Name
Abstract | ||
|---|---|---|
We tackle the problem of mobile visual search. Moving pictures experts group (MPEG) has completed a standard named compact descriptor for visual search (CDVS) to provide a standardized syntax in the context of image retrieval application. CDVS applies principal components analysis to reduce the dimension of local feature descriptor as the input of global descriptor pipeline, and utilizes traditional fisher vector as the local feature descriptor aggregation algorithm. However, the descriptor components of SIFT and Fisher Vector (FV) have highly non-Gaussian statistics, and applying a single PCA transform can in-fact hurt compression performance at high rates. We develop a net-based architecture combining neural networks with FV layer to obtain fisher vector. There are two advantages in our architecture comparing with CDVS global descriptor pipeline. One is that we employ "autoencoder" networks to reduce the dimensionality of data, the other is that we exploit a trainable system to learn parameters after the FV codebook obtained. The experiments demonstrate an obvious advantage of our proposed architecture in terms of CDVS retrieval task. |
Year | Venue | Keywords |
|---|---|---|
2017 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | CDVS, mobile visual search, Fisher Vector, autoencoder, fisher layer |
Field | DocType | ISSN |
Computer vision,Scale-invariant feature transform,Visual search,Autoencoder,Pattern recognition,Computer science,Image retrieval,Curse of dimensionality,Artificial intelligence,Artificial neural network,Principal component analysis,Codebook | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chen Huang | 1 | 6 | 4.16 |
| Shengchuan Zhang | 2 | 1 | 1.36 |
| Xianming Lin | 3 | 1 | 2.04 |
| Xiangrong Liu | 4 | 9 | 4.27 |
| Rongrong Ji | 5 | 3616 | 189.98 |