Robust and scalable aggregation of local features for ultra large-scale retrieval
Husain, Syed and Bober, Miroslaw (2014) Robust and scalable aggregation of local features for ultra large-scale retrieval In: nternational Conference on Image Processing (ICIP), Paris, 2014, 27-30 October 2014, Paris.
Text (Paper in pdf format)
ROBUST AND SCALABLE AGGREGATION_Husain_Bober_Author_version_ICIP2014.pdf - Accepted version Manuscript
Download (639kB) | Preview
This paper is concerned with design of a compact, binary and scalable image representation that is easy to compute, fast to match and delivers beyond state-of-the-art performance in visual recognition of objects, buildings and scenes. A novel descriptor is proposed which combines rank-based multi-assignment with robust aggregation framework and cluster/bit selection mechanisms for size scalability. Extensive performance evaluation is presented, including experiments within the state-of-the art pipeline developed by the MPEG group standardising Compact Descriptors for Visual Search (CVDS).
|Item Type:||Conference or Workshop Item (Conference Paper)|
|Divisions :||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Date :||27 October 2014|
|Identification Number :||https://doi.org/10.1109/ICIP.2014.7025566|
|Related URLs :|
|Depositing User :||Miroslaw Bober|
|Date Deposited :||20 Mar 2015 10:36|
|Last Modified :||20 Mar 2015 10:36|
Actions (login required)
Downloads per month over past year