Title :
Mapping method between image and natural sentence
Author :
Su Mei Xi ; Qian Gao ; Young Im Cho
Author_Institution :
Dept. of Comput., Univ. of Suwon, Suwon, South Korea
Abstract :
In this paper we espouse to build a scoring procedure that evaluates the similarity between a sentence and an image. This approach is attractive, because it is symmetric: given an image (resp. sentence), one can search for the best sentence (resp. image) in a large set. Furthermore, because the learning cost is independent from the amount of data, the system has scalability, which makes it useful with large-scale data.
Keywords :
feature extraction; image classification; inference mechanisms; natural language processing; image similarity; large-scale data; learning cost; mapping method; natural sentence; scoring procedure; Birds; Continuous wavelet transforms; Materials; Tin; Image feature extraction; Meaning space; Scene classification; Similarity measure;
Conference_Titel :
Robotics (ISR), 2013 44th International Symposium on
Conference_Location :
Seoul
DOI :
10.1109/ISR.2013.6695696
