Abstract | ||
---|---|---|
The Bag-Of-Visual-Words (BOVW) paradigm is fast becoming a popular image representation for Content-Based Image Retrieval (CBIR), mainly because of its better retrieval effectiveness over global feature representations on collections with images being near-duplicate to queries. In this experimental study we demonstrate that this advantage of BOVW is diminished when visual diversity is enhanced by using a secondary modality, such as text, to pre-filter images. The TOP-SURF descriptor is evaluated against Compact Composite Descriptors on a two-stage image retrieval setup, which first uses a text modality to rank the collection and then perform CBIR only on the top-K items. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1145/2009916.2010144 | SIGIR |
Keywords | Field | DocType |
global feature representation,compact composite descriptors,secondary modality,better retrieval effectiveness,global image descriptors,popular image representation,top-surf descriptor,two-stage image retrieval setup,text modality,experimental study,two-stage multimodal retrieval,content-based image,image retrieval,bag of visual words | Computer vision,Automatic image annotation,Information retrieval,Bag-of-words model in computer vision,Pattern recognition,Image texture,Computer science,Image representation,Image retrieval,Visual descriptors,Artificial intelligence,Visual Word | Conference |
Citations | PageRank | References |
3 | 0.36 | 5 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Konstantinos Zagoris | 1 | 231 | 17.12 |
Savvas A. Chatzichristofis | 2 | 810 | 44.88 |
Avi Arampatzis | 3 | 443 | 39.38 |