Representation Of Multiple Views Research Articles

Robust multi-view learning via M-estimator joint sparse representation

Recently, multi-view learning has achieved extraordinary success in many research areas such as pattern recognition and data mining. Most existing multi-view methods mainly focus on exploring the correlation information between different views and their performance may severely degrade in the presence of heavy noises and outliers. In this paper, we put forward a robust multi-view joint sparse representation (RMJSR) method for multi-view learning. Firstly, we design a novel multi-view Cauchy estimator based loss function originating from robust statistics to address complex noises and outliers in reality. Based on this, we leverage the ℓ1,q norm to enhance our model by encouraging the learned representation of multiple views to share the same sparsity pattern. Secondly, to explore the optimal solution for the RMJSR model, we devise an effective optimization algorithm based on the half-quadratic (HQ) theory and the alternating direction method of multipliers (ADMM) framework. Thirdly, we provide the theoretical guarantee for revealing the theoretical condition for the success of the proposed method. Further, we have also provided extensive analysis of the proposed method, including the optimality condition, convergence analysis, and complexity analysis. Extensive experimental results validate the effectiveness and robustness of the proposed method in comparison with state-of-the-art competitors. The source code is available at https://github.com/Huyutao7/RMJSRC.

Learning View-Based Graph Convolutional Network for Multi-View 3D Shape Analysis.

View-based approach that recognizes 3D shape through its projected 2D images has achieved state-of-the-art results for 3D shape recognition. The major challenges are how to aggregate multi-view features and deal with 3D shapes in arbitrary poses. We propose two versions of a novel view-based Graph Convolutional Network, dubbed view-GCN and view-GCN++, to recognize 3D shape based on graph representation of multiple views. We first construct view-graph with multiple views as graph nodes, then design two graph convolutional networks over the view-graph to hierarchically learn discriminative shape descriptor considering relations of multiple views. Specifically, view-GCN is a hierarchical network based on two pivotal operations, i.e., feature transform based on local positional and non-local graph convolution, and graph coarsening based on a selective view-sampling operation. To deal with rotation sensitivity, we further propose view-GCN++ with local attentional graph convolution operation and rotation robust view-sampling operation for graph coarsening. By these designs, view-GCN++ achieves invariance to transformations under the finite subgroup of rotation group SO(3). Extensive experiments on benchmark datasets (i.e., ModelNet40, ScanObjectNN, RGBD and ShapeNet Core55) show that view-GCN and view-GCN++ achieve state-of-the-art results for 3D shape classification and retrieval tasks under aligned and rotated settings.

JLCRB: A unified multi-view-based joint representation learning for CircRNA binding sites prediction

CircRNAs usually bind to the corresponding RBPs(RNA Binding proteins) and play a key role in gene regulation. Therefore, it is important to identify the binding sites of RBPs on CircRNAs for the regulation of certain diseases. Due to the information provided by the single view feature is limited, the current mainstream methods are mainly to detect the RBP binding sites by constructing multi-view models. However, with the number of view features increases, the invalid information also increases, and the existing methods only simply concatenate together various features from different views, while ignoring the intrinsic connection between multi-view data. To solve this problem, we propose a new multi-view joint representation learning network by improving the consistency of multi-view feature information. First, the network uses different feature encoding methods to fully extract the feature information of RNA, respectively. Then we construct the intrinsic connection between the views by generating a global joint representation of multiple views, and this is used for feature calibration of each view to highlight important features and suppress unimportant ones. Finally, the depth features obtained from the fusion of multiple views are used to detect the binding sites of RNAs. The average AUC of our method is 93.68% in 37 CircRNA-RBP datasets. The experimental results show that the prediction performance of the method is better than existing methods. The code and datasets are obtained at https://github.com/Xuezg/JLCRB. In addition, we also provide a free web server that is freely available at http://82.157.188.204/JLCRB/.

Maneuvers of Multi Perspective Media Retrieval

Recently, Learning Machines have achieved a measure of success in the representation of multiple views. Since the effectiveness of data mining methods is highly dependent on the ability to produce data representation, learning multi-visual representation has become a very promising topic with widespread use. It is an emerging data mining guide that looks at multidisciplinary learning to improve overall performance. Multi-view reading is also known as data integration or data integration from multiple feature sets. In general, learning the representation of multiple views is able to learn the informative and cohesive representation that leads to the improvement in the performance of predictors. Therefore, learning multi-view representation has been widely used in many real-world applications including media retrieval, native language processing, video analysis, and a recommendation program. We propose two main stages of learning multidisciplinary representation: (i) alignment of multidisciplinary representation, which aims to capture relationships between different perspectives on content alignment; (ii) a combination of different visual representations, which seeks to combine different aspects learned from many different perspectives into a single integrated representation. Both of these strategies seek to use the relevant information contained in most views to represent the data as a whole. In this project we use the concept of canonical integration analysis to get more details. Encouraged by the success of in-depth reading, in-depth reading representation of multiple theories has attracted a lot of attention in media access due to its ability to read explicit visual representation.

