Learning Cross-Media Joint Representation With Sparse and Semisupervised Regularization

By Xiaohua Zhai, Yuxin Peng, Jianguo Xiao. 2014

275 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Liang Wang
3. Jing Zhang
4. Heng Tao Shen
5. Xuelong Li
6. Tien-Ping Tan
7. Xing Xu
8. Ran He

In Multimodal Learning

1. Heng Tao Shen
2. Xing Xu
3. Liang Wang
4. Kaiye Wang
5. Shu Wu
6. Qiyue Yin
7. Yang Yang
8. Alan Hanjalic

Citations in the corpus

• Fine-Grained Image Classification via Combining Vision and Language (2017, methodology): “Zhai et al. [24] propose to learn projection functions by the metric learning, and this method is further improved as Joint Representation Learning (JRL) [ 25] by adding other information such as semantic categories and semi-supervised information.”
• Adversarial Cross-Modal Retrieval (2017, methodology): “In this category, several subclasses of approaches can be distinguished: unsupervised [1, 5, 9, 29, 36], pair-wise [5, 11, 25, 43], ranking-based [33, 39] and supervised [7, 30, 31, 40] ones.”
• Learning Cross-Modal Common Representations by Private–Shared Subspaces Separation (2020, methodology): “To tackle this problem, several methods [14], [28], [29] leverage unlabeled images or documents that can be easily crawled on the web to construct partially labeled graph, which further boost the common representation learning performance.”
• Cross-modal deep metric learning with multi-task regularization (2017, methodology): “8 state-of-the-art cross-modal retrieval methods are used for comparison: CCA [1], CFA [4], KCCA [18] (with Poly and RBF kernel functions), Bimodal AE [8], Multimodal DBN [19], Corr-AE [13], JRL [5] and CMDN [10].”
• Scalable Deep Multimodal Learning for Cross-Modal Retrieval (2019, methodology): “Image → Text Text → Image Average MCCA [33] 0.510 0.525 0.517 ml-CCA [31] 0.527 0.532 0.530 GMLDA [35] 0.582 0.577 0.580 JRL [41] 0.634 0.652 0.643 MvDA-VC [12] 0.604 0.616 0.610 GSS-SL [43] 0.640 0.659 0.650 DCCA [2] 0.524 0.541 0.533 DCCAE [40] 0.525 0.542 0.534 ACMR [38] 0.658 0.663 0.661…”
• Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge (2019, methodology): “Additionally, since images and text belong to different domains, it is difficult to directly project them into the same feature space [18, 34, 41].”
• An Overview of Cross-Media Retrieval: Concepts, Methodologies, Benchmarks, and Challenges (2017, methodology): “For example, the results of CMCP, JGRHML and JRL are close to each other on bi-modality cross-media retrieval, while JRL clearly outperforms CMCP and JGRHML on multimodality cross-media retrieval.”
• Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval (2016, methodology): “Besides these three kinds of methods, there are some other methods [40], [41], [42], [43], [44], [45] proposed for the cross-modal problem, such as the dictionary learning method [40], the graph-based learning method [42], the”
• Deep Supervised Cross-Modal Retrieval (2019, methodology): “To verify the effectiveness of our proposed methods, we compare the proposed method with ten state-of-the-art methods in the experiments, including five traditional methods, namely CCA [8], MCCA [27], MvDA [10], MvDAVC [11] and JRL [40], as well as five deep learning-based methods, namely CMDN [19],”
• Confederated Machine Learning on Horizontally and Vertically Separated Medical Data for Large-Scale Health System Intelligence (2019, methodology): “2014)​, we propose a confederated machine learning method that trains machine learning models on data both horizontally and vertically separated by jointly learning a high level representation from data distributed across silios​(Qi et al. 2017; Zhang & Xiao 2015; Zhai et al. 2014)​require frequent ”
• A Comprehensive Survey on Cross-modal Retrieval (2016, methodology): “…[41], DT-RNNs [42], Deep Fragment [43], C 2 MLR [44] Supervised methods Subspace learning methods CDFE [45], GMA [15], I 2 SCA [46], PFAR [47], JRL [48], SliM 2 [49], cluster-CCA [50], CCA-3V [51], LCFS [52], JFSSL [53] Topic model SupDocNADE [54], NPBUS [55], M 3 R [56] Deep learning methods…”