| Presentation | 2014-05-23 Generalized Super-Vector coding for image classification Motoki Nakajima, Xian-Hua Han, Yen-Wei Chen, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Semantic understanding of images remains an important research challenge in machine intelligence and statistical learning. This study mainly aims to explore a generalized feature extraction framework motivated by the popularly used Bag-of-feature (BOF) and super-vector coding using local descriptor (such as SIFT), which is intuitively time-consuming for computation. Compared to the uniformly quantized strategy such as the conventional color histogram, the proposed framework can represent the image more faithful and compact, and then lead to more discriminant representation for images. With the extracted adaptive statistics, a simple linear support vector machine (SVM), which is especially efficient for large-scale database, can be effectively utilized for achieving acceptable recognition performances. Our proposed strategy can achieve much better recognition performances than the conventional and the state-of-the art methods. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | RGB Color Histogram / Edge Histogram / Bag-Of-features / Super-Vector Cording / SVM |
| Paper # | SIP2014-21,IE2014-21,PRMU2014-21,MI2014-21 |
| Date of Issue |
| Conference Information | |
| Committee | IE |
|---|---|
| Conference Date | 2014/5/15(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Image Engineering (IE) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Generalized Super-Vector coding for image classification |
| Sub Title (in English) | |
| Keyword(1) | RGB Color Histogram |
| Keyword(2) | Edge Histogram |
| Keyword(3) | Bag-Of-features |
| Keyword(4) | Super-Vector Cording |
| Keyword(5) | SVM |
| 1st Author's Name | Motoki Nakajima |
| 1st Author's Affiliation | Ritsumeikan University() |
| 2nd Author's Name | Xian-Hua Han |
| 2nd Author's Affiliation | Ritsumeikan University |
| 3rd Author's Name | Yen-Wei Chen |
| 3rd Author's Affiliation | Ritsumeikan University |
| Date | 2014-05-23 |
| Paper # | SIP2014-21,IE2014-21,PRMU2014-21,MI2014-21 |
| Volume (vol) | vol.114 |
| Number (no) | 40 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |