”
• Good Practice in CNN Feature Transfer (2016, methodology): “Comparing with “ONE+SVM” [41], our result on Indoor-67 and SUN-397 is higher by +5.”
• A survey on deep learning-based fine-grained object classification and semantic segmentation (2017, background): “Some other general deep convolutional feature extractors for image classification include CNN features off-the-shelf [11] , ONE [12] and InterActive [13] .”
• DisturbLabel: Regularizing CNN on the Loss Layer (2016, background): “CNN also provides efficient visual features for other tasks [4][26][39][40][41].”
• InterActive: Inter-Layer Activeness Propagation (2016, methodology): “They can be used for various vision applications, including image classification [20], image retrieval [38][48], object detection [15][14] and object parsing [45].”
• Towards Reversal-Invariant Image Representation (2017, methodology): “A popular case is finegrained object recognition, which is aimed at predicting the object class at a finer level of granularity.”