Generalized Multi-view Embedding for Visual Recognition and Cross-modal Retrieval
Cao, Guanqun; Iosifidis, Alexandros; Chen, Ke; Gabbouj, Moncef (2018-09)
Cao, Guanqun
Iosifidis, Alexandros
Chen, Ke
Gabbouj, Moncef
09 / 2018
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tty-201907151953
https://urn.fi/URN:NBN:fi:tty-201907151953
Kuvaus
Peer reviewed
Tiivistelmä
In this paper, the problem of multi-view embed-ding from different visual cues and modalities is considered. We propose a unified solution for subspace learning methods using the Rayleigh quotient, which is extensible for multiple views, supervised learning, and non-linear embeddings. Numerous methods including Canonical Correlation Analysis, Partial Least Square regression and Linear Discriminant Analysis are studied using specific intrinsic and penalty graphs within the same framework. Non-linear extensions based on kernels and (deep) neural networks are derived, achieving better performance than the linear ones. Moreover, a novel Multi-view Modular Discriminant Analysis (MvMDA) is proposed by taking the view difference into consideration. We demonstrate the effectiveness of the proposed multi-view embedding methods on visual object recognition and cross-modal image retrieval, and obtain superior results in both applications compared to related methods.
Kokoelmat
- TUNICRIS-julkaisut [16726]