Burst-survive Temporal Matching Kernel with Fibonacci Periods
作者： Fan Yang , Shinrichi Satoh
DOI: 10.1109/ICASSP.2019.8682971
关键词:
摘要: In this paper we present a novel approach to improve temporal matching kernel (TMK) for video retrieval tasks. TMK has the ability align videos during retrieval, but provides little none performance improvement over baseline methods. We discovered that cannot discriminate between true match case in which two have long, consecutive segments of similar frames and false contain non-consecutive randomly frames. Our proposed burst-survive adopts shuffle strategy rule out cases, with assistance multiple periods selected from Fibonacci series. As result, achieved significant on EVVE dataset.
sci-hub.se 参考文章(17)
Matthijs Douze, Hervé Jégou, Cordelia Schmid, Patrick Pérez, Compact video description for copy detection with precise temporal alignment european conference on computer vision. ,vol. 6311, pp. 522- 535 ,(2010) , 10.1007/978-3-642-15549-9_38
Hervé Jégou, Ondřej Chum, Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening Computer Vision – ECCV 2012. pp. 774- 787 ,(2012) , 10.1007/978-3-642-33709-3_55
Sébastien Poullot, Shunsuke Tsukatani, Anh Phuong Nguyen, Hervé Jégou, Shin'Ichi Satoh, Temporal Matching Kernel with Explicit Feature Maps acm multimedia. pp. 381- 390 ,(2015) , 10.1145/2733373.2806228
Alan F. Smeaton, Paul Over, Wessel Kraaij, Evaluation campaigns and TRECVid multimedia information retrieval. pp. 321- 330 ,(2006) , 10.1145/1178677.1178722
Jingkuan Song, Yi Yang, Zi Huang, Heng Tao Shen, Richang Hong, Multiple feature hashing for real-time large scale near-duplicate video retrieval acm multimedia. pp. 423- 432 ,(2011) , 10.1145/2072298.2072354
Matthijs Douze, Jerome Revaud, Cordelia Schmid, Herve Jegou, Stable Hyper-pooling and Query Expansion for Event Detection international conference on computer vision. pp. 1825- 1832 ,(2013) , 10.1109/ICCV.2013.229
Relja Arandjelovic, Andrew Zisserman, All About VLAD computer vision and pattern recognition. pp. 1578- 1585 ,(2013) , 10.1109/CVPR.2013.207
A. Vedaldi, A. Zisserman, Efficient Additive Kernels via Explicit Feature Maps IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 34, pp. 480- 492 ,(2012) , 10.1109/TPAMI.2011.153
A Karpenko, P Aarabi, Tiny Videos: A Large Data Set for Nonparametric Video Retrieval and Frame Classification IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 33, pp. 618- 630 ,(2011) , 10.1109/TPAMI.2010.118
Sivic, Zisserman, Video Google: a text retrieval approach to object matching in videos international conference on computer vision. ,vol. 3, pp. 1470- 1477 ,(2003) , 10.1109/ICCV.2003.1238663