DocumentCode
3021315
Title
A KNN-based Chinese generating method on static image description
Author
Liu, Haipeng ; Wang, Xiaojie ; Zhong, Yixin
Author_Institution
Center for Intell. Sci. & Technol., Beijing Univ. of Posts & Telecommun., Beijing, China
fYear
2011
fDate
26-28 July 2011
Firstpage
39
Lastpage
42
Abstract
In this research we present a novel cognition language model ViMac. Through the vision system ViMac can acquire the semantic of the objects shown in 2D images and output its own description for the new images. ViMac uses prototypes as its semantic representation and use KNN method to measure the similarity between these data points in visual subspaces. The BLEU evaluation shows that this method can generate good performance on new image description.
Keywords
computer vision; image representation; natural language processing; pattern classification; BLEU evaluation; KNN based Chinese generating method; ViMac; cognition language model; image description; semantic representation; static image description; vision system; visual subspaces; Cognition; Grounding; Image color analysis; Prototypes; Semantics; Shape; Visualization; K nearest neighbor method; image descrption; language generation; vision language grounding;
fLanguage
English
Publisher
ieee
Conference_Titel
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location
Hangzhou
Print_ISBN
978-1-61284-771-9
Type
conf
DOI
10.1109/ICMT.2011.6001657
Filename
6001657
Link To Document