Home >

news Help

Publication Information


Title
Japanese: 
English:Neighbor-To-Neighbor Search for Fast Coding of Feature Vectors 
Author
Japanese: 井上 中順, 篠田 浩一.  
English: Nakamasa Inoue, Koichi Shinoda.  
Language English 
Journal/Book name
Japanese: 
English:2013 IEEE International Conference on Computer Vision 
Volume, Number, Page         pp. 1233-1240
Published date Dec. 3, 2013 
Publisher
Japanese: 
English: 
Conference name
Japanese: 
English:2013 IEEE International Conference on Computer Vision 
Conference site
Japanese: 
English:Sydney 
File
DOI http://dx.doi.org/10.1109/ICCV.2013.156
Abstract Assigning a visual code to a low-level image descriptor, which we call code assignment, is the most computationally expensive part of image classification algorithms based on the bag of visual word (BoW) framework. This paper proposes a fast computation method, Neighbor-to- Neighbor (NTN) search, for this code assignment. Based on the fact that image features from an adjacent region are usually similar to each other, this algorithm effectively reduces the cost of calculating the distance between a codeword and a feature vector. This method can be applied not only to a hard codebook constructed by vector quantization (NTN-VQ), but also to a soft codebook, a Gaussian mixture model (NTN-GMM). We evaluated this method on the PASCAL VOC 2007 classification challenge task. NTN-VQ reduced the assignment cost by 77.4% in super-vector coding, and NTN-GMM reduced it by 89.3% in Fisher-vector coding, without any significant degradation in classification performance.

©2007 Tokyo Institute of Technology All rights reserved.