Paper Info
Title
Towards a universal and limited visual vocabulary
Abstract
Bag-of-visual-words is a popular image representation and attains wide application in image processing community. While its potential has been explored in many aspects, its operation still follows a basic mode, namely for a given dataset, using k-means-like clustering methods to train a vocabulary. The vocabulary obtained this way is data dependent, i.e., with a new dataset, we must train a new vocabulary. Based on previous research on determining the optimal vocabulary size, in this paper we research on the possibility of building a universal and limited visual vocabulary with optimal performance. We analyze why such a vocabulary should exist and conduct extensive experiments on three challenging datasets to validate this hypothesis. As a consequence, we believe this work sheds a new light on finally obtaining a universal visual vocabulary of limited size which can be used with any datasets to obtain the best or near-best performance.
Year
DOI
Venue
2011
10.1007/978-3-642-24031-7_40
ISVC
Keywords
Field
DocType
limited size,near-best performance,optimal vocabulary size,new dataset,image processing community,challenging datasets,universal visual vocabulary,limited visual vocabulary,new vocabulary,new light
Cosine similarity,Video retrieval,Computer science,Image representation,Data dependent,Image processing,Speech recognition,Artificial intelligence,Natural language processing,Cluster analysis,Vocabulary,Visual Word
Conference
Citations 
PageRank 
References 
2
0.38
21
Authors
4
Name
Order
Citations
PageRank
Jian Hou112617.11
Zhan-Shen Feng261.58
Yong Yang380.84
Nai-Ming Qi4385.09