TY  - JOUR
A1  - Wang, Cheng
A1  - Yang, Haojin
A1  - Meinel, Christoph
T1  - A deep semantic framework for multimodal representation learning
JF  - Multimedia tools and applications : an international journal
N2  - Multimodal representation learning has gained increasing importance in various real-world multimedia applications. Most previous approaches focused on exploring inter-modal correlation by learning a common or intermediate space in a conventional way, e.g. Canonical Correlation Analysis (CCA). These works neglected the exploration of fusing multiple modalities at higher semantic level. In this paper, inspired by the success of deep networks in multimedia computing, we propose a novel unified deep neural framework for multimodal representation learning. To capture the high-level semantic correlations across modalities, we adopted deep learning feature as image representation and topic feature as text representation respectively. In joint model learning, a 5-layer neural network is designed and enforced with a supervised pre-training in the first 3 layers for intra-modal regularization. The extensive experiments on benchmark Wikipedia and MIR Flickr 25K datasets show that our approach achieves state-of-the-art results compare to both shallow and deep models in multimodal and cross-modal retrieval.
KW  - Multimodal representation
KW  - Deep neural networks
KW  - Semantic feature
KW  - Cross-modal retrieval
Y1  - 2016
U6  - https://doi.org/10.1007/s11042-016-3380-8
SN  - 1380-7501
SN  - 1573-7721
VL  - 75
SP  - 9255
EP  - 9276
PB  - Springer
CY  - Dordrecht
ER  - 
TY  - THES
A1  - Wang, Cheng
T1  - Deep Learning of Multimodal Representations
Y1  - 2016
ER  -