TIIS (한국인터넷정보학회)
Current Result Document : 1 / 5
| 한글제목(Korean Title) |
Enhanced VLAD |
| 영문제목(English Title) |
Enhanced VLAD |
| 저자(Author) |
Benchang Wei
Tao Guan1
Yawei Luo
Liya Duan
Junqing Yu
|
| 원문수록처(Citation) |
VOL 10 NO. 07 PP. 3272 ~ 3285 (2016. 07) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Recently, Vector of Locally Aggregated Descriptors (VLAD) has been proposed to index image by compact representations, which encodes powerful local descriptors and makes significant improvement on search performance with less memory compared against the state of art. However, its performance relies heavily on the size of the codebook which is used to generate VLAD representation. It indicates better accuracy needs higher dimensional representation. Thus, more memory overhead is needed. In this paper, we enhance VLAD image representation by using two level hierarchical-codebooks. It can provide more accurate search performance while keeping the VLAD size unchanged. In addition, hierarchical-codebooks are used to construct multiple inverted files for more accurate non-exhaustive search. Experimental results show that our method can make significant improvement on both VLAD image representation and non-exhaustive search.
|
| 키워드(Keyword) |
hierarchical-codebook
enhanced VLAD
projected residual vector quantization
multiple inverted files
|
| 파일첨부 |
PDF 다운로드
|
