• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.41-68
• /
• 2019

Multi-view learning considers data from various viewpoints as well as attempts to integrate various information from data. Multi-view learning has been studied recently and has showed superior performance to a model learned from only a single view. With the introduction of deep learning techniques to a multi-view learning approach, it has showed good results in various fields such as image, text, voice, and video. In this study, we introduce how multi-view learning methods solve various problems faced in human behavior recognition, medical areas, information retrieval and facial expression recognition. In addition, we review data integration principles of multi-view learning methods by classifying traditional multi-view learning methods into data integration, classifiers integration, and representation integration. Finally, we examine how CNN, RNN, RBM, Autoencoder, and GAN, which are commonly used among various deep learning methods, are applied to multi-view learning algorithms. We categorize CNN and RNN-based learning methods as supervised learning, and RBM, Autoencoder, and GAN-based learning methods as unsupervised learning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5546-5559
• /
• 2019

Facial action units (AUs) have recently drawn increased attention because they can be used to recognize facial expressions. A variety of methods have been designed for frontal-view AU detection, but few have been able to handle multi-view face images. In this paper we propose a method for multi-view facial AU detection using a fused multilayer, multi-task, and multi-label deep learning network. The network can complete two tasks: AU detection and facial view detection. AU detection is a multi-label problem and facial view detection is a single-label problem. A residual network and multilayer fusion are applied to obtain more representative features. Our method is effective and performs well. The F1 score on FERA 2017 is 13.1% higher than the baseline. The facial view recognition accuracy is 0.991. This shows that our multi-task, multi-label model could achieve good performance on the two tasks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4317-4335
• /
• 2018

Semi-supervised multi-view latent space learning is gaining considerable popularity recently in many machine learning applications due to the high cost and difficulty to obtain the large amount of label information of data. Although some semi-supervised multi-view latent space learning methods have been presented, there is still much space for improvement: 1) How to learn latent discriminant intact feature representations by employing data of multiple views; 2) How to exploit the manifold structure of both labeled and unlabeled point in the learned latent intact space effectively. To address the above issues, we propose an approach called semi-supervised multi-view manifold discriminant intact space learning ($SM^2DIS$) for image classification in this paper. $SM^2DIS$ aims to seek a manifold discriminant intact space for data of different views by making use of both the discriminant information of labeled data and the manifold structure of both labeled and unlabeled data. Experimental results on MNIST, COIL-20, Multi-PIE, and Caltech-101 databases demonstrate the effectiveness and robustness of our proposed approach.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.174-184
• /
• 2022

3D human pose estimation models can be classified into a multi-view model and a single-view model. In general, the multi-view model shows superior pose estimation performance compared to the single-view model. In the case of the single-view model, the improvement of the 3D pose estimation performance requires a large amount of training data. However, it is not easy to obtain annotations for training 3D pose estimation models. To address this problem, we propose a method to generate pseudo ground-truths of multi-view human pose data from a multi-view model and exploit the resultant pseudo ground-truths to train a single-view model. In addition, we propose a multi-view consistency loss function that considers the consistency of poses estimated from multi-view images, showing that the proposed loss helps the effective training of single-view models. Experiments using Human3.6M and MPI-INF-3DHP datasets show that the proposed method is effective for training single-view 3D human pose estimation models.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1179-1191
• /
• 2019

We design an ingenious view-pooling method named learning-based multiple pooling fusion (LMPF), and apply it to multi-view convolutional neural network (MVCNN) for 3D model classification or retrieval. By this means, multi-view feature maps projected from a 3D model can be compiled as a simple and effective feature descriptor. The LMPF method fuses the max pooling method and the mean pooling method by learning a set of optimal weights. Compared with the hand-crafted approaches such as max pooling and mean pooling, the LMPF method can decrease the information loss effectively because of its "learning" ability. Experiments on ModelNet40 dataset and McGill dataset are presented and the results verify that LMPF can outperform those previous methods to a great extent.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.142-148
• /
• 2003

Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By ap-plying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic net-work for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

• Journal of the Korea Society for Simulation
• /
• v.3 no.2
• /
• pp.69-76
• /
• 1994

Traditionally, simulation-based learning games which are known as flight-simulators have been constructed as a black-box game. Within a black-box game, game-players can view and modify only a part of model parameters. Game-players cannot change the structure of a simulation model. In a black-box game, game-players cannot understand and learn the system structure which is responsible for the system behavior. In this paper, the multi-tasking at the level of operating systems is exploited to enhance the transparency of simulation-based learning game. The white-box game or transparent-box game allows game-players ot view and modify the model structure. The multi-tasking solution for white-box learning game is implemented with Smalltalk language on MS-/windows operating system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.4-7
• /
• 2022

Recently, multi-view depth estimation methods using deep learning network for the 3D scene reconstruction have gained lots of attention. Multi-view video contents have various characteristics according to their camera composition, environment, and setting. It is important to understand these characteristics and apply the proper depth estimation methods for high-quality 3D reconstruction tasks. The camera setting represents the physical distance which is called baseline, between each camera viewpoint. Our proposed methods focus on deciding the appropriate depth estimation methodologies according to the characteristics of multi-view video contents. Some limitations were found from the empirical results when the existing multi-view depth estimation methods were applied to a divergent or large baseline dataset. Therefore, we verified the necessity of obtaining the proper number of source views and the application of the source view selection algorithm suitable for each dataset's capturing environment. In conclusion, when implementing a deep learning-based depth estimation network for 3D scene reconstruction, the results of this study can be used as a guideline for finding adaptive depth estimation methods.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.85-92
• /
• 2021

In a face, there is much information of person's identity. Because of this property, various tasks such as expression recognition, identity recognition and deepfake have been actively conducted. Most of them use the exact frontal view of the given face. However, various directions of the face can be observed rather than the exact frontal image in real situation. The profile (side view) lacks information when comparing with the frontal view image. Therefore, if we can generate the frontal face from other directions, we can obtain more information on the given face. In this paper, we propose a combined style model based the conditional generative adversarial network (cGAN) for generating the frontal face from multi-view images that consist of characteristics that not only includes the style around the face (hair and beard) but also detailed areas (eye, nose, and mouth).