Learning Cross-Media Joint Representation With Sparse and Semisupervised Regularization

@article{Zhai2014LearningCJ,
  title={Learning Cross-Media Joint Representation With Sparse and Semisupervised Regularization},
  author={Xiaohua Zhai and Yuxin Peng and J. Xiao},
  journal={IEEE Transactions on Circuits and Systems for Video Technology},
  year={2014},
  volume={24},
  pages={965-978}
}
Cross-media retrieval has become a key problem in both research and application, in which users can search results across all of the media types (text, image, audio, video, and 3-D) by submitting a query of any media type. How to measure the content similarity among different media is the key challenge. Existing cross-media retrieval methods usually focus on modeling the pairwise correlation or semantic information separately. In fact, these two kinds of information are complementary to each… Expand
Semi-Supervised Cross-Media Feature Learning With Unified Patch Graph Regularization
TLDR
A semi-supervised cross-media feature learning algorithm with unified patch graph regularization (S2UPG) that fully exploits cross- media unlabeled instances and their patches, which can increase the diversity of training data and boost the accuracy of cross- Media retrieval. Expand
Cross-media retrieval based on semi-supervised regularization and correlation learning
TLDR
This work proposes a novel feature learning algorithm for cross-media retrieval, called semi-supervised regularization and correlation learning (SSRCL), which is capable of modeling multiple types of media simultaneously, and considers both semantic category similarity and dissimilarity simultaneously. Expand
Cross-Media Feature Learning Framework with Semi-supervised Graph Regularization
TLDR
A novel feature learning algorithm for cross- media data, called cross-media feature learning frame-work with semi-supervised graph regularization (FLGR), which calculates the similarity matrix based on the distances between the projected instances that can not only accurately protect the relevance of multimedia data, but also effectively reduce the computational time of the algorithm. Expand
Semisupervised Cross-Media Retrieval by Distance-Preserving Correlation Learning and Multi-modal Manifold Regularization
TLDR
A novel distance-preserving correlation learning and multi-modal manifold regularization approach to exploit the common representation of heterogeneous data for cross-media retrieval, compared with the state-of-the-art methods. Expand
Cross-Media Correlation Analysis with Semi-supervised Graph Regularization
TLDR
A novel algorithm for cross- media data, called cross-media correlation analysis with semi-supervised graph regularization (CMCA), which can not only take full advantage of both the media instances and their patches in one graph, but also explore the similarity matrix which can improve the correlation between data. Expand
Attention-Sharing Correlation Learning for Cross-Media Retrieval
TLDR
Inspired by attention mechanism, this paper proposes the attention-sharing correlation learning network, which is an end-to-end network to generate cross-media common representation for retrieval, which can not only emphasize the single-media discriminative parts, but also enhance the cross- media fine-grained consistent pattern, and so learn more precious cross- Media correlation to improve retrieval accuracy. Expand
Cross-Media Retrieval by Multimodal Representation Fusion with Deep Networks
TLDR
A deep multimodal learning method (DML) for cross-media shared representation learning is proposed, which can obtain the high-level semantic representation of single media. Expand
Semi-supervised cross-modal common representation learning with vector-valued manifold regularization
TLDR
This paper proposes a novel feature learning algorithm, which is semi-supervised cross-modal vector-valued manifold regularization (SCVM), to explore common representation of heterogeneous data. Expand
Semi-Supervised Learning Based Semantic Cross-Media Retrieval
TLDR
A Semi-Supervised learning based Semantic Cross-Media Retrieval (S3CMR) method aiming at the above problems, which demonstrates that the proposed method outperforms eight state-of-the-art cross-media retrieval methods. Expand
Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval
  • K. Wang, R. He, Liang Wang, Wei Wang, T. Tan
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2016
TLDR
An iterative algorithm is presented to solve the proposed joint learning problem, along with its convergence analysis, and Experimental results on cross-modal retrieval tasks demonstrate that the proposed method outperforms the state-of-the-art subspace approaches. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 36 REFERENCES
Ranking with local regression and global alignment for cross media retrieval
TLDR
A novel ranking algorithm, namely ranking with Local Regression and Global Alignment (LRGA), which learns a robust Laplacian matrix for data ranking and a unified objective function to globally align the local models from all the data points so that an optimal ranking value can be assigned to each data point. Expand
Learning cross-modality similarity for multinomial data
TLDR
The model can be seen as a Markov random field of topic models, which connects the documents based on their similarity, and the topics learned with the model are shared across connected documents, thus encoding the relations between different modalities. Expand
Mining Semantic Correlation of Heterogeneous Multimedia Data for Cross-Media Retrieval
TLDR
This paper proposes a method of transductive learning to mine the semantic correlations among media objects of different modalities so that to achieve the cross-media retrieval. Expand
Harmonizing Hierarchical Manifolds for Multimedia Document Semantics Understanding and Cross-Media Retrieval
TLDR
A Laplacian media object space is constructed for media object representation of each modality and an MMD semantic graph is constructed to perform cross-media retrieval and different methods are proposed to utilize relevance feedback. Expand
A new approach to cross-modal multimedia retrieval
TLDR
It is shown that accounting for cross-modal correlations and semantic abstraction both improve retrieval accuracy and are shown to outperform state-of-the-art image retrieval systems on a unimodal retrieval task. Expand
Effective Heterogeneous Similarity Measure with Nearest Neighbors for Cross-Media Retrieval
TLDR
A novel heterogeneous similarity measure with nearest neighbors (HSNN) is proposed which could compute the similarity between media objects with different media types and shows to outperform image retrieval systems on a unimedia retrieval task. Expand
Multimedia content processing through cross-modal association
TLDR
This paper investigates different cross-modal association methods using the linear correlation model, and introduces a novel method for cross- modal association called Cross-modAL Factor Analysis (CFA), which shows several advantages in analysis performance and feature usage. Expand
A Discriminative Kernel-based Model to Rank Images from Text Queries
This paper introduces a discriminative model for the retrieval of images from text queries. Our approach formalizes the retrieval task as a ranking problem, and introduces a learning procedureExpand
A Discriminative Kernel-Based Approach to Rank Images from Text Queries
This paper introduces a discriminative model for the retrieval of images from text queries. Our approach formalizes the retrieval task as a ranking problem, and introduces a learning procedureExpand
Cross-modality correlation propagation for cross-media retrieval
  • Xiaohua Zhai, Yuxin Peng, J. Xiao
  • Mathematics, Computer Science
  • 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2012
TLDR
This paper proposes a novel cross-modality correlation propagation approach to simultaneously deal with positive correlation and negative correlation between media objects of different modalities, while existing works focus solely on the positive correlation. Expand
...
1
2
3
4
...