TY - GEN
T1 - Locally linear salient coding for image classification
AU - Babaee, Mohammadreza
AU - Rigoll, Gerhard
AU - Bahmanyar, Reza
AU - Datcu, Mihai
PY - 2014
Y1 - 2014
N2 - Representing images with their descriptive features is the fundamental problem in CBIR. Feature coding as a key-step in feature description has attracted the attentions in recent years. Among the proposed coding strategies, Bag-of-Words (BoW) is the most widely used model. Recently saliency has been mentioned as the fundamental characteristic of BoW. Base on this idea, Salient Coding (SaC) has been introduced. Empirical studies show that SaC is not able to represent the global structure of data with small number of codewords. In this paper, we remedy this limitation by introducing Locally Linear Salient Coding (LLSaC). This method discovers the global structure of the data by exploiting the local linear reconstructions of the data points. This knowledge in addition to the salient responses, provided by SaC, helps to describe the structure of the data even with a few codewords. Experimental results show that LLSaC obtains state-of-the-art results on various data types such as multimedia and Earth Observation.
AB - Representing images with their descriptive features is the fundamental problem in CBIR. Feature coding as a key-step in feature description has attracted the attentions in recent years. Among the proposed coding strategies, Bag-of-Words (BoW) is the most widely used model. Recently saliency has been mentioned as the fundamental characteristic of BoW. Base on this idea, Salient Coding (SaC) has been introduced. Empirical studies show that SaC is not able to represent the global structure of data with small number of codewords. In this paper, we remedy this limitation by introducing Locally Linear Salient Coding (LLSaC). This method discovers the global structure of the data by exploiting the local linear reconstructions of the data points. This knowledge in addition to the salient responses, provided by SaC, helps to describe the structure of the data even with a few codewords. Experimental results show that LLSaC obtains state-of-the-art results on various data types such as multimedia and Earth Observation.
KW - Content-Based Image Retrieval
KW - Feature Coding
KW - Locally Linear Embedding
KW - Salient Coding
UR - http://www.scopus.com/inward/record.url?scp=84904968357&partnerID=8YFLogxK
U2 - 10.1109/CBMI.2014.6849822
DO - 10.1109/CBMI.2014.6849822
M3 - Conference contribution
AN - SCOPUS:84904968357
SN - 9781479939909
T3 - Proceedings - International Workshop on Content-Based Multimedia Indexing
BT - 2014 12th International Workshop on Content-Based Multimedia Indexing, CBMI 2014
PB - IEEE Computer Society
T2 - 12th International Workshop on Content-Based Multimedia Indexing, CBMI 2014
Y2 - 18 June 2014 through 20 June 2014
ER -