Query-driven iterated neighborhood graph search for large scale indexing

By Jingdong Wang, Shipeng Li. 2012

82 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Information Retrieval & Search, Signal Processing

How researchers see this paper

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

In Aerospace Engineering

1. Liang Zheng
2. Yi Yang
3. Ting Zhang
4. Dmitry A. Yashunin
5. Yury Malkov
6. Jingdong Wang
7. Jingkuan Song
8. Jinhui Tang

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Liang Zheng
3. Qi Tian
4. Dacheng Tao
5. Jingdong Wang
6. Luc Van Gool
7. Zhedong Zheng
8. Xiaogang Wang

In Information Retrieval & Search

1. Liang Zheng
2. Jingkuan Song
3. Dmitry A. Yashunin
4. Yi Yang
5. Ting Zhang
6. Jingdong Wang
7. Yury Malkov
8. Heng Tao Shen

In Signal Processing

1. Liang Zheng
2. Dmitry A. Yashunin
3. Yi Yang
4. Yury Malkov
5. Ting Zhang
6. Jingdong Wang
7. Zhedong Zheng
8. Alexander G. Hauptmann

Citations in the corpus

• Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs (2016, methodology): “Proximity graph K-ANNS algorithms [10], [18], [19], [20], [21], [22], [23], [24], [25],”
• Scalable Person Re-identification: A Benchmark (2015, methodology): “In large-scale experiments, Euclidean distance is employed for Approximate Nearest Neighbor algorithm [33].”
• Pedestrian Alignment Network for Large-scale Person Re-Identification (2017, methodology): “Approximate nearest neighbor search [Wang and Li, 2012] is employed for fast retrieval but accuracy compromise.”
• Fast Neighborhood Graph Search Using Cartesian Concatenation (2013, methodology): “We compare our approach with stateof-the-art algorithms, including iterative neighborhood graph search [38], original neighborhood graph search (AryaM93) [2], trinary projection (TP) trees [20], vantage point (VP) tree [46], Spill trees [24], FLANN [27], and inverted multi-index [4].”
• Sparse composite quantization (2015, methodology): “The approximate nearest neighbor search algorithms are in general developed from two main aspects: (1) comparing the query with only a small subset of database vectors through special data structures, such as k-d trees [4, 31], FLANN [19], and neighborhood graph [26, 30], and (2) accelerating the di”
• Person Re-identification: Past, Present and Future (2016, methodology): “Moreover, in [44], approximate nearest neighbor search [145] is employed for fast retrieval but at the cost of compromised accuracy.”
• Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach (2018, methodology): “The Market1501 dataset [21] is used to pre-train the FCN followed by a 1,500-way softmax with the size of network input set to 320 × 120.”
• Large Scale Nearest Neighbors Search Based on Neighborhood Graph (2013, methodology): “A number of centralized indexing approaches [6, 7, 8, 9, 10, 11, 12, 13] for the AKNN search have been proposed in the past few decades.”
• A Survey on Learning to Hash (2016, methodology): “The neighborhood graphbased search algorithm [144] for real-value vectors is extended to the Hamming space [59].”
• Optimized Cartesian K-Means (2014, unknown): “C V ] 16 M ay 2 01 4 Index Terms—Clustering, Cartesian product, Nearest neighbor search ✦”