The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo propõe o Extended Bag-of-Visterms (EBOV) para representar cenas semânticas. Nos métodos anteriores, a maioria das representações são bag-of-visterms (BOV), onde os visterms se referiam à informação quantizada da textura local. Nossa nova representação é construída através da introdução de informações de textura global para estender o pacote de visterms padrão. Em particular, aplicamos o peso adaptativo para fundir as informações locais e globais, a fim de fornecer uma melhor representação do visterm. Dadas essas representações, a classificação da cena pode ser realizada pelo modelo pLSA (Análise Semântica Latente Probabilística). Os resultados do experimento mostram que o uso adequado de informações globais melhora o desempenho da classificação de cenas, em comparação com a representação BOV que leva em consideração apenas as informações locais.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Shuoyan LIU, De XU, Xu YANG, "Adaptively Combining Local with Global Information for Natural Scenes Categorization" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 7, pp. 2087-2090, July 2008, doi: 10.1093/ietisy/e91-d.7.2087.
Abstract: This paper proposes the Extended Bag-of-Visterms (EBOV) to represent semantic scenes. In previous methods, most representations are bag-of-visterms (BOV), where visterms referred to the quantized local texture information. Our new representation is built by introducing global texture information to extend standard bag-of-visterms. In particular we apply the adaptive weight to fuse the local and global information together in order to provide a better visterm representation. Given these representations, scene classification can be performed by pLSA (probabilistic Latent Semantic Analysis) model. The experiment results show that the appropriate use of global information improves the performance of scene classification, as compared with BOV representation that only takes the local information into account.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.7.2087/_p
Copiar
@ARTICLE{e91-d_7_2087,
author={Shuoyan LIU, De XU, Xu YANG, },
journal={IEICE TRANSACTIONS on Information},
title={Adaptively Combining Local with Global Information for Natural Scenes Categorization},
year={2008},
volume={E91-D},
number={7},
pages={2087-2090},
abstract={This paper proposes the Extended Bag-of-Visterms (EBOV) to represent semantic scenes. In previous methods, most representations are bag-of-visterms (BOV), where visterms referred to the quantized local texture information. Our new representation is built by introducing global texture information to extend standard bag-of-visterms. In particular we apply the adaptive weight to fuse the local and global information together in order to provide a better visterm representation. Given these representations, scene classification can be performed by pLSA (probabilistic Latent Semantic Analysis) model. The experiment results show that the appropriate use of global information improves the performance of scene classification, as compared with BOV representation that only takes the local information into account.},
keywords={},
doi={10.1093/ietisy/e91-d.7.2087},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - Adaptively Combining Local with Global Information for Natural Scenes Categorization
T2 - IEICE TRANSACTIONS on Information
SP - 2087
EP - 2090
AU - Shuoyan LIU
AU - De XU
AU - Xu YANG
PY - 2008
DO - 10.1093/ietisy/e91-d.7.2087
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2008
AB - This paper proposes the Extended Bag-of-Visterms (EBOV) to represent semantic scenes. In previous methods, most representations are bag-of-visterms (BOV), where visterms referred to the quantized local texture information. Our new representation is built by introducing global texture information to extend standard bag-of-visterms. In particular we apply the adaptive weight to fuse the local and global information together in order to provide a better visterm representation. Given these representations, scene classification can be performed by pLSA (probabilistic Latent Semantic Analysis) model. The experiment results show that the appropriate use of global information improves the performance of scene classification, as compared with BOV representation that only takes the local information into account.
ER -