hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.17559/TV-20190730110003

Cross-Media Semantic Matching based on Sparse Representation

Gongwen Xu* ; Business School, Shandong Jianzhu University, Jinan 250101, China
Aidong Zhai ; Maternity and Child Health Care Hospital, Zibo 255029, China
Jing Wang ; Business School, Shandong Jianzhu University, Jinan 250101, China
Zhijun Zhang ; Computer Science and Technology School, Shandong Jianzhu University, Jinan 250101, China
Xiaomei Li ; The Second Hospital, Shandong University, Jinan 250013, China

Puni tekst: engleski, pdf (962 KB) str. 1707-1713 preuzimanja: 10* citiraj
APA 6th Edition
Xu*, G., Zhai, A., Wang, J., Zhang, Z. i Li, X. (2019). Cross-Media Semantic Matching based on Sparse Representation. Tehnički vjesnik, 26 (6), 1707-1713. https://doi.org/10.17559/TV-20190730110003
MLA 8th Edition
Xu*, Gongwen, et al. "Cross-Media Semantic Matching based on Sparse Representation." Tehnički vjesnik, vol. 26, br. 6, 2019, str. 1707-1713. https://doi.org/10.17559/TV-20190730110003. Citirano 06.12.2019.
Chicago 17th Edition
Xu*, Gongwen, Aidong Zhai, Jing Wang, Zhijun Zhang i Xiaomei Li. "Cross-Media Semantic Matching based on Sparse Representation." Tehnički vjesnik 26, br. 6 (2019): 1707-1713. https://doi.org/10.17559/TV-20190730110003
Harvard
Xu*, G., et al. (2019). 'Cross-Media Semantic Matching based on Sparse Representation', Tehnički vjesnik, 26(6), str. 1707-1713. https://doi.org/10.17559/TV-20190730110003
Vancouver
Xu* G, Zhai A, Wang J, Zhang Z, Li X. Cross-Media Semantic Matching based on Sparse Representation. Tehnički vjesnik [Internet]. 2019 [pristupljeno 06.12.2019.];26(6):1707-1713. https://doi.org/10.17559/TV-20190730110003
IEEE
G. Xu*, A. Zhai, J. Wang, Z. Zhang i X. Li, "Cross-Media Semantic Matching based on Sparse Representation", Tehnički vjesnik, vol.26, br. 6, str. 1707-1713, 2019. [Online]. https://doi.org/10.17559/TV-20190730110003

Sažetak
With the rapid growth of multi-modal data, cross-media retrieval has aroused many research interests. In this paper, the cross-media retrieval includes two tasks: query image retrieves relevant text and query text retrieves relevant images. With the development of sparse representation, two independent sparse representation classifiers are used to map the heterogeneous features of images and texts into their common semantic space before implementing similarity comparison. The proposed method makes full use of semantic information, and it is effective in the retrieving task. The performance of this method was evaluated on Wiki dataset, NUS-WIDE dataset, Wiki dataset with CNN features and Pascal dataset with CNN features. The experimental results validate its effectiveness compared with several state-of-the-art algorithms on the Mean Average Precision and other performance indexes.

Ključne riječi
cross-media retrieval; semantic matching; sparse representation

Hrčak ID: 228519

URI
https://hrcak.srce.hr/228519

Posjeta: 19 *