Unsupervised multi-view representation learning with proximity guided representation and generalized canonical correlation analysis

Multi-view data can collaborate with each other to provide more comprehensive information than single-view data. Although there exist a few unsupervised multi-view representation learning methods taking both the discrepancies and incorporating complementary information from different views into consideration, they always ignore the use of inner-view discriminant information. It remains challenging to learn a meaningful shared representation of multiple views. To overcome this difficulty, this paper proposes a novel unsupervised multi-view representation learning model, MRL. Unlike most state-of-art multi-view representation learning, which only can be used for clustering or classification task, our method explores the proximity guided representation from inner-view and complete the task of multi-label classification and clustering by the discrimination fusion representation simultaneously. MRL consists of three parts. The first part is a deep representation learning for each view and then aims to represent the latent specific discriminant characteristic of each view, the second part builds a proximity guided dynamic routing to preserve its inner features of direction,location and etc. At last, the third part, GCCA-based fusion, exploits the maximum correlations among multiple views based on Generalized Canonical Correlation Analysis (GCCA). To the best of our knowledge, the proposed MRL could be one of the first unsupervised multi-view representation learning models that work in proximity guided dynamic routing and GCCA modes. The proposed model MRL is tested on five multi-view datasets for two different tasks. In the task of multi-label classification, the results show that our model is superior to the state-of-the-art multi-view learning methods in precision, recall, F1 and accuracy. In clustering task, its performance is better than the latest related popular algorithms. And the performance varies w.r.t. the dimensionality of G is also made to explore the characteristics of MRL.

Latent Semantic Aware Multi-View Multi-Label Classification

For real-world applications, data are often associated with multiple labels and represented with multiple views. Most existing multi-label learning methods do not sufficiently consider the complementary information among multiple views, leading to unsatisfying performance. To address this issue, we propose a novel approach for multi-view multi-label learning based on matrix factorization to exploit complementarity among different views. Specifically, under the assumption that there exists a common representation across different views, the uncovered latent patterns are enforced to be aligned across different views in kernel spaces. In this way, the latent semantic patterns underlying in data could be well uncovered and this enhances the reasonability of the common representation of multiple views. As a result, the consensus multi-view representation is obtained which encodes the complementarity and consistence of different views in latent semantic space. We provide theoretical guarantee for the strict convexity for our method by properly setting parameters. Empirical evidence shows the clear advantages of our method over the state-of-the-art ones.

Intelligent agents for feature modelling in computer aided design

Abstract CAD modelling can be referred to as the process of generating an integrated multiple view model as a representation of multiple views of engineering design. In many situations, a change in the model of one view may conflict with the models of other views. In such situations, the model of some views needs to be adapted in order to make all models consistent. Thus, CAD models should be capable of adapting themselves to new situations. Recently, agent based technologies have been considered in order to increase both knowledge level and intelligence of real and virtual objects. The contribution of this paper consists in introducing the intelligent agents in intelligent CAD modelling. The proposed agents are elementary geometrical and topological objects. They incorporate the functions of observation, decision and action, and possess their own knowledge. Agents have the capacity of communication and inference based on the feature grammars. They are modelled as bio-dynamic objects that enjoy the properties of fusion, division and multiplication. Being aware of the context, the proposed agents interact to form potential regional transitory communities, called regions. Being aware of their belonging in a region, agents interact by generating virtual links (virtual extensions). These virtual links produce: (a) fusion of agents, (b) division of agents and c) multiplication of agents. The emerged agents interact with the other agents in a region to recognize each other and to form specific sub-communities, called intelligent features. From a CAD software development point of view, this paper advocates the idea of a new phase of CAD system development based on the agent-oriented programming (AOP) paradigm. Highlights This paper proposes the agent paradigm for intelligent CAD modelling. Second section presents the state of art. In the third section, using the linguistic hypothesis of product design, a feature modelling formalism is presented. Fourth section presents a formal model for agent modelling. In the fifth section, agents for feature generation and modelling are formalised and modelled. The sixth section presents the application of the method. Finally, in the last section, the conclusion and future developments are proposed.

