@inproceedings{813d4e0c131040b3a44ffe407565c3c1,
title = "Exploring statistical properties for semantic annotation: Sparse distributed and convergent assumptions for keywords",
abstract = "Does there exist a compact set of visual topics in form of keyword clusters capable to represent all images visual content within an acceptable error? In this paper, we answer this question by analyzing distribution laws for keywords from image descriptions and comparing with traditional techniques in NLP, thereby propose three assumptions: Sparse Distribution Attribute, Local Convergent Assumption and Global Convergent Conjecture. They are essential for keywords selection and image content understanding to overcome the semantic gap. Experiments are performed on a 60,000 web crawled images, and the correctness is validated by the performance.",
keywords = "Image annotation, Image retrieval, Keyword selection, Topic models",
author = "Xianming Liu and Hongxun Yao and Rongrong Ji",
year = "2010",
doi = "10.1109/ICASSP.2010.5494954",
language = "英语",
isbn = "9781424442966",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "802--805",
booktitle = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings",
address = "美国",
note = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 ; Conference date: 14-03-2010 Through 19-03-2010",
}