Transactional Support for Visual Instance Search

被引:1
|
作者
Lejsek, Herwig [1 ]
Asmundsson, Fridrik Heidar [1 ]
Jonsson, Bjorn Thor [2 ,3 ]
Amsaleg, Laurent [4 ]
机构
[1] Videntifier Technol, Reykjavik, Iceland
[2] Reykjavik Univ, Reykjavik, Iceland
[3] IT Univ Copenhagen, Copenhagen, Denmark
[4] CNRS IRISA, Rennes, France
关键词
NEAREST; QUANTIZATION;
D O I
10.1007/978-3-030-02224-2_6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This article addresses the issue of dynamicity and durability for scalable indexing of very large and rapidly growing collections of local features for visual instance retrieval. By extending the NV-tree, a scalable disk-based high-dimensional index, we show how to implement the ACID properties of transactions which ensure both dynamicity and durability. We present a detailed performance evaluation of the transactional NV-tree, showing that the insertion throughput is excellent despite the effort to enforce the ACID properties.
引用
收藏
页码:73 / 86
页数:14
相关论文
共 50 条
  • [1] Comics Instance Search with Bag of Visual Words
    Duc-Hoang Nguyen
    Minh-Triet Tran
    Vinh-Tiep Nguyen
    [J]. FUTURE DATA AND SECURITY ENGINEERING, FDSE 2015, 2015, 9446 : 299 - 313
  • [2] Transactional behavior of a workflow instance
    Vieira, Tatiana A. S. C.
    Casanova, Marco A.
    [J]. ON THE MOVE TO MEANINGFUL INTERNET SYSTEMS 2006: COOPIS, DOA, GADA, AND ODBAS, PT 1, PROCEEDINGS, 2006, 4275 : 756 - 771
  • [3] An Evaluation of Visual Search Support in Maps
    Netzel, Rudolf
    Hlawatsch, Marcel
    Burch, Michael
    Balakrishnan, Sanjeev
    Schmauder, Hansjrg
    Weiskopf, Daniel
    [J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2017, 23 (01) : 421 - 430
  • [4] Video instance search via spatial fusion of visual words and object proposals
    Vinh-Tiep Nguyen
    Duy Dinh Le
    Minh-Triet Tran
    Nguyen, Tam V.
    Thanh Duc Ngo
    Satoh, Shin'ichi
    Duc Anh Duong
    [J]. INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL, 2019, 8 (03) : 181 - 192
  • [5] Video instance search via spatial fusion of visual words and object proposals
    Vinh-Tiep Nguyen
    Duy Dinh Le
    Minh-Triet Tran
    Tam V. Nguyen
    Thanh Duc Ngo
    Shin’ichi Satoh
    Duc Anh Duong
    [J]. International Journal of Multimedia Information Retrieval, 2019, 8 : 181 - 192
  • [6] Adapting Video Instance Segmentation for Instance Search
    Nguyen, An Thi
    [J]. 20TH INTERNATIONAL CONFERENCE ON CONTENT-BASED MULTIMEDIA INDEXING, CBMI 2023, 2023, : 256 - 260
  • [7] TRACKED INSTANCE SEARCH
    Girbau, Andreu
    Hinami, Ryota
    Satoh, Shin'ichi
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 1663 - 1667
  • [8] Visual Information and Support Surface for Postural Control in Visual Search Task
    Huang, Chia-Chun
    Yang, Chih-Mei
    [J]. PERCEPTUAL AND MOTOR SKILLS, 2016, 123 (02) : 394 - 410
  • [9] OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning
    Liu, Sheng
    Lin, Kevin
    Wang, Lijuan
    Yuan, Junsong
    Liu, Zicheng
    [J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 1773 - 1781
  • [10] UNSUPERVISED MULTIPLE-INSTANCE LEARNING FOR INSTANCE SEARCH
    Wang, Zhenzhen
    Yuan, Junsong
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018,