Multiview Video Coding Optimization using SIMD on Portable Devices

Multimedia support on hand-held devices is growing rapidly. The introduction of 3D videos in cinemas and on home entertainment systems has made it appealing on mobile environment devices. MVC (Multiview Video Coding) provides a compressed representation of multiple views in a single scene. However, handheld devices have hardware constraints that makes it challenging to support highdefinition content and increases the complexity of the algorithms used. Due to this, an advanced processor with the capabilities of low power consumption and high instruction computation is needed. Compression standards such as H.264/MPEG-4 and its amendment, AVC (Advanced Video Coding), have had great success in video compression. However, more complex algorithms and significantly higher processing power are necessary. As an extension to this standard, MVC was introduced for 3D stereo video support. Conventional processors contain coprocessors that support Single Instruction and Multiple Data technology. Some arithmetic operations are also supported on the main processor. Therefore these features can reduce the decoding time of the MVC decoding process. General Terms Multiview video coding, Video codec, SIMD, H.264 codec, Decoder, Standards, Optimization

Hierarchy-oriented modeling of enterprise architecture using reference-model of open distributed processing

Modeling Enterprise Architecture (EA) requires the representation of multiple views for an enterprise. This could be done by a team of stakeholders that essentially have different backgrounds. One way to do this is to structure the model into hierarchical levels each of which can be of interest to just some, not all, stakeholders. Due to the multidisciplinary nature of EA, stakeholders simply cannot choose a single modeling approach, even a widely-recognized one, to build their enterprise model and make it viewable and understandable to the whole team. Developing a modeling framework that can be applied uniformly throughout the entire enterprise model and that can be used by all stakeholders is thus challenging. We based our work on the RM-ODP (Reference Model of Open Distributed Processing) – a standardization effort that defines essential concepts for modeling distributed systems, as well as ODP-related international standards/recommendations, to develop such a modeling framework that we call SeamCAD. This framework consists of a computer-aided tool and a language behind the tool for modeling EA in a hierarchical manner. SeamCAD makes RM-ODP applicable in the context of multi-level EA and consolidates the SEAM – a family of methods for seamless integration between disciplines.

A Multiple View Assembly Process Representation Based on Three Dimensional Models

In order to effectively represent assembly process information based on three dimensional (3D) models and rapidly extract the necessary information for assembly process planning, analysis and simulation, this paper aims to research the multiple view representation of assembly process information based on 3D models. Assembly process information based on 3D models is summarized and considered as the single source of the multiple view representation. The definition and organization of assembly process view is defined to implement assembly process representation based on view. Assembly process views based on assembly process planning work flow are established. View mapping approach is investigated to rapidly extract the necessary information for assembly process planning, analysis and simulation. The use of the multiple view assembly process representation is illustrated by building detailed assembly process view and assembly process simulation view and by extracting relevant information for the assembly process simulation view from detailed assembly process view.

Aspect graph generation for non-convex polyhedra from perspective projection view

The aspect graph is basically a multiple-view representation of the designated three-dimensional (3D) object. In this paper, a complete algorithm is presented for constructing the aspect graph of general polyhedral objects from the perspective point of view. The aspect graph generation is based on a so-called visual event. These visual events will completely capture the way the appearance of an edge or a face can be occluded by other faces and edges in the model. All the visual events can be found for polyhedra as facial, EE, and EEE events. The facial event indicates the visibility transition of the faces, the EE event indicates the possible visibility variation of the occlusion of two edges, and the EEE event represents another visibility change, the consecutive occlusion among three edges. The system consists of the following five stages: (1) find the viewing cell for each planar face, EE event, and EEE event and then create the “parcellation graph”; (2) employ the parcellation graph to create a “face-level enumeration array” and “edge-level enumeration array”; (3) generate test points; (4) examine plausible cells that enclose a volume of viewing space; and (5) generate an explicit aspect graph structure. Finally, nine non-convex polyhedra are obtained in the experiments. The aspect graphs of these non-regular shaped objects can be easily generated by this system.

A self-organizing multiple-view representation of 3D objects

We explore representation of 3D objects in which several distinct 2D views are stored for each object. We demonstrate the ability of a two-layer network of thresholded summation units to support such representations. Using unsupervised Hebbian relaxation, the network learned to recognize ten objects from different viewpoints. The training process led to the emergence of compact representations of the specific input views. When tested on novel views of the same objects, the network exhibited a substantial generalization capability. In simulated psychophysical experiments, the network's behavior was qualitatively similar to that of human subjects.

Modeling a class of 3-D objects using cycles of a graph

This paper describes a new multiple-view representation scheme for modeling 3-D planar faced objects. In this approach, each 3-D model is represented by a small set of 2-D views called the Distinct Region Views (DRV). These DRV's will comprise all the possible 2-D views of the 3-D model in the topological sense. Each DRV is decomposed into a complete set of cycles and a shape descriptor for each of the cycles is acquired. A four-level ordered rooted tree is employed to represent each 3-D model. The first level of the tree represents the object label, the second level represents all the possible DRV's, the third level represents the cycles of each DRV and the fourth level represents the shape descriptor of each cycle. The representation is suitable for recognizing 3-D objects from their 2-D views under situations such as missing lines, scaling and rotation differences and shape distortion.