Please use this identifier to cite or link to this item:
https://doi.org/10.3169/mta.1.138
DC Field | Value | |
---|---|---|
dc.title | Relative-distance-based soft voting for human attribute analysis using top-view images | |
dc.contributor.author | Yamasaki T. | |
dc.contributor.author | Chen T. | |
dc.date.accessioned | 2018-08-21T04:56:39Z | |
dc.date.available | 2018-08-21T04:56:39Z | |
dc.date.issued | 2013 | |
dc.identifier.citation | Yamasaki T., Chen T. (2013). Relative-distance-based soft voting for human attribute analysis using top-view images. ITE Transactions on Media Technology and Applications 1 (2) : 138-147. ScholarBank@NUS Repository. https://doi.org/10.3169/mta.1.138 | |
dc.identifier.issn | 21867364 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/146110 | |
dc.description.abstract | This paper proposes a soft voting based bag-of-features (BoF) model considering relative distance of the feature vectors to the nearest-neighbor codeword. The proposed method is more efficient than the kernel distance based soft voting method, which requires brute force parameter optimization. The proposed algorithm is applied to human attribute analysis using top-view images and conventional object classification. The experimental results for the human attribute analysis have demonstrated 100% accuracy for both gender classification and bag possession status classification. It has also been demonstrated that discriminative ability is comparable to that of the fine-tuned kernel distance based soft voting method. | |
dc.publisher | Institute of Image Information and Television Engineers | |
dc.source | Scopus | |
dc.subject | Bag of features | |
dc.subject | Human attribute analysis | |
dc.subject | Soft voting | |
dc.type | Article | |
dc.contributor.department | OFFICE OF THE PROVOST | |
dc.contributor.department | DEPARTMENT OF COMPUTER SCIENCE | |
dc.description.doi | 10.3169/mta.1.138 | |
dc.description.sourcetitle | ITE Transactions on Media Technology and Applications | |
dc.description.volume | 1 | |
dc.description.issue | 2 | |
dc.description.page | 138-147 | |
dc.published.state | published | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.