Large-Margin Multi-ViewInformation Bottleneck

By Chang Xu, Dacheng Tao, Chao Xu. 2014

258 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Dual Contrastive Prediction for Incomplete Multi-View Representation Learning (2022, methodology): “In recent years, some efforts have been devoted to the problem of multi-view representation learning based on information theory [35], [36], [41], [42], [43], [44], [45].”
Learning Visual Semantic Relationships for Efficient Visual Retrieval (2015, background): “Moreover, to facilitate large-scale image retrieval and other multimedia-related applications [8], [9], [10], [11], [12], [13], efficient indexing techniques are in great demand as well.”
Multicolumn Bidirectional Long Short-Term Memory for Mobile Devices-Based Human Activity Recognition (2016, background): “Although k-NN is simple in concept, the classification accuracy is still relatively good [3], [28], [42].”
On Unifying Multi-view Self-Representations for Clustering by Tensor Multi-rank Minimization (2016, background): “To extend the self-representation based subspace clustering to multi-view setting, Zhang et al. (2015) introduced a low-rank tensor constraint (Liu et al.”
General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer (2017, background): “The feature spaces of source and target domains can be quite different and there is sometimes semantic gap between them (e.g. text and visual features) [Xu et al., 2014; 2015].”
Information Bottleneck Domain Adaptation with Privileged Information for Visual Recognition (2016, background): “Compared to multi-view and multi-task learning [14, 46, 18, 34, 49], instead, rather than having all views or task labels available or predicted during testing, here one view is missing, and a single task label is predicted based on a biased view.”
Bilinear heterogeneous information machine for RGB-D action recognition (2015, background): “Furthermore, human bodies consist of multiple structural objects, and thus motions of human body parts are highly correlated.”
Robust Face Recognition via Multimodal Deep Face Representation (2015, background): “Multimodal systems that fuse multiple feature cues are also employed in other topics of multimedia and computer vision, e . g ., visual tracking [20], image classiﬁcation [21], [22], [23], and social media analysis [24], [25], [26], [27], [28].”
Diversity-induced Multi-view Subspace Clustering (2015, background): “Therefore, multiple views can be employed to comprehensively and accurately describe the data [30] [31].”
Information Bottleneck Learning Using Privileged Information for Visual Recognition (2016, background): “Indeed, our problem is more related to multi-view and multi-task learning [9, 40, 14, 28, 45].”
GMC: Graph-Based Multi-View Clustering (2020, background): “Apart from clustering, multi-view learning methods and applications have been investigated in [45], [46], [47], [48], [49], [50], to list a few.”
Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval (2016, background): “Although much attention has been paid to multimodal data analysis [1], [2], [3], [4], the common strategy is to integrate multiple modalities to improve”
Cross-Modality Submodular Dictionary Learning for Information Retrieval (2014, background): “, are considered somewhat outdated, multimodal systems [37], [9], [44] become popular for information retrieval.”
Generalized Latent Multi-View Subspace Clustering (2020, background): “Based on the ubiquitous multi-view data, multi-view learning [21], [22], [23], [24], [25] has shown remarkable success in a wide range of real-world applications.”
Understanding Blooming Human Groups in Social Networks (2015, background): “studied the multi-view learning [18] [19] and scene classification [20].”
Trusted Multi-View Classification With Dynamic Evidential Fusion (2022, methodology): “These methods are typically built on complex models [1], [2], [3], [4], [5], [6], [7] (usually integrating differ-”