Polysemious visual representation based on feature aggregation for large scale image applications

Verfasser / Beitragende:
[Xinghang Song, Shuqiang Jiang, Shuhui Wang, Liang Li, Qingming Huang]
Ort, Verlag, Jahr:
2015
Enthalten in:
Multimedia Tools and Applications, 74/2(2015-01-01), 595-611
Format:
Artikel (online)
ID: 605446741
LEADER caa a22 4500
001 605446741
003 CHVBK
005 20210128100128.0
007 cr unu---uuuuu
008 210128e20150101xx s 000 0 eng
024 7 0 |a 10.1007/s11042-014-1975-5  |2 doi 
035 |a (NATIONALLICENCE)springer-10.1007/s11042-014-1975-5 
245 0 0 |a Polysemious visual representation based on feature aggregation for large scale image applications  |h [Elektronische Daten]  |c [Xinghang Song, Shuqiang Jiang, Shuhui Wang, Liang Li, Qingming Huang] 
520 3 |a Multiple image features and multiple semantic concepts from the images have intrinsic and complex relations. These relations influence the effectiveness of image semantic analysis methods, especially on the large scale problems. In this paper, a framework of generating polysemious image representation through three levels of feature aggregation is proposed. In the codebook level aggregation, visual dictionaries are learned for each feature type, and each image feature can be reconstructed with this dictionary. In the semantic level aggregation, the multiple concept distributions are learned with each feature codebook by using the improved local anchor embedding. Then the polysemious representation for for single feature type can be established after this level. In the multiple feature level aggregation, final image polysemious representation is obtained through multiple feature fusion with a weighted pooling approach. Through the proposed framework, multiple feature fusion and multiple semantic descriptions are both achieved in an integrated way. Experimental evaluations on large scale image dataset validate the effectiveness of the proposed method. 
540 |a Springer Science+Business Media New York, 2014 
690 7 |a Polysemious representation  |2 nationallicence 
690 7 |a Feature aggregation  |2 nationallicence 
690 7 |a Max pooling  |2 nationallicence 
690 7 |a Large scale  |2 nationallicence 
700 1 |a Song  |D Xinghang  |u Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology(ICT), No.6 Kexueyuan South Road Zhongguancun, Haidian District, Beijing, China  |4 aut 
700 1 |a Jiang  |D Shuqiang  |u Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology(ICT), No.6 Kexueyuan South Road Zhongguancun, Haidian District, Beijing, China  |4 aut 
700 1 |a Wang  |D Shuhui  |u Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology(ICT), No.6 Kexueyuan South Road Zhongguancun, Haidian District, Beijing, China  |4 aut 
700 1 |a Li  |D Liang  |u University of Chinese Academy of Sciences, Beijing, China  |4 aut 
700 1 |a Huang  |D Qingming  |u University of Chinese Academy of Sciences, Beijing, China  |4 aut 
773 0 |t Multimedia Tools and Applications  |d Springer US; http://www.springer-ny.com  |g 74/2(2015-01-01), 595-611  |x 1380-7501  |q 74:2<595  |1 2015  |2 74  |o 11042 
856 4 0 |u https://doi.org/10.1007/s11042-014-1975-5  |q text/html  |z Onlinezugriff via DOI 
898 |a BK010053  |b XK010053  |c XK010000 
900 7 |a Metadata rights reserved  |b Springer special CC-BY-NC licence  |2 nationallicence 
908 |D 1  |a research-article  |2 jats 
949 |B NATIONALLICENCE  |F NATIONALLICENCE  |b NL-springer 
950 |B NATIONALLICENCE  |P 856  |E 40  |u https://doi.org/10.1007/s11042-014-1975-5  |q text/html  |z Onlinezugriff via DOI 
950 |B NATIONALLICENCE  |P 700  |E 1-  |a Song  |D Xinghang  |u Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology(ICT), No.6 Kexueyuan South Road Zhongguancun, Haidian District, Beijing, China  |4 aut 
950 |B NATIONALLICENCE  |P 700  |E 1-  |a Jiang  |D Shuqiang  |u Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology(ICT), No.6 Kexueyuan South Road Zhongguancun, Haidian District, Beijing, China  |4 aut 
950 |B NATIONALLICENCE  |P 700  |E 1-  |a Wang  |D Shuhui  |u Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology(ICT), No.6 Kexueyuan South Road Zhongguancun, Haidian District, Beijing, China  |4 aut 
950 |B NATIONALLICENCE  |P 700  |E 1-  |a Li  |D Liang  |u University of Chinese Academy of Sciences, Beijing, China  |4 aut 
950 |B NATIONALLICENCE  |P 700  |E 1-  |a Huang  |D Qingming  |u University of Chinese Academy of Sciences, Beijing, China  |4 aut 
950 |B NATIONALLICENCE  |P 773  |E 0-  |t Multimedia Tools and Applications  |d Springer US; http://www.springer-ny.com  |g 74/2(2015-01-01), 595-611  |x 1380-7501  |q 74:2<595  |1 2015  |2 74  |o 